Microsoft Azure HBv4 HPC Performance Benchmarks

Benchmarks for a future article on Phoronix looking at HBv4 Genoa-X Linux performance..

HTML result view exported from: https://openbenchmarking.org/result/2308011-PTS-AZUREHBV71&sro&gru.

Microsoft Azure HBv4 HPC Performance BenchmarksProcessorMotherboardMemoryDiskGraphicsOSKernelCompilerFile-SystemScreen ResolutionSystem LayerHCHBv2HBv3HBv42 x Intel Xeon Platinum 8168 (44 Cores)Microsoft Virtual Machine (Hyper-V UEFI v4.1 BIOS)1 GB + 60928 MB + 118272 MB + 176 GB32GB Virtual Disk + 752GB Virtual Diskhyperv_fbAlmaLinux 8.84.18.0-425.3.1.el8.x86_64 (x86_64)GCC 13.1.0 + CUDA 12.1nfs1024x768microsoft2 x AMD EPYC 7V12 64-Core (120 Cores)1 GB + 59 GB + 54 GB + 114 GB + 114 GB + 114 GB960GB Microsoft NVMe Direct Disk + 32GB Virtual Disk + 515GB Virtual Disk2 x AMD EPYC 7V73X 64-Core (120 Cores)2 x 960GB Microsoft NVMe Direct Disk + 32GB Virtual Disk + 515GB Virtual Disk2 x AMD EPYC 9V33X 96-Core (176 Cores)1 GB + 59 GB + 116 GB + 176 GB + 176 GB + 176 GB2 x 1920GB Microsoft NVMe Direct Disk + 32GB Virtual Disk + 515GB Virtual DiskOpenBenchmarking.orgKernel Details- Transparent Huge Pages: alwaysEnvironment Details- CFLAGS="-O3 -march=native" CXXFLAGS="-O3 -march=native"Compiler Details- --disable-multilib --enable-checking=releaseProcessor Details- CPU Microcode: 0xffffffffPython Details- Python 3.6.8Security Details- HC: itlb_multihit: Not affected + l1tf: Mitigation of PTE Inversion + mds: Vulnerable: Clear buffers attempted no microcode; SMT Host state unknown + meltdown: Mitigation of PTI + mmio_stale_data: Vulnerable: Clear buffers attempted no microcode; SMT Host state unknown + retbleed: Vulnerable + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Vulnerable: Clear buffers attempted no microcode; SMT Host state unknown - HBv2: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT disabled + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - HBv3: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - HBv4: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Microsoft Azure HBv4 HPC Performance Benchmarkshpcg: 104 104 104 - 60hpcg: 144 144 144 - 60hpcg: 160 160 160 - 60heffte: c2c - FFTW - float - 256heffte: c2c - FFTW - float - 512heffte: r2c - FFTW - float - 512heffte: c2c - FFTW - double - 512heffte: c2c - Stock - float - 256heffte: c2c - Stock - float - 512heffte: r2c - FFTW - double - 256heffte: r2c - FFTW - double - 512heffte: r2c - Stock - float - 512heffte: c2c - Stock - double - 512heffte: r2c - Stock - double - 256heffte: r2c - Stock - double - 512heffte: c2c - FFTW - float-long - 256heffte: c2c - FFTW - float-long - 512heffte: r2c - FFTW - float-long - 256heffte: r2c - FFTW - float-long - 512heffte: c2c - FFTW - double-long - 512heffte: c2c - Stock - float-long - 256heffte: c2c - Stock - float-long - 512heffte: r2c - FFTW - double-long - 256heffte: r2c - FFTW - double-long - 512heffte: r2c - Stock - float-long - 512heffte: c2c - Stock - double-long - 512heffte: r2c - Stock - double-long - 256heffte: r2c - Stock - double-long - 512mt-dgemm: Sustained Floating-Point Ratelibxsmm: 128libxsmm: 256libxsmm: 32libxsmm: 64oidn: RT.hdr_alb_nrm.3840x2160 - CPU-Onlyoidn: RT.ldr_alb_nrm.3840x2160 - CPU-Onlyoidn: RTLightmap.hdr.4096x4096 - CPU-Onlyospray: particle_volume/ao/real_timeospray: particle_volume/scivis/real_timeospray: particle_volume/pathtracer/real_timeospray: gravity_spheres_volume/dim_512/ao/real_timeospray: gravity_spheres_volume/dim_512/scivis/real_timeospray: gravity_spheres_volume/dim_512/pathtracer/real_timelaghos: Triple Point Problemlaghos: Sedov Blast Wave, ube_922_hex.meshpetsc: Streamscompress-7zip: Compression Ratingcompress-7zip: Decompression Ratingliquid-dsp: 128 - 256 - 57liquid-dsp: 176 - 256 - 32liquid-dsp: 176 - 256 - 57liquid-dsp: 176 - 256 - 512npb: BT.Cnpb: CG.Cnpb: FT.Cnpb: IS.Dnpb: MG.Cnpb: SP.Cpgbench: 1 - 500 - Read Onlypgbench: 1 - 800 - Read Onlynamd: ATPase Simulation - 327,506 Atomspennant: sedovbigpennant: leblancbigonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUpgbench: 1 - 500 - Read Only - Average Latencypgbench: 1 - 800 - Read Only - Average Latencybuild-nodejs: Time To Compileblender: BMW27 - CPU-Onlyblender: Classroom - CPU-Onlyblender: Fishy Cat - CPU-Onlyblender: Barbershop - CPU-Onlyblender: Pabellon Barcelona - CPU-OnlyHCHBv2HBv3HBv425.997125.865925.563558.356762.9750114.02533.519359.729257.764357.310160.8804110.04931.571860.572759.821658.549862.9027122.772113.94033.554559.552757.920357.129060.8204110.19731.584660.887259.895414.0720271284.8904.1384.9748.11.851.850.878.996188.8783196.76309.522939.0268910.0611156.52247.49151286.2491216451150841157063333315366333331683033333544626667106230.5227619.0555288.191864.6863404.0141543.94135351011594920.5269725.0195610.64548707.322442.4710.3690.690330.61349.95138.5171.76526.93175.0737.041036.086636.016791.538395.8801191.77547.605091.260193.792391.918691.4802190.94946.979493.313794.530190.788396.4941200.035191.14147.369692.129093.257388.608191.4296189.20846.928992.388395.19896.3954151011.41128.3164.8331.42.032.010.9622.366822.1747162.4498.668888.3232313.9416183.82345.14197895.4717501534388577430913333342755333334350100000924243333241509.8836367.3598485.233977.02108985.72104771.90246732824813200.265055.9158053.4668851367.73910.9370.2030.323194.36719.5850.9526.43211.4664.8439.609338.973939.1106103.5147135.694254.25257.3307103.409123.242103.2457121.283232.16656.2161102.7046117.731105.093135.950221.861257.41957.2263105.361124.595106.632120.957233.79756.2690105.5003118.23625.0483522273.52045.71438.12413.71.721.690.8024.471024.2197167.50411.750111.172314.6088192.74361.81284001.9162566595406516421696666738640000004281533333814950000313813.9836681.43102122.365730.01131635.41205795.59243474924789170.271116.2771073.649317886.810529.9730.2060.323185.56719.4350.7125.59188.9662.9089.384088.516087.9013256.349355.855622.580159.175244.342323.356261.903314.336596.226154.648264.954311.803255.968355.512427.101624.951159.258247.725323.696273.121315.982590.925154.568258.716311.26752.8024406655.26908.66163.05898.23.113.081.3236.654836.5446208.05038.076937.062432.5839228.15402.94598417.695710835237428595412900000618176666770950333332221966667744413.9074101.94230164.7912967.37437417.16427298.99316184831461730.143803.5813912.122074533.494411.2340.1580.254150.55810.1125.6113.7497.5233.01OpenBenchmarking.org

