Xeon Platinum Ubuntu 19.04 vs 21.04

2 x Intel Xeon Platinum 8280 comparison for a future article looking at the performance change over two years.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2102114-HA-CASCADE0202
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

Limit displaying results to tests within:

Bioinformatics 2 Tests
C++ Boost Tests 3 Tests
C/C++ Compiler Tests 8 Tests
CPU Massive 19 Tests
Creator Workloads 12 Tests
Database Test Suite 4 Tests
Encoding 3 Tests
Fortran Tests 5 Tests
Game Development 3 Tests
HPC - High Performance Computing 21 Tests
Common Kernel Benchmarks 2 Tests
Linear Algebra 2 Tests
Machine Learning 6 Tests
Molecular Dynamics 5 Tests
MPI Benchmarks 5 Tests
Multi-Core 21 Tests
NVIDIA GPU Compute 6 Tests
Intel oneAPI 3 Tests
OpenMPI Tests 7 Tests
Programmer / Developer System Benchmarks 5 Tests
Python 3 Tests
Renderers 4 Tests
Scientific Computing 11 Tests
Server 5 Tests
Server CPU Tests 14 Tests
Single-Threaded 4 Tests
Video Encoding 3 Tests
Common Workstation Benchmarks 4 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
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Ubuntu 19.04
February 08 2021
  9 Hours, 56 Minutes
Ubuntu 21.04 Dev
February 09 2021
  7 Hours, 28 Minutes
Ubuntu 21.04 Dev + Linux 5.11
February 10 2021
  6 Hours, 58 Minutes
Ubuntu 21.04 Dev + Linux 5.11 + GCC11
February 10 2021
  6 Hours, 45 Minutes
Invert Hiding All Results Option
  7 Hours, 47 Minutes

Only show results where is faster than
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):

Ubuntu 19.04

Processor: 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 378GB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: llvmpipe, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE

OS: Ubuntu 19.04, Kernel: 5.0.0-38-generic (x86_64), Desktop: GNOME Shell 3.32.2, Display Server: X Server 1.20.4, OpenGL: 3.3 Mesa 19.0.8 (LLVM 8.0 256 bits), Compiler: GCC 8.3.0, File-System: ext4, Screen Resolution: 1024x768

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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 powersave - CPU Microcode: 0x500002c
Python Notes: Python 2.7.16 + Python 3.7.3
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled

Ubuntu 21.04 Dev

Processor: 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 378GB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE

OS: Ubuntu 21.04, Kernel: 5.8.0-36-generic (x86_64), Desktop: GNOME Shell 3.38.2, Display Server: X Server 1.20.9, Vulkan: 1.0.2, Compiler: GCC 10.2.1 20210130, File-System: ext4, Screen Resolution: 1024x768

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-YIlI3N/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-YIlI3N/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --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
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x5003003
Python Notes: Python 3.9.1+
Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled

Ubuntu 21.04 Dev + Linux 5.11

OS: Ubuntu 21.04, Kernel: 5.11.0-051100rc7daily20210209-generic (x86_64) 20210208, Desktop: GNOME Shell 3.38.2, Display Server: X Server 1.20.9, Vulkan: 1.0.2, Compiler: GCC 10.2.1 20210130, File-System: ext4, Screen Resolution: 1024x768

Ubuntu 21.04 Dev + Linux 5.11 + GCC11

OS: Ubuntu 21.04, Kernel: 5.11.0-051100rc7daily20210209-generic (x86_64) 20210208, Desktop: GNOME Shell 3.38.2, Display Server: X Server 1.20.9, Vulkan: 1.0.2, Compiler: GCC 11.0.0 20210115, File-System: ext4, Screen Resolution: 1024x768

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"
Compiler Notes: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-snapshot-nHdSaM/gcc-snapshot-20210115/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-nHdSaM/gcc-snapshot-20210115/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --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
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x5003003
Python Notes: Python 3.9.1+
Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled

Xeon Platinum Ubuntu 19.04 vs 21.04ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionVulkanUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC112 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads)GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS)Intel Sky Lake-E DMI3 Registers378GB280GB INTEL SSDPED1D280GAllvmpipe2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbEUbuntu 19.045.0.0-38-generic (x86_64)GNOME Shell 3.32.2X Server 1.20.43.3 Mesa 19.0.8 (LLVM 8.0 256 bits)GCC 8.3.0ext41024x768ASPEEDUbuntu 21.045.8.0-36-generic (x86_64)GNOME Shell 3.38.2X Server 1.20.91.0.2GCC 10.2.1 202101305.11.0-051100rc7daily20210209-generic (x86_64) 20210208GCC 11.0.0 20210115OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseEnvironment Details- CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"Compiler Details- Ubuntu 19.04: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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 - Ubuntu 21.04 Dev: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-YIlI3N/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-YIlI3N/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --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 21.04 Dev + Linux 5.11: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-YIlI3N/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-YIlI3N/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --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 21.04 Dev + Linux 5.11 + GCC11: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-snapshot-nHdSaM/gcc-snapshot-20210115/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-nHdSaM/gcc-snapshot-20210115/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --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 Processor Details- Ubuntu 19.04: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c- Ubuntu 21.04 Dev: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x5003003- Ubuntu 21.04 Dev + Linux 5.11: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x5003003- Ubuntu 21.04 Dev + Linux 5.11 + GCC11: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x5003003Python Details- Ubuntu 19.04: Python 2.7.16 + Python 3.7.3- Ubuntu 21.04 Dev: Python 3.9.1+- Ubuntu 21.04 Dev + Linux 5.11: Python 3.9.1+- Ubuntu 21.04 Dev + Linux 5.11 + GCC11: Python 3.9.1+Security Details- Ubuntu 19.04: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled - Ubuntu 21.04 Dev: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled - Ubuntu 21.04 Dev + Linux 5.11: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled - Ubuntu 21.04 Dev + Linux 5.11 + GCC11: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled

Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11Result OverviewPhoronix Test Suite100%132%164%196%228%YafaRayFinanceBenchNAS Parallel BenchmarksNebular Empirical Analysis ToolArrayFireRedisNgspiceTimed MAFFT AlignmentKripkeASKAPLibRawDolfynRodiniaACES DGEMMPyPerformanceNumpy BenchmarkPHPBenchOpenVKLONNX RuntimeSVT-VP9MariaDBPennantLAMMPS Molecular Dynamics SimulatorSQLite SpeedtestPlaidMLTNNoneDNNKvazaarHimeno BenchmarkAppleseedChaos Group V-RAYx265Intel Open Image DenoisePyBenchOpenFOAMNAMDHigh Performance Conjugate GradientBlenderTensorFlow Lite

Xeon Platinum Ubuntu 19.04 vs 21.04openvkl: vklBenchmarkplaidml: No - Inference - VGG19 - CPUplaidml: No - Inference - ResNet 50 - CPUyafaray: Total Time For Sample Scenemysqlslap: 256mysqlslap: 512mysqlslap: 128lammps: 20k Atomsngspice: C2670openfoam: Motorbike 60Mngspice: C7552onnx: bertsquad-10 - OpenMP CPUnumpy: onnx: shufflenet-v2-10 - OpenMP CPUonnx: super-resolution-10 - OpenMP CPUtensorflow-lite: Mobilenet Floathpcg: tensorflow-lite: Mobilenet Quantrodinia: OpenMP Leukocytetensorflow-lite: NASNet Mobileopenvkl: vklBenchmarkStructuredVolumeonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUkripke: tensorflow-lite: Inception ResNet V2tensorflow-lite: SqueezeNetonnx: fcn-resnet101-11 - OpenMP CPUonnx: yolov4 - OpenMP CPUrodinia: OpenMP HotSpot3Dappleseed: Emilyblender: Classroom - CPU-Onlypyperformance: python_startuponednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUneat: pyperformance: raytracefinancebench: Bonds OpenMPv-ray: CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUopenvkl: vklBenchmarkVdbVolumepyperformance: 2to3sqlite-speedtest: Timed Time - Size 1,000financebench: Repo OpenMPhimeno: Poisson Pressure Solvernpb: EP.Daskap: tConvolve MPI - Griddingaskap: tConvolve MPI - Degriddingblender: BMW27 - CPU-Onlyaskap: Hogbom Clean OpenMPpyperformance: django_templatekvazaar: Bosphorus 4K - Very Fastnamd: ATPase Simulation - 327,506 Atomsrodinia: OpenMP Streamclusterpyperformance: regex_compilepgbench: 100 - 250 - Read Write - Average Latencypgbench: 100 - 250 - Read Writeredis: SETpyperformance: pathlibphpbench: PHP Benchmark Suitelibraw: Post-Processing Benchmarkredis: GETpyperformance: pickle_pure_pythonredis: SADDpyperformance: json_loadstnn: CPU - MobileNet v2pybench: Total For Average Test Timestnn: CPU - SqueezeNet v1.1pyperformance: chaospyperformance: crypto_pyaesdolfyn: Computational Fluid Dynamicsonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUarrayfire: Conjugate Gradient CPUkvazaar: Bosphorus 4K - Ultra Fastrodinia: OpenMP CFD Solveronednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUx265: Bosphorus 1080predis: LPUSHmt-dgemm: Sustained Floating-Point Rateonednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPUmafft: Multiple Sequence Alignment - LSU RNAsvt-vp9: Visual Quality Optimized - Bosphorus 1080ppennant: leblancbigonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUsvt-vp9: VMAF Optimized - Bosphorus 1080psvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080poidn: MemorialUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1145623.494.72223.46849952159926.654163.824168.52135.573402344.636156641053606.729.039557234.662.064104739.175077913576.48893502577101155867294.4138317114.036157.874552104.2211.3923.53432.95846888678.11458447419558.1262481276734064.90751894.8046873994.5041774069.1012085.010262.138.38615.30654.116.880.3659711.9601735.771434521747022.3918.763317738.612201881.924451901359.6526.1365.9971080329.55510910922.8924.583328.48328.637.2600.33199134.501486892.5418.7188910.81479913.049222.788.4620183.17360258.83267.3635.4746524.124.7197.92652750761025.815137.291169.46120.027404364.566620626252927.829.166755274.662.814101158.179214488549.210103248727105001764866.8144350109.624158.457465104.489.79988.09131.44644758793.12500047234546.3142686554933263.95641538.3476564024.8186936262.3112439.110396.938.10824.37347.116.960.3686111.3581625.456459431907194.9217.167021641.962550238.754172155059.3325.4354.3441071326.37810310421.1194.387907.86629.095.8230.29102534.761630926.2119.7855920.82434311.285226.568.5410303.18874265.20266.0135.3848523.524.6798.50250752761825.860137.504169.68126.147412355.326773615551553.729.250952709.651.61897422.375669957548.077104251517102290064059.9143341109.779155.547889104.2711.2983.39227.09344859180.92447946640543.3372651280033864.37341697.7786463983.4621006504.8212438.710436.238.17663.72447.317.080.3661111.6751625.045496931887004.0817.466824543.052445380.334192152898.1725.7348.7871069327.05310310421.7614.386717.27729.226.8390.29468534.881643872.2919.8547540.82245911.849233.038.5463953.19344270.03278.2635.6246423.304.59100.87552652663926.752135.827170.25126.295387366.086730694749849.029.184752690.651.61996474.075577088547.815105812950103071863798.7141345112.550155.826333104.3411.3981.08127.56544757588.26822947033559.3602700833033962.83540971.9869794073.1432186230.8612382.810416.537.93665.19547.317.160.3692411.6241631993808.8717.266650141.952643078.504222227428.4225.6350.5361072328.66510410520.8474.253147.10329.496.8090.29274434.911695910.2520.1576770.82080712.161226.818.1997853.18417273.04277.3935.21OpenBenchmarking.org

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11100200300400500SE +/- 4.20, N = 9SE +/- 5.62, N = 4SE +/- 1.45, N = 3SE +/- 6.49, N = 3456465485464MIN: 1 / MAX: 1812MIN: 1 / MAX: 1811MIN: 1 / MAX: 1790MIN: 1 / MAX: 1832
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1190180270360450Min: 434 / Avg: 456.11 / Max: 476Min: 450 / Avg: 464.75 / Max: 474Min: 483 / Avg: 485.33 / Max: 488Min: 454 / Avg: 463.67 / Max: 476

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11612182430SE +/- 0.25, N = 15SE +/- 0.21, N = 15SE +/- 0.32, N = 15SE +/- 0.30, N = 1523.4924.1223.5223.30
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11612182430Min: 20.99 / Avg: 23.49 / Max: 24.73Min: 22.11 / Avg: 24.12 / Max: 25.13Min: 19.93 / Avg: 23.52 / Max: 24.83Min: 20.85 / Avg: 23.3 / Max: 24.88

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC111.0622.1243.1864.2485.31SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 34.724.714.674.59
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11246810Min: 4.71 / Avg: 4.72 / Max: 4.74Min: 4.66 / Avg: 4.71 / Max: 4.75Min: 4.6 / Avg: 4.67 / Max: 4.71Min: 4.5 / Avg: 4.59 / Max: 4.67

YafaRay

YafaRay is an open-source physically based montecarlo ray-tracing engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterYafaRay 3.4.1Total Time For Sample SceneUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1150100150200250SE +/- 16.23, N = 12SE +/- 0.79, N = 3SE +/- 0.82, N = 3SE +/- 1.79, N = 15223.4797.9398.50100.88-lboost_system -lboost_filesystem -lboost_locale-lpthread-lpthread-lpthread1. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype
OpenBenchmarking.orgSeconds, Fewer Is BetterYafaRay 3.4.1Total Time For Sample SceneUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC114080120160200Min: 151.42 / Avg: 223.47 / Max: 313.16Min: 96.84 / Avg: 97.93 / Max: 99.46Min: 97.64 / Avg: 98.5 / Max: 100.14Min: 91.79 / Avg: 100.87 / Max: 114.041. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype

MariaDB

This is a MariaDB MySQL database server benchmark making use of mysqlslap. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 256Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11110220330440550SE +/- 1.09, N = 3SE +/- 0.61, N = 3SE +/- 0.23, N = 3SE +/- 0.24, N = 3499527507526-llzma -lbz2 -lsnappy -lnuma -lcrypt -lssl -lcrypto-llzma -lbz2 -lsnappy -lnuma -lcrypt -lssl -lcrypto-llzma -lbz2 -lsnappy -lnuma -lcrypt -lssl -lcrypto-shared -lrt -lstdc++1. (CXX) g++ options: -O3 -march=native -pie -fPIC -fstack-protector -O2 -lpthread -lz -lm -ldl
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 256Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1190180270360450Min: 497.02 / Avg: 499.17 / Max: 500.5Min: 526.59 / Avg: 527.33 / Max: 528.54Min: 506.84 / Avg: 507.19 / Max: 507.61Min: 525.21 / Avg: 525.58 / Max: 526.041. (CXX) g++ options: -O3 -march=native -pie -fPIC -fstack-protector -O2 -lpthread -lz -lm -ldl

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 512Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11110220330440550SE +/- 0.18, N = 3SE +/- 0.56, N = 3SE +/- 0.33, N = 3SE +/- 1.29, N = 3521507527526-llzma -lbz2 -lsnappy -lnuma -lcrypt -lssl -lcrypto-llzma -lbz2 -lsnappy -lnuma -lcrypt -lssl -lcrypto-llzma -lbz2 -lsnappy -lnuma -lcrypt -lssl -lcrypto-shared -lrt -lstdc++1. (CXX) g++ options: -O3 -march=native -pie -fPIC -fstack-protector -O2 -lpthread -lz -lm -ldl
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 512Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1190180270360450Min: 521.1 / Avg: 521.47 / Max: 521.65Min: 506.33 / Avg: 507.01 / Max: 508.13Min: 526.04 / Avg: 526.69 / Max: 527.15Min: 524.66 / Avg: 525.95 / Max: 528.541. (CXX) g++ options: -O3 -march=native -pie -fPIC -fstack-protector -O2 -lpthread -lz -lm -ldl