High Performance Conjugate Gradient

X Y Z: 104 104 104 - RT: 60

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 104 104 104 - RT: 60HBv2HBv3HBv4HC20406080100SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.26, N = 3SE +/- 0.02, N = 337.0439.6189.3826.001. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi

High Performance Conjugate Gradient

X Y Z: 144 144 144 - RT: 60

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 144 144 144 - RT: 60HBv2HBv3HBv4HC20406080100SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 336.0938.9788.5225.871. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi

High Performance Conjugate Gradient

X Y Z: 160 160 160 - RT: 60

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 160 160 160 - RT: 60HBv2HBv3HBv4HC20406080100SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.12, N = 3SE +/- 0.06, N = 336.0239.1187.9025.561. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi

HeFFTe - Highly Efficient FFT for Exascale

Test: c2c - Backend: FFTW - Precision: float - X Y Z: 256

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: FFTW - Precision: float - X Y Z: 256HBv2HBv3HBv4HC60120180240300SE +/- 0.67, N = 15SE +/- 1.41, N = 15SE +/- 1.07, N = 3SE +/- 0.07, N = 391.54103.51256.3558.361. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: c2c - Backend: FFTW - Precision: float - X Y Z: 512

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: FFTW - Precision: float - X Y Z: 512HBv2HBv3HBv4HC80160240320400SE +/- 0.47, N = 3SE +/- 0.93, N = 3SE +/- 1.24, N = 3SE +/- 0.04, N = 395.88135.69355.8662.981. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: r2c - Backend: FFTW - Precision: float - X Y Z: 512