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 128Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11140280420560700SE +/- 2.90, N = 3SE +/- 2.27, N = 3SE +/- 0.38, N = 3SE +/- 1.78, N = 3599610618639-llzma -lbz2 -lsnappy -lnuma -lcrypt -lssl -lcrypto-llzma -lbz2 -lsnappy -lnuma -lcrypt -lssl -lcrypto-llzma -lbz2 -lsnappy -lnuma -lcrypt -lssl -lcrypto-shared -lrt -lstdc++1. (CXX) g++ options: -O3 -march=native -pie -fPIC -fstack-protector -O2 -lpthread -lz -lm -ldl
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 128Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11110220330440550Min: 594.18 / Avg: 599.31 / Max: 604.23Min: 605.33 / Avg: 609.53 / Max: 613.12Min: 618.05 / Avg: 618.43 / Max: 619.2Min: 636.13 / Avg: 639.4 / Max: 642.261. (CXX) g++ options: -O3 -march=native -pie -fPIC -fstack-protector -O2 -lpthread -lz -lm -ldl

LAMMPS Molecular Dynamics Simulator

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: 20k AtomsUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11612182430SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 326.6525.8225.8626.751. (CXX) g++ options: -O3 -march=native -pthread -lm
OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: 20k AtomsUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11612182430Min: 26.6 / Avg: 26.65 / Max: 26.7Min: 25.79 / Avg: 25.82 / Max: 25.84Min: 25.83 / Avg: 25.86 / Max: 25.92Min: 26.74 / Avg: 26.75 / Max: 26.771. (CXX) g++ options: -O3 -march=native -pthread -lm

Ngspice

Ngspice is an open-source SPICE circuit simulator. Ngspice was originally based on the Berkeley SPICE electronic circuit simulator. Ngspice supports basic threading using OpenMP. This test profile is making use of the ISCAS 85 benchmark circuits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C2670Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC114080120160200SE +/- 1.27, N = 12SE +/- 1.52, N = 3SE +/- 0.55, N = 3SE +/- 0.39, N = 3163.82137.29137.50135.831. (CC) gcc options: -O3 -march=native -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE
OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C2670Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11306090120150Min: 156.05 / Avg: 163.82 / Max: 173.45Min: 135.35 / Avg: 137.29 / Max: 140.3Min: 136.42 / Avg: 137.5 / Max: 138.2Min: 135.05 / Avg: 135.83 / Max: 136.241. (CC) gcc options: -O3 -march=native -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE

OpenFOAM

OpenFOAM is the leading free, open source software for computational fluid dynamics (CFD). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 8Input: Motorbike 60MUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC114080120160200SE +/- 0.34, N = 3SE +/- 0.34, N = 3SE +/- 0.23, N = 3SE +/- 0.16, N = 3168.52169.46169.68170.25-lfoamToVTK -lfileFormats-lfoamToVTK -lfileFormats-lfoamToVTK -lfileFormats-ldecompose -lmetisDecomp -lscotchDecomp -lregionModels1. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -llagrangian -lgenericPatchFields -lOpenFOAM -ldl -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 8Input: Motorbike 60MUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11306090120150Min: 167.89 / Avg: 168.52 / Max: 169.04Min: 168.99 / Avg: 169.46 / Max: 170.13Min: 169.25 / Avg: 169.68 / Max: 170.04Min: 169.95 / Avg: 170.25 / Max: 170.511. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -llagrangian -lgenericPatchFields -lOpenFOAM -ldl -lm

Ngspice

Ngspice is an open-source SPICE circuit simulator. Ngspice was originally based on the Berkeley SPICE electronic circuit simulator. Ngspice supports basic threading using OpenMP. This test profile is making use of the ISCAS 85 benchmark circuits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C7552Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11306090120150SE +/- 1.71, N = 3SE +/- 0.07, N = 3SE +/- 0.66, N = 3SE +/- 2.20, N = 12135.57120.03126.15126.301. (CC) gcc options: -O3 -march=native -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE
OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C7552Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11306090120150Min: 132.2 / Avg: 135.57 / Max: 137.7Min: 119.92 / Avg: 120.03 / Max: 120.15Min: 125.46 / Avg: 126.15 / Max: 127.47Min: 119.62 / Avg: 126.3 / Max: 138.911. (CC) gcc options: -O3 -march=native -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: bertsquad-10 - Device: OpenMP CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1190180270360450SE +/- 2.57, N = 3SE +/- 2.47, N = 3SE +/- 4.92, N = 12SE +/- 1.92, N = 34024044123871. (CXX) g++ options: -O3 -march=native -fopenmp -ffunction-sections -fdata-sections -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: bertsquad-10 - Device: OpenMP CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1170140210280350Min: 397 / Avg: 402 / Max: 405.5Min: 399 / Avg: 403.5 / Max: 407.5Min: 392.5 / Avg: 412.46 / Max: 440Min: 385 / Avg: 387.17 / Max: 3911. (CXX) g++ options: -O3 -march=native -fopenmp -ffunction-sections -fdata-sections -ldl -lrt

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1180160240320400SE +/- 1.31, N = 3SE +/- 0.40, N = 3SE +/- 2.59, N = 3SE +/- 0.49, N = 3344.63364.56355.32366.08
OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1170140210280350Min: 342.59 / Avg: 344.63 / Max: 347.06Min: 363.87 / Avg: 364.56 / Max: 365.24Min: 351.6 / Avg: 355.32 / Max: 360.31Min: 365.33 / Avg: 366.08 / Max: 366.99

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: shufflenet-v2-10 - Device: OpenMP CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1115003000450060007500SE +/- 35.31, N = 3SE +/- 70.00, N = 12SE +/- 26.43, N = 3SE +/- 19.77, N = 361566620677367301. (CXX) g++ options: -O3 -march=native -fopenmp -ffunction-sections -fdata-sections -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: shufflenet-v2-10 - Device: OpenMP CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1112002400360048006000Min: 6087 / Avg: 6156 / Max: 6203.5Min: 6073.5 / Avg: 6620.33 / Max: 6845Min: 6722.5 / Avg: 6772.83 / Max: 6812Min: 6706.5 / Avg: 6729.67 / Max: 67691. (CXX) g++ options: -O3 -march=native -fopenmp -ffunction-sections -fdata-sections -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: super-resolution-10 - Device: OpenMP CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1115003000450060007500SE +/- 33.38, N = 3SE +/- 54.74, N = 3SE +/- 78.69, N = 12SE +/- 72.47, N = 364106262615569471. (CXX) g++ options: -O3 -march=native -fopenmp -ffunction-sections -fdata-sections -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: super-resolution-10 - Device: OpenMP CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1112002400360048006000Min: 6356 / Avg: 6410 / Max: 6471Min: 6153 / Avg: 6261.83 / Max: 6326.5Min: 5670 / Avg: 6154.63 / Max: 6450Min: 6808 / Avg: 6946.67 / Max: 7052.51. (CXX) g++ options: -O3 -march=native -fopenmp -ffunction-sections -fdata-sections -ldl -lrt

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1111K22K33K44K55KSE +/- 675.73, N = 12SE +/- 444.73, N = 15SE +/- 381.91, N = 11SE +/- 396.71, N = 353606.752927.851553.749849.0
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC119K18K27K36K45KMin: 50163.2 / Avg: 53606.73 / Max: 57999.5Min: 50456.5 / Avg: 52927.79 / Max: 56468Min: 50327.4 / Avg: 51553.68 / Max: 54813.1Min: 49174.5 / Avg: 49849 / Max: 50548.1

High Performance Conjugate Gradient

HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11714212835SE +/- 0.15, N = 3SE +/- 0.13, N = 3SE +/- 0.10, N = 3SE +/- 0.13, N = 329.0429.1729.2529.181. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11612182430Min: 28.89 / Avg: 29.04 / Max: 29.33Min: 28.94 / Avg: 29.17 / Max: 29.4Min: 29.06 / Avg: 29.25 / Max: 29.42Min: 28.99 / Avg: 29.18 / Max: 29.431. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1112K24K36K48K60KSE +/- 727.18, N = 15SE +/- 580.61, N = 15SE +/- 147.50, N = 3SE +/- 335.56, N = 357234.655274.652709.652690.6
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1110K20K30K40K50KMin: 52160.4 / Avg: 57234.61 / Max: 61867.2Min: 52621.4 / Avg: 55274.64 / Max: 60432.5Min: 52510.2 / Avg: 52709.63 / Max: 52997.6Min: 52020.1 / Avg: 52690.57 / Max: 53051.5

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LeukocyteUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC111428425670SE +/- 0.71, N = 13SE +/- 0.24, N = 3SE +/- 0.41, N = 3SE +/- 0.59, N = 1562.0662.8151.6251.621. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LeukocyteUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC111224364860Min: 54.92 / Avg: 62.06 / Max: 64.89Min: 62.37 / Avg: 62.81 / Max: 63.18Min: 51.12 / Avg: 51.62 / Max: 52.44Min: 47.34 / Avg: 51.62 / Max: 57.371. (CXX) g++ options: -O2 -lOpenCL

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1120K40K60K80K100KSE +/- 2444.48, N = 12SE +/- 974.76, N = 6SE +/- 760.68, N = 10SE +/- 469.23, N = 3104739.1101158.197422.396474.0
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1120K40K60K80K100KMin: 95838.7 / Avg: 104739.11 / Max: 124985Min: 99142.9 / Avg: 101158.08 / Max: 104795Min: 94722.5 / Avg: 97422.25 / Max: 102474Min: 95572.5 / Avg: 96474 / Max: 97150.6

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkStructuredVolumeUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1120M40M60M80M100MSE +/- 1084350.33, N = 15SE +/- 907902.42, N = 15SE +/- 887912.44, N = 4SE +/- 515321.24, N = 375077913792144887566995775577088MIN: 1073646 / MAX: 803527920MIN: 1183368 / MAX: 1019150352MIN: 1211791 / MAX: 633286944MIN: 1183326 / MAX: 645253056
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkStructuredVolumeUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1114M28M42M56M70MMin: 70198351 / Avg: 75077912.93 / Max: 84280623Min: 74988677 / Avg: 79214487.53 / Max: 85141014Min: 74274124 / Avg: 75669957 / Max: 78267976Min: 74550865 / Avg: 75577088 / Max: 76172769

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11120240360480600SE +/- 9.03, N = 15SE +/- 1.81, N = 3SE +/- 3.91, N = 3SE +/- 0.48, N = 3576.49549.21548.08547.82MIN: 541.14MIN: 537.59MIN: 532.31MIN: 534.251. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11100200300400500Min: 548.13 / Avg: 576.49 / Max: 667.41Min: 546.06 / Avg: 549.21 / Max: 552.31Min: 542.58 / Avg: 548.08 / Max: 555.63Min: 546.86 / Avg: 547.82 / Max: 548.361. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Kripke

Kripke is a simple, scalable, 3D Sn deterministic particle transport code. Its primary purpose is to research how data layout, programming paradigms and architectures effect the implementation and performance of Sn transport. Kripke is developed by LLNL. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgThroughput FoM, More Is BetterKripke 1.2.4Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1120M40M60M80M100MSE +/- 1474539.43, N = 15SE +/- 1522978.65, N = 15SE +/- 860592.92, N = 15SE +/- 1086593.46, N = 4935025771032487271042515171058129501. (CXX) g++ options: -O3 -march=native -fopenmp
OpenBenchmarking.orgThroughput FoM, More Is BetterKripke 1.2.4Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1120M40M60M80M100MMin: 84368740 / Avg: 93502576.67 / Max: 103435500Min: 94160250 / Avg: 103248726.67 / Max: 111318800Min: 98457800 / Avg: 104251516.67 / Max: 108365200Min: 103227200 / Avg: 105812950 / Max: 1085356001. (CXX) g++ options: -O3 -march=native -fopenmp

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11200K400K600K800K1000KSE +/- 17126.87, N = 15SE +/- 9914.36, N = 3SE +/- 8164.03, N = 3SE +/- 10731.38, N = 51011558105001710229001030718
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11200K400K600K800K1000KMin: 902860 / Avg: 1011558.47 / Max: 1111070Min: 1034340 / Avg: 1050016.67 / Max: 1068370Min: 1010790 / Avg: 1022900 / Max: 1038440Min: 994198 / Avg: 1030717.6 / Max: 1056270

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1114K28K42K56K70KSE +/- 669.07, N = 15SE +/- 715.03, N = 4SE +/- 618.86, N = 3SE +/- 332.53, N = 367294.464866.864059.963798.7
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1112K24K36K48K60KMin: 63971.8 / Avg: 67294.37 / Max: 71824.1Min: 63088.6 / Avg: 64866.8 / Max: 66467.7Min: 63328.1 / Avg: 64059.93 / Max: 65290.3Min: 63141.7 / Avg: 63798.67 / Max: 64216.7

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: fcn-resnet101-11 - Device: OpenMP CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11306090120150SE +/- 0.58, N = 3SE +/- 1.09, N = 3SE +/- 0.60, N = 3SE +/- 1.09, N = 31381441431411. (CXX) g++ options: -O3 -march=native -fopenmp -ffunction-sections -fdata-sections -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: fcn-resnet101-11 - Device: OpenMP CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11306090120150Min: 137 / Avg: 138 / Max: 139Min: 141.5 / Avg: 143.67 / Max: 145Min: 142 / Avg: 142.83 / Max: 144Min: 140 / Avg: 141.33 / Max: 143.51. (CXX) g++ options: -O3 -march=native -fopenmp -ffunction-sections -fdata-sections -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: yolov4 - Device: OpenMP CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1180160240320400SE +/- 3.24, N = 3SE +/- 1.59, N = 3SE +/- 3.62, N = 3SE +/- 1.48, N = 33173503413451. (CXX) g++ options: -O3 -march=native -fopenmp -ffunction-sections -fdata-sections -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: yolov4 - Device: OpenMP CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1160120180240300Min: 312 / Avg: 316.83 / Max: 323Min: 347.5 / Avg: 350.33 / Max: 353Min: 335 / Avg: 341 / Max: 347.5Min: 342.5 / Avg: 345.33 / Max: 347.51. (CXX) g++ options: -O3 -march=native -fopenmp -ffunction-sections -fdata-sections -ldl -lrt

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3DUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11306090120150SE +/- 1.32, N = 4SE +/- 0.14, N = 3SE +/- 0.16, N = 3SE +/- 0.81, N = 3114.04109.62109.78112.551. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3DUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1120406080100Min: 110.53 / Avg: 114.04 / Max: 116.64Min: 109.38 / Avg: 109.62 / Max: 109.87Min: 109.46 / Avg: 109.78 / Max: 109.94Min: 110.94 / Avg: 112.55 / Max: 113.461. (CXX) g++ options: -O2 -lOpenCL

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: EmilyUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC114080120160200157.87158.46155.55155.83

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Classroom - Compute: CPU-OnlyUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1120406080100SE +/- 0.38, N = 3SE +/- 0.15, N = 3SE +/- 0.20, N = 3SE +/- 0.14, N = 3104.22104.48104.27104.34
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Classroom - Compute: CPU-OnlyUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1120406080100Min: 103.64 / Avg: 104.22 / Max: 104.93Min: 104.3 / Avg: 104.48 / Max: 104.78Min: 104.04 / Avg: 104.27 / Max: 104.66Min: 104.07 / Avg: 104.34 / Max: 104.5

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: python_startupUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC113691215SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 311.309.7911.2011.30
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: python_startupUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC113691215Min: 11.3 / Avg: 11.3 / Max: 11.3Min: 9.77 / Avg: 9.79 / Max: 9.81Min: 11.2 / Avg: 11.23 / Max: 11.3Min: 11.2 / Avg: 11.33 / Max: 11.4

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC112004006008001000SE +/- 0.79, N = 3SE +/- 9.48, N = 6SE +/- 4.40, N = 3SE +/- 1.76, N = 3923.53988.09983.39981.08MIN: 910.01MIN: 952.93MIN: 964.72MIN: 966.891. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC112004006008001000Min: 922.61 / Avg: 923.53 / Max: 925.1Min: 970.31 / Avg: 988.09 / Max: 1032.94Min: 977.39 / Avg: 983.39 / Max: 991.96Min: 979.09 / Avg: 981.08 / Max: 984.591. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Nebular Empirical Analysis Tool