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: FFTW - Precision: float - X Y Z: 512HBv2HBv3HBv4HC130260390520650SE +/- 1.03, N = 3SE +/- 2.52, N = 6SE +/- 2.25, N = 3SE +/- 0.09, N = 3191.78254.25622.58114.031. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: c2c - Backend: FFTW - Precision: double - X Y Z: 512

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: FFTW - Precision: double - X Y Z: 512HBv2HBv3HBv4HC4080120160200SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.34, N = 3SE +/- 0.03, N = 347.6157.33159.1833.521. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: c2c - Backend: Stock - Precision: float - X Y Z: 256

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: Stock - Precision: float - X Y Z: 256HBv2HBv3HBv4HC50100150200250SE +/- 0.61, N = 15SE +/- 0.77, N = 15SE +/- 3.04, N = 4SE +/- 0.02, N = 391.26103.41244.3459.731. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: c2c - Backend: Stock - Precision: float - X Y Z: 512

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: Stock - Precision: float - X Y Z: 512HBv2HBv3HBv4HC70140210280350SE +/- 0.34, N = 3SE +/- 0.73, N = 3SE +/- 0.80, N = 3SE +/- 0.02, N = 393.79123.24323.3657.761. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: r2c - Backend: FFTW - Precision: double - X Y Z: 256

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: FFTW - Precision: double - X Y Z: 256HBv2HBv3HBv4HC60120180240300SE +/- 1.31, N = 3SE +/- 0.75, N = 15SE +/- 5.66, N = 15SE +/- 0.25, N = 391.92103.25261.9057.311. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: r2c - Backend: FFTW - Precision: double - X Y Z: 512

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: FFTW - Precision: double - X Y Z: 512HBv2HBv3HBv4HC70140210280350SE +/- 0.15, N = 3SE +/- 0.86, N = 3SE +/- 0.50, N = 3SE +/- 0.05, N = 391.48121.28314.3460.881. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: r2c - Backend: Stock - Precision: float - X Y Z: 512

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: Stock - Precision: float - X Y Z: 512HBv2HBv3HBv4HC130260390520650SE +/- 2.04, N = 3SE +/- 1.85, N = 3SE +/- 2.14, N = 3SE +/- 0.06, N = 3190.95232.17596.23110.051. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: c2c - Backend: Stock - Precision: double - X Y Z: 512

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: Stock - Precision: double - X Y Z: 512HBv2HBv3HBv4HC306090120150SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.27, N = 3SE +/- 0.02, N = 346.9856.22154.6531.571. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: r2c - Backend: Stock - Precision: double - X Y Z: 256

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: Stock - Precision: double - X Y Z: 256HBv2HBv3HBv4HC60120180240300SE +/- 1.10, N = 4SE +/- 0.80, N = 15SE +/- 4.27, N = 12SE +/- 0.08, N = 393.31102.70264.9560.571. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: r2c - Backend: Stock - Precision: double - X Y Z: 512

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: Stock - Precision: double - X Y Z: 512HBv2HBv3HBv4HC70140210280350SE +/- 0.25, N = 3SE +/- 0.40, N = 3SE +/- 1.60, N = 3SE +/- 0.05, N = 394.53117.73311.8059.821. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: c2c - Backend: FFTW - Precision: float-long - X Y Z: 256

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: FFTW - Precision: float-long - X Y Z: 256HBv2HBv3HBv4HC60120180240300SE +/- 0.74, N = 15SE +/- 1.13, N = 3SE +/- 3.64, N = 15SE +/- 0.16, N = 390.79105.09255.9758.551. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: c2c - Backend: FFTW - Precision: float-long - X Y Z: 512

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: FFTW - Precision: float-long - X Y Z: 512HBv2HBv3HBv4HC80160240320400SE +/- 0.05, N = 3SE +/- 0.58, N = 3SE +/- 1.18, N = 3SE +/- 0.04, N = 396.49135.95355.5162.901. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: r2c - Backend: FFTW - Precision: float-long - X Y Z: 256

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: FFTW - Precision: float-long - X Y Z: 256HBv2HBv3HBv4HC90180270360450SE +/- 3.34, N = 12SE +/- 3.45, N = 15SE +/- 10.91, N = 15SE +/- 0.53, N = 3200.04221.86427.10122.771. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: r2c - Backend: FFTW - Precision: float-long - X Y Z: 512

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: FFTW - Precision: float-long - X Y Z: 512HBv2HBv3HBv4HC130260390520650SE +/- 1.39, N = 3SE +/- 2.91, N = 3SE +/- 4.23, N = 3SE +/- 0.18, N = 3191.14257.42624.95113.941. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: c2c - Backend: FFTW - Precision: double-long - X Y Z: 512