NEAT is the Nebular Empirical Analysis Tool for empirical analysis of ionised nebulae, with uncertainty propagation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNebular Empirical Analysis Tool 2020-02-29Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11816243240SE +/- 0.26, N = 15SE +/- 0.21, N = 15SE +/- 0.05, N = 3SE +/- 0.39, N = 332.9631.4527.0927.571. (F9X) gfortran options: -cpp -ffree-line-length-0 -Jsource/ -fopenmp -O3 -fno-backtrace
OpenBenchmarking.orgSeconds, Fewer Is BetterNebular Empirical Analysis Tool 2020-02-29Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11714212835Min: 31.67 / Avg: 32.96 / Max: 35.02Min: 30.11 / Avg: 31.45 / Max: 32.85Min: 27.03 / Avg: 27.09 / Max: 27.2Min: 26.81 / Avg: 27.57 / Max: 28.131. (F9X) gfortran options: -cpp -ffree-line-length-0 -Jsource/ -fopenmp -O3 -fno-backtrace

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: raytraceUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11100200300400500SE +/- 0.33, N = 3SE +/- 1.00, N = 3SE +/- 1.20, N = 3468447448447
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: raytraceUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1180160240320400Min: 468 / Avg: 468.33 / Max: 469Min: 446 / Avg: 448 / Max: 449Min: 445 / Avg: 447.33 / Max: 449

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU via OpenCL and CPU benchmarking with OpenMP. The FinanceBench test cases are focused on Black-Sholes-Merton Process with Analytic European Option engine, QMC (Sobol) Monte-Carlo method (Equity Option Example), Bonds Fixed-rate bond with flat forward curve, and Repo Securities repurchase agreement. FinanceBench was originally written by the Cavazos Lab at University of Delaware. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Bonds OpenMPUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1120K40K60K80K100KSE +/- 101.32, N = 3SE +/- 107.08, N = 3SE +/- 53.90, N = 3SE +/- 83.74, N = 388678.1158793.1359180.9257588.271. (CXX) g++ options: -O3 -march=native -fopenmp
OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Bonds OpenMPUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1115K30K45K60K75KMin: 88503.65 / Avg: 88678.11 / Max: 88854.62Min: 58652.6 / Avg: 58793.13 / Max: 59003.34Min: 59079.69 / Avg: 59180.92 / Max: 59263.62Min: 57469.11 / Avg: 57588.27 / Max: 57749.761. (CXX) g++ options: -O3 -march=native -fopenmp

Chaos Group V-RAY

This is a test of Chaos Group's V-RAY benchmark. V-RAY is a commercial renderer that can integrate with various creator software products like SketchUp and 3ds Max. The V-RAY benchmark is standalone and supports CPU and NVIDIA CUDA/RTX based rendering. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 5Mode: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1110K20K30K40K50KSE +/- 166.62, N = 3SE +/- 121.64, N = 3SE +/- 571.93, N = 3SE +/- 467.11, N = 347419472344664047033
OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 5Mode: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC118K16K24K32K40KMin: 47236 / Avg: 47419.33 / Max: 47752Min: 47010 / Avg: 47234.33 / Max: 47428Min: 45565 / Avg: 46640 / Max: 47516Min: 46148 / Avg: 47032.67 / Max: 47735

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11120240360480600SE +/- 5.67, N = 3SE +/- 3.68, N = 3SE +/- 2.43, N = 3SE +/- 7.60, N = 3558.13546.31543.34559.36MIN: 543.23MIN: 533.79MIN: 530.81MIN: 536.061. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11100200300400500Min: 551.83 / Avg: 558.13 / Max: 569.44Min: 541.58 / Avg: 546.31 / Max: 553.56Min: 539.06 / Avg: 543.34 / Max: 547.47Min: 544.27 / Avg: 559.36 / Max: 568.561. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkVdbVolumeUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC116M12M18M24M30MSE +/- 70798.88, N = 3SE +/- 217704.15, N = 3SE +/- 65172.45, N = 3SE +/- 94239.71, N = 324812767268655492651280027008330MIN: 868934 / MAX: 162479232MIN: 1021515 / MAX: 200332152MIN: 1022996 / MAX: 184673880MIN: 1049658 / MAX: 186492960
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkVdbVolumeUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC115M10M15M20M25MMin: 24731071 / Avg: 24812767.33 / Max: 24953774Min: 26445529 / Avg: 26865548.67 / Max: 27174921Min: 26434488 / Avg: 26512799.67 / Max: 26642193Min: 26887201 / Avg: 27008329.67 / Max: 27193951

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: 2to3Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1170140210280350340332338339

SQLite Speedtest

This is a benchmark of SQLite's speedtest1 benchmark program with an increased problem size of 1,000. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC111428425670SE +/- 0.15, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 364.9163.9664.3762.841. (CC) gcc options: -O3 -march=native -ldl -lz -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC111326395265Min: 64.72 / Avg: 64.91 / Max: 65.21Min: 63.85 / Avg: 63.96 / Max: 64.05Min: 64.32 / Avg: 64.37 / Max: 64.45Min: 62.78 / Avg: 62.83 / Max: 62.911. (CC) gcc options: -O3 -march=native -ldl -lz -lpthread

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU via OpenCL and CPU benchmarking with OpenMP. The FinanceBench test cases are focused on Black-Sholes-Merton Process with Analytic European Option engine, QMC (Sobol) Monte-Carlo method (Equity Option Example), Bonds Fixed-rate bond with flat forward curve, and Repo Securities repurchase agreement. FinanceBench was originally written by the Cavazos Lab at University of Delaware. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Repo OpenMPUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1111K22K33K44K55KSE +/- 498.18, N = 3SE +/- 180.05, N = 3SE +/- 131.71, N = 3SE +/- 231.02, N = 351894.8041538.3541697.7840971.991. (CXX) g++ options: -O3 -march=native -fopenmp
OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Repo OpenMPUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC119K18K27K36K45KMin: 51284.64 / Avg: 51894.8 / Max: 52882.03Min: 41341.61 / Avg: 41538.35 / Max: 41897.91Min: 41517.43 / Avg: 41697.78 / Max: 41954.22Min: 40730.48 / Avg: 40971.99 / Max: 41433.861. (CXX) g++ options: -O3 -march=native -fopenmp

Himeno Benchmark

The Himeno benchmark is a linear solver of pressure Poisson using a point-Jacobi method. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC119001800270036004500SE +/- 0.36, N = 3SE +/- 5.05, N = 3SE +/- 2.71, N = 3SE +/- 1.60, N = 33994.504024.823983.464073.141. (CC) gcc options: -O3 -march=native -mavx2
OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC117001400210028003500Min: 3993.82 / Avg: 3994.5 / Max: 3995.01Min: 4016.5 / Avg: 4024.82 / Max: 4033.94Min: 3978.83 / Avg: 3983.46 / Max: 3988.2Min: 4070.63 / Avg: 4073.14 / Max: 4076.11. (CC) gcc options: -O3 -march=native -mavx2

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.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1114002800420056007000SE +/- 18.13, N = 3SE +/- 160.71, N = 13SE +/- 73.13, N = 4SE +/- 4.94, N = 34069.106262.316504.826230.86-lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz-lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz-lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Ubuntu 19.04: Open MPI 3.1.33. Ubuntu 21.04 Dev: Open MPI 4.1.04. Ubuntu 21.04 Dev + Linux 5.11: Open MPI 4.1.05. Ubuntu 21.04 Dev + Linux 5.11 + GCC11: Open MPI 4.1.0
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1111002200330044005500Min: 4050.9 / Avg: 4069.1 / Max: 4105.36Min: 4458.15 / Avg: 6262.31 / Max: 6642.82Min: 6345.14 / Avg: 6504.82 / Max: 6672.36Min: 6221.75 / Avg: 6230.86 / Max: 6238.731. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Ubuntu 19.04: Open MPI 3.1.33. Ubuntu 21.04 Dev: Open MPI 4.1.04. Ubuntu 21.04 Dev + Linux 5.11: Open MPI 4.1.05. Ubuntu 21.04 Dev + Linux 5.11 + GCC11: Open MPI 4.1.0

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC113K6K9K12K15KSE +/- 78.97, N = 3SE +/- 55.90, N = 3SE +/- 28.13, N = 3SE +/- 27.77, N = 312085.012439.112438.712382.81. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC112K4K6K8K10KMin: 11927.1 / Avg: 12085.03 / Max: 12164Min: 12327.3 / Avg: 12439.1 / Max: 12495Min: 12410.6 / Avg: 12438.73 / Max: 12495Min: 12327.3 / Avg: 12382.83 / Max: 12410.61. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - DegriddingUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC112K4K6K8K10KSE +/- 66.19, N = 3SE +/- 19.67, N = 3SE +/- 0.00, N = 3SE +/- 19.67, N = 310262.110396.910436.210416.51. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - DegriddingUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC112K4K6K8K10KMin: 10147.9 / Avg: 10262.13 / Max: 10377.2Min: 10377.2 / Avg: 10396.87 / Max: 10436.2Min: 10436.2 / Avg: 10436.2 / Max: 10436.2Min: 10377.2 / Avg: 10416.53 / Max: 10436.21. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: BMW27 - Compute: CPU-OnlyUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11918273645SE +/- 0.17, N = 3SE +/- 0.24, N = 3SE +/- 0.17, N = 3SE +/- 0.08, N = 338.3838.1038.1737.93
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: BMW27 - Compute: CPU-OnlyUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11816243240Min: 38.07 / Avg: 38.38 / Max: 38.65Min: 37.84 / Avg: 38.1 / Max: 38.57Min: 37.84 / Avg: 38.17 / Max: 38.37Min: 37.77 / Avg: 37.93 / Max: 38.03

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Second, More Is BetterASKAP 1.0Test: Hogbom Clean OpenMPUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC112004006008001000SE +/- 17.36, N = 15SE +/- 8.96, N = 3SE +/- 1.47, N = 3SE +/- 1.47, N = 3615.31824.37663.72665.201. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgIterations Per Second, More Is BetterASKAP 1.0Test: Hogbom Clean OpenMPUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11140280420560700Min: 526.32 / Avg: 615.31 / Max: 746.27Min: 806.45 / Avg: 824.37 / Max: 833.33Min: 662.25 / Avg: 663.72 / Max: 666.67Min: 662.25 / Avg: 665.2 / Max: 666.671. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: django_templateUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC111224364860SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.12, N = 354.147.147.347.3
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: django_templateUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC111122334455Min: 54 / Avg: 54.07 / Max: 54.2Min: 47 / Avg: 47.13 / Max: 47.2Min: 47.1 / Avg: 47.27 / Max: 47.4Min: 47.1 / Avg: 47.3 / Max: 47.5

Kvazaar

This is a test of Kvazaar as a CPU-based H.265 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.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Very FastUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1148121620SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 316.8816.9617.0817.161. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Very FastUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1148121620Min: 16.82 / Avg: 16.88 / Max: 16.98Min: 16.87 / Avg: 16.96 / Max: 17.03Min: 17.07 / Avg: 17.08 / Max: 17.09Min: 17.1 / Avg: 17.16 / Max: 17.261. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lpthread -lm -lrt

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.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC110.08310.16620.24930.33240.4155SE +/- 0.00094, N = 3SE +/- 0.00131, N = 3SE +/- 0.00050, N = 3SE +/- 0.00222, N = 30.365970.368610.366110.36924
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1112345Min: 0.36 / Avg: 0.37 / Max: 0.37Min: 0.37 / Avg: 0.37 / Max: 0.37Min: 0.37 / Avg: 0.37 / Max: 0.37Min: 0.37 / Avg: 0.37 / Max: 0.37

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP StreamclusterUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC113691215SE +/- 0.02, N = 3SE +/- 0.09, N = 15SE +/- 0.12, N = 3SE +/- 0.09, N = 1511.9611.3611.6811.621. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP StreamclusterUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC113691215Min: 11.92 / Avg: 11.96 / Max: 11.99Min: 10.78 / Avg: 11.36 / Max: 11.84Min: 11.49 / Avg: 11.68 / Max: 11.9Min: 10.89 / Avg: 11.62 / Max: 11.961. (CXX) g++ options: -O2 -lOpenCL

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: regex_compileUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC114080120160200173162162163

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average LatencyUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.111.29852.5973.89555.1946.4925SE +/- 0.037, N = 3SE +/- 0.017, N = 3SE +/- 0.013, N = 35.7715.4565.0451. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average LatencyUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11246810Min: 5.72 / Avg: 5.77 / Max: 5.84Min: 5.42 / Avg: 5.46 / Max: 5.47Min: 5.02 / Avg: 5.04 / Max: 5.071. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read WriteUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.1111K22K33K44K55KSE +/- 269.58, N = 3SE +/- 140.45, N = 3SE +/- 126.36, N = 34345245943496931. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read WriteUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.119K18K27K36K45KMin: 42930.77 / Avg: 43452.26 / Max: 43831.59Min: 45799.93 / Avg: 45943.11 / Max: 46224Min: 49498.94 / Avg: 49693.31 / Max: 49930.371. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SETUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11400K800K1200K1600K2000KSE +/- 30273.24, N = 15SE +/- 14871.09, N = 3SE +/- 24706.77, N = 3SE +/- 22443.34, N = 31747022.391907194.921887004.081993808.871. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SETUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11300K600K900K1200K1500KMin: 1575334.62 / Avg: 1747022.39 / Max: 1952774.88Min: 1877934.38 / Avg: 1907194.92 / Max: 1926441.88Min: 1847410.25 / Avg: 1887004.08 / Max: 1932404.12Min: 1958549.12 / Avg: 1993808.87 / Max: 2035494.381. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pathlibUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11510152025SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 318.717.117.417.2
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pathlibUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11510152025Min: 18.7 / Avg: 18.7 / Max: 18.7Min: 17.1 / Avg: 17.13 / Max: 17.2Min: 17.3 / Avg: 17.37 / Max: 17.4Min: 17.2 / Avg: 17.2 / Max: 17.2

PHPBench

PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11140K280K420K560K700KSE +/- 321.84, N = 3SE +/- 1341.16, N = 3SE +/- 2936.03, N = 3SE +/- 1019.45, N = 3633177670216668245666501
OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11120K240K360K480K600KMin: 632830 / Avg: 633177 / Max: 633820Min: 667847 / Avg: 670216 / Max: 672490Min: 664580 / Avg: 668245.33 / Max: 674051Min: 664845 / Avg: 666500.67 / Max: 668359

LibRaw

LibRaw is a RAW image decoder for digital camera photos. This test profile runs LibRaw's post-processing benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpix/sec, More Is BetterLibRaw 0.20Post-Processing BenchmarkUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC111020304050SE +/- 0.05, N = 3SE +/- 0.22, N = 3SE +/- 0.15, N = 3SE +/- 0.11, N = 338.6141.9643.0541.951. (CXX) g++ options: -O3 -march=native -fopenmp -ljpeg -lz -lm
OpenBenchmarking.orgMpix/sec, More Is BetterLibRaw 0.20Post-Processing BenchmarkUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11918273645Min: 38.53 / Avg: 38.61 / Max: 38.7Min: 41.67 / Avg: 41.96 / Max: 42.39Min: 42.87 / Avg: 43.05 / Max: 43.35Min: 41.76 / Avg: 41.95 / Max: 42.131. (CXX) g++ options: -O3 -march=native -fopenmp -ljpeg -lz -lm

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: GETUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11600K1200K1800K2400K3000KSE +/- 70535.69, N = 15SE +/- 6330.39, N = 3SE +/- 13811.23, N = 3SE +/- 11499.67, N = 32201881.922550238.752445380.332643078.501. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: GETUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11500K1000K1500K2000K2500KMin: 1918293.62 / Avg: 2201881.92 / Max: 2617124.25Min: 2540658.5 / Avg: 2550238.75 / Max: 2562197.25Min: 2417810.25 / Avg: 2445380.33 / Max: 2460637.75Min: 2622640.5 / Avg: 2643078.5 / Max: 2662432.251. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pickle_pure_pythonUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11100200300400500SE +/- 0.88, N = 3SE +/- 1.45, N = 3445417419422
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pickle_pure_pythonUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1180160240320400Min: 416 / Avg: 417.33 / Max: 419Min: 416 / Avg: 418.67 / Max: 421

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SADDUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11500K1000K1500K2000K2500KSE +/- 39203.08, N = 12SE +/- 22931.99, N = 3SE +/- 14200.11, N = 3SE +/- 8203.23, N = 31901359.652155059.332152898.172227428.421. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SADDUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11400K800K1200K1600K2000KMin: 1728912.88 / Avg: 1901359.65 / Max: 2092932.62Min: 2115513.25 / Avg: 2155059.33 / Max: 2194949.75Min: 2124509.25 / Avg: 2152898.17 / Max: 2167786.75Min: 2211453.5 / Avg: 2227428.42 / Max: 2238653.251. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: json_loadsUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11612182430SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 326.125.425.725.6
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: json_loadsUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11612182430Min: 26.1 / Avg: 26.1 / Max: 26.1Min: 25.4 / Avg: 25.43 / Max: 25.5Min: 25.6 / Avg: 25.67 / Max: 25.7Min: 25.5 / Avg: 25.57 / Max: 25.6

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v2Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1180160240320400SE +/- 1.21, N = 3SE +/- 3.23, N = 3SE +/- 0.41, N = 3SE +/- 1.10, N = 3366.00354.34348.79350.54MIN: 354.49 / MAX: 501.68MIN: 345.92 / MAX: 489.99MIN: 346.29 / MAX: 410.44MIN: 347.02 / MAX: 522.091. (CXX) g++ options: -O3 -march=native -fopenmp -pthread -fvisibility=hidden -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v2Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1170140210280350Min: 363.6 / Avg: 366 / Max: 367.39Min: 349.39 / Avg: 354.34 / Max: 360.4Min: 348.13 / Avg: 348.79 / Max: 349.55Min: 349.4 / Avg: 350.54 / Max: 352.741. (CXX) g++ options: -O3 -march=native -fopenmp -pthread -fvisibility=hidden -rdynamic -ldl

PyBench

This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC112004006008001000SE +/- 2.52, N = 3SE +/- 2.52, N = 3SE +/- 1.67, N = 31080107110691072
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC112004006008001000Min: 1075 / Avg: 1080 / Max: 1083Min: 1068 / Avg: 1071 / Max: 1076Min: 1067 / Avg: 1068.67 / Max: 1072

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.1Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1170140210280350SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.69, N = 3SE +/- 0.74, N = 3329.56326.38327.05328.67MIN: 329.04 / MAX: 331.16MIN: 325.29 / MAX: 327.12MIN: 326.19 / MAX: 330.75MIN: 326.96 / MAX: 331.191. (CXX) g++ options: -O3 -march=native -fopenmp -pthread -fvisibility=hidden -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.1Ubuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1160120180240300Min: 329.45 / Avg: 329.55 / Max: 329.64Min: 326.33 / Avg: 326.38 / Max: 326.44Min: 326.35 / Avg: 327.05 / Max: 328.43Min: 327.18 / Avg: 328.67 / Max: 329.451. (CXX) g++ options: -O3 -march=native -fopenmp -pthread -fvisibility=hidden -rdynamic -ldl

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: chaosUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1120406080100SE +/- 0.33, N = 3SE +/- 0.33, N = 3109103103104
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: chaosUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1120406080100Min: 103 / Avg: 103.33 / Max: 104Min: 103 / Avg: 103.67 / Max: 104

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: crypto_pyaesUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1120406080100109104104105

Dolfyn

Dolfyn is a Computational Fluid Dynamics (CFD) code of modern numerical simulation techniques. The Dolfyn test profile measures the execution time of the bundled computational fluid dynamics demos that are bundled with Dolfyn. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid DynamicsUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11510152025SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 322.8921.1221.7620.85
OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid DynamicsUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11510152025Min: 22.83 / Avg: 22.89 / Max: 22.97Min: 21.07 / Avg: 21.12 / Max: 21.18Min: 21.66 / Avg: 21.76 / Max: 21.86Min: 20.81 / Avg: 20.85 / Max: 20.88

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC111.03122.06243.09364.12485.156SE +/- 0.00382, N = 3SE +/- 0.00385, N = 3SE +/- 0.00438, N = 3SE +/- 0.00276, N = 34.583324.387904.386714.25314MIN: 4.45MIN: 4.25MIN: 4.24MIN: 4.121. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11246810Min: 4.58 / Avg: 4.58 / Max: 4.59Min: 4.38 / Avg: 4.39 / Max: 4.39Min: 4.38 / Avg: 4.39 / Max: 4.39Min: 4.25 / Avg: 4.25 / Max: 4.261. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

ArrayFire

ArrayFire is an GPU and CPU numeric processing library, this test uses the built-in CPU and OpenCL ArrayFire benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11246810SE +/- 0.739, N = 15SE +/- 0.182, N = 15SE +/- 0.086, N = 15SE +/- 0.099, N = 158.4837.8667.2777.1031. (CXX) g++ options: -O3 -march=native -rdynamic
OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC113691215Min: 6.07 / Avg: 8.48 / Max: 12.83Min: 6.77 / Avg: 7.87 / Max: 9.41Min: 6.66 / Avg: 7.28 / Max: 7.87Min: 6.5 / Avg: 7.1 / Max: 7.751. (CXX) g++ options: -O3 -march=native -rdynamic

Kvazaar

This is a test of Kvazaar as a CPU-based H.265 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.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Ultra FastUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11714212835SE +/- 0.22, N = 3SE +/- 0.07, N = 3SE +/- 0.16, N = 3SE +/- 0.06, N = 328.6329.0929.2229.491. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Ultra FastUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11714212835Min: 28.39 / Avg: 28.63 / Max: 29.07Min: 28.98 / Avg: 29.09 / Max: 29.21Min: 28.93 / Avg: 29.22 / Max: 29.49Min: 29.41 / Avg: 29.49 / Max: 29.621. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lpthread -lm -lrt

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD SolverUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11246810SE +/- 0.090, N = 15SE +/- 0.129, N = 15SE +/- 0.010, N = 3SE +/- 0.012, N = 37.2605.8236.8396.8091. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD SolverUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC113691215Min: 6.63 / Avg: 7.26 / Max: 7.76Min: 5.58 / Avg: 5.82 / Max: 7.42Min: 6.83 / Avg: 6.84 / Max: 6.86Min: 6.79 / Avg: 6.81 / Max: 6.831. (CXX) g++ options: -O2 -lOpenCL

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC110.07470.14940.22410.29880.3735SE +/- 0.002873, N = 8SE +/- 0.003010, N = 4SE +/- 0.003609, N = 4SE +/- 0.003168, N = 30.3319910.2910250.2946850.292744MIN: 0.27MIN: 0.25MIN: 0.25MIN: 0.251. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1112345Min: 0.32 / Avg: 0.33 / Max: 0.34Min: 0.28 / Avg: 0.29 / Max: 0.3Min: 0.29 / Avg: 0.29 / Max: 0.3Min: 0.29 / Avg: 0.29 / Max: 0.31. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11816243240SE +/- 0.14, N = 3SE +/- 0.18, N = 3SE +/- 0.16, N = 3SE +/- 0.20, N = 334.5034.7634.8834.911. (CXX) g++ options: -O3 -march=native -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11714212835Min: 34.36 / Avg: 34.5 / Max: 34.77Min: 34.46 / Avg: 34.76 / Max: 35.08Min: 34.6 / Avg: 34.88 / Max: 35.16Min: 34.53 / Avg: 34.91 / Max: 35.211. (CXX) g++ options: -O3 -march=native -rdynamic -lpthread -lrt -ldl -lnuma

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: LPUSHUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11400K800K1200K1600K2000KSE +/- 12883.11, N = 3SE +/- 4419.84, N = 3SE +/- 3153.11, N = 3SE +/- 776.26, N = 31486892.541630926.211643872.291695910.251. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: LPUSHUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11300K600K900K1200K1500KMin: 1461793.25 / Avg: 1486892.54 / Max: 1504486.25Min: 1624452.25 / Avg: 1630926.21 / Max: 1639375.75Min: 1640446.12 / Avg: 1643872.29 / Max: 1650170.38Min: 1694395.12 / Avg: 1695910.25 / Max: 1696961.121. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native

ACES DGEMM

This is a multi-threaded DGEMM benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11510152025SE +/- 0.08, N = 3SE +/- 0.25, N = 3SE +/- 0.20, N = 5SE +/- 0.01, N = 318.7219.7919.8520.161. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11510152025Min: 18.6 / Avg: 18.72 / Max: 18.88Min: 19.33 / Avg: 19.79 / Max: 20.18Min: 19.21 / Avg: 19.85 / Max: 20.27Min: 20.13 / Avg: 20.16 / Max: 20.181. (CC) gcc options: -O3 -march=native -fopenmp

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC110.18550.3710.55650.7420.9275SE +/- 0.001869, N = 3SE +/- 0.003410, N = 3SE +/- 0.000961, N = 3SE +/- 0.000418, N = 30.8147990.8243430.8224590.820807MIN: 0.76MIN: 0.76MIN: 0.77MIN: 0.761. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11246810Min: 0.81 / Avg: 0.81 / Max: 0.82Min: 0.82 / Avg: 0.82 / Max: 0.83Min: 0.82 / Avg: 0.82 / Max: 0.82Min: 0.82 / Avg: 0.82 / Max: 0.821. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Timed MAFFT Alignment

This test performs an alignment of 100 pyruvate decarboxylase sequences. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNAUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC113691215SE +/- 0.18, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 3SE +/- 0.11, N = 313.0511.2911.8512.161. (CC) gcc options: -std=c99 -O3 -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNAUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1148121620Min: 12.7 / Avg: 13.05 / Max: 13.23Min: 11.16 / Avg: 11.28 / Max: 11.47Min: 11.72 / Avg: 11.85 / Max: 11.99Min: 11.98 / Avg: 12.16 / Max: 12.381. (CC) gcc options: -std=c99 -O3 -lm -lpthread

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: Visual Quality Optimized - Input: Bosphorus 1080pUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1150100150200250SE +/- 2.60, N = 3SE +/- 1.89, N = 9SE +/- 2.15, N = 15SE +/- 1.69, N = 3222.78226.56233.03226.811. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: Visual Quality Optimized - Input: Bosphorus 1080pUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC114080120160200Min: 218.1 / Avg: 222.78 / Max: 227.1Min: 216.37 / Avg: 226.56 / Max: 235.29Min: 223.21 / Avg: 233.03 / Max: 247.32Min: 224.38 / Avg: 226.81 / Max: 230.061. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Pennant

Pennant is an application focused on hydrodynamics on general unstructured meshes in 2D. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11246810SE +/- 0.013902, N = 3SE +/- 0.039683, N = 3SE +/- 0.004992, N = 3SE +/- 0.055343, N = 38.4620188.5410308.5463958.1997851. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC113691215Min: 8.44 / Avg: 8.46 / Max: 8.48Min: 8.49 / Avg: 8.54 / Max: 8.62Min: 8.54 / Avg: 8.55 / Max: 8.55Min: 8.1 / Avg: 8.2 / Max: 8.291. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC110.71851.4372.15552.8743.5925SE +/- 0.01090, N = 3SE +/- 0.01304, N = 3SE +/- 0.00395, N = 3SE +/- 0.01203, N = 33.173603.188743.193443.18417MIN: 2.94MIN: 2.96MIN: 2.97MIN: 2.951. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11246810Min: 3.15 / Avg: 3.17 / Max: 3.19Min: 3.17 / Avg: 3.19 / Max: 3.21Min: 3.19 / Avg: 3.19 / Max: 3.2Min: 3.16 / Avg: 3.18 / Max: 3.211. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: VMAF Optimized - Input: Bosphorus 1080pUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1160120180240300SE +/- 3.52, N = 3SE +/- 1.72, N = 3SE +/- 2.34, N = 15SE +/- 1.55, N = 3258.83265.20270.03273.041. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: VMAF Optimized - Input: Bosphorus 1080pUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1150100150200250Min: 252.95 / Avg: 258.83 / Max: 265.13Min: 262.93 / Avg: 265.2 / Max: 268.58Min: 247.32 / Avg: 270.03 / Max: 284.9Min: 271.25 / Avg: 273.04 / Max: 276.121. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1160120180240300SE +/- 3.58, N = 3SE +/- 3.60, N = 3SE +/- 1.92, N = 15SE +/- 2.29, N = 3267.36266.01278.26277.391. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC1150100150200250Min: 260.87 / Avg: 267.36 / Max: 273.22Min: 260.98 / Avg: 266.01 / Max: 272.98Min: 265.49 / Avg: 278.26 / Max: 291.97Min: 273.85 / Avg: 277.39 / Max: 281.691. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.2.0Scene: MemorialUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11816243240SE +/- 0.41, N = 3SE +/- 0.05, N = 3SE +/- 0.20, N = 3SE +/- 0.19, N = 335.4735.3835.6235.21
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.2.0Scene: MemorialUbuntu 19.04Ubuntu 21.04 DevUbuntu 21.04 Dev + Linux 5.11Ubuntu 21.04 Dev + Linux 5.11 + GCC11816243240Min: 35.01 / Avg: 35.47 / Max: 36.3Min: 35.28 / Avg: 35.38 / Max: 35.45Min: 35.38 / Avg: 35.62 / Max: 36.01Min: 35.02 / Avg: 35.21 / Max: 35.6

Ubuntu 19.04

Processor: 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 378GB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: llvmpipe, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE

OS: Ubuntu 19.04, Kernel: 5.0.0-38-generic (x86_64), Desktop: GNOME Shell 3.32.2, Display Server: X Server 1.20.4, OpenGL: 3.3 Mesa 19.0.8 (LLVM 8.0 256 bits), Compiler: GCC 8.3.0, File-System: ext4, Screen Resolution: 1024x768

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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 powersave - CPU Microcode: 0x500002c
Python Notes: Python 2.7.16 + Python 3.7.3
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled

Testing initiated at 8 February 2021 12:50 by user phoronix.

Ubuntu 21.04 Dev

Processor: 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 378GB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE

OS: Ubuntu 21.04, Kernel: 5.8.0-36-generic (x86_64), Desktop: GNOME Shell 3.38.2, Display Server: X Server 1.20.9, Vulkan: 1.0.2, Compiler: GCC 10.2.1 20210130, File-System: ext4, Screen Resolution: 1024x768

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-YIlI3N/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-YIlI3N/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --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
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x5003003
Python Notes: Python 3.9.1+
Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled

Testing initiated at 9 February 2021 11:55 by user phoronix.

Ubuntu 21.04 Dev + Linux 5.11

Processor: 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 378GB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE

OS: Ubuntu 21.04, Kernel: 5.11.0-051100rc7daily20210209-generic (x86_64) 20210208, Desktop: GNOME Shell 3.38.2, Display Server: X Server 1.20.9, Vulkan: 1.0.2, Compiler: GCC 10.2.1 20210130, File-System: ext4, Screen Resolution: 1024x768

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-YIlI3N/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-YIlI3N/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --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
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x5003003
Python Notes: Python 3.9.1+
Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled

Testing initiated at 10 February 2021 05:27 by user phoronix.

Ubuntu 21.04 Dev + Linux 5.11 + GCC11

Processor: 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 378GB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE

OS: Ubuntu 21.04, Kernel: 5.11.0-051100rc7daily20210209-generic (x86_64) 20210208, Desktop: GNOME Shell 3.38.2, Display Server: X Server 1.20.9, Vulkan: 1.0.2, Compiler: GCC 11.0.0 20210115, File-System: ext4, Screen Resolution: 1024x768

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"
Compiler Notes: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-snapshot-nHdSaM/gcc-snapshot-20210115/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-nHdSaM/gcc-snapshot-20210115/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --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
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x5003003
Python Notes: Python 3.9.1+
Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled

Testing initiated at 10 February 2021 20:09 by user phoronix.