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: FFTW - Precision: double-long - X Y Z: 512HBv2HBv3HBv4HC4080120160200SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 347.3757.23159.2633.551. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: c2c - Backend: Stock - Precision: float-long - X Y Z: 256

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: Stock - Precision: float-long - X Y Z: 256HBv2HBv3HBv4HC50100150200250SE +/- 1.33, N = 3SE +/- 1.07, N = 6SE +/- 4.85, N = 15SE +/- 0.27, N = 392.13105.36247.7359.551. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: c2c - Backend: Stock - Precision: float-long - X Y Z: 512

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: Stock - Precision: float-long - X Y Z: 512HBv2HBv3HBv4HC70140210280350SE +/- 0.23, N = 3SE +/- 0.05, N = 3SE +/- 0.96, N = 3SE +/- 0.06, N = 393.26124.60323.7057.921. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: r2c - Backend: FFTW - Precision: double-long - X Y Z: 256

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: FFTW - Precision: double-long - X Y Z: 256HBv2HBv3HBv4HC60120180240300SE +/- 1.12, N = 15SE +/- 1.05, N = 3SE +/- 4.03, N = 14SE +/- 0.12, N = 388.61106.63273.1257.131. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: r2c - Backend: FFTW - Precision: double-long - X Y Z: 512

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: FFTW - Precision: double-long - X Y Z: 512HBv2HBv3HBv4HC70140210280350SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 1.65, N = 3SE +/- 0.06, N = 391.43120.96315.9860.821. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: r2c - Backend: Stock - Precision: float-long - X Y Z: 512

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: Stock - Precision: float-long - X Y Z: 512HBv2HBv3HBv4HC130260390520650SE +/- 1.02, N = 3SE +/- 0.15, N = 3SE +/- 2.49, N = 3SE +/- 0.10, N = 3189.21233.80590.93110.201. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: c2c - Backend: Stock - Precision: double-long - X Y Z: 512

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: Stock - Precision: double-long - X Y Z: 512HBv2HBv3HBv4HC306090120150SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 346.9356.27154.5731.581. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: r2c - Backend: Stock - Precision: double-long - X Y Z: 256

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: Stock - Precision: double-long - X Y Z: 256HBv2HBv3HBv4HC60120180240300SE +/- 1.27, N = 3SE +/- 0.81, N = 15SE +/- 2.84, N = 15SE +/- 0.19, N = 392.39105.50258.7260.891. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: r2c - Backend: Stock - Precision: double-long - X Y Z: 512

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: Stock - Precision: double-long - X Y Z: 512HBv2HBv3HBv4HC70140210280350SE +/- 0.16, N = 3SE +/- 0.49, N = 3SE +/- 0.81, N = 3SE +/- 0.03, N = 395.20118.24311.2759.901. (CXX) g++ options: -O3 -pthread

ACES DGEMM

Sustained Floating-Point Rate

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateHBv2HBv3HBv4HC1224364860SE +/- 0.275809, N = 12SE +/- 0.146977, N = 3SE +/- 0.581762, N = 5SE +/- 0.474074, N = 126.39541525.04835252.80244014.0720271. (CC) gcc options: -O3 -march=native -fopenmp

libxsmm

M N K: 128

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 128HBv2HBv3HBv4HC14002800420056007000SE +/- 169.50, N = 9SE +/- 20.51, N = 9SE +/- 59.23, N = 3SE +/- 13.64, N = 151011.42273.56655.21284.81. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lpthread -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -pedantic -O2 -fopenmp -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -march=core-avx2

libxsmm

M N K: 256

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 256HBv2HBv3HBv4HC15003000450060007500SE +/- 17.53, N = 9SE +/- 25.11, N = 4SE +/- 57.85, N = 9SE +/- 23.39, N = 91128.32045.76908.6904.11. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lpthread -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -pedantic -O2 -fopenmp -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -march=core-avx2

libxsmm

M N K: 32

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 32HBv2HBv3HBv4HC13002600390052006500SE +/- 1.72, N = 3SE +/- 38.99, N = 12SE +/- 87.98, N = 3SE +/- 3.15, N = 9164.81438.16163.0384.91. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lpthread -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -pedantic -O2 -fopenmp -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -march=core-avx2

libxsmm

M N K: 64

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 64HBv2HBv3HBv4HC13002600390052006500SE +/- 2.64, N = 15SE +/- 8.24, N = 3SE +/- 74.65, N = 3SE +/- 7.70, N = 3331.42413.75898.2748.11. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lpthread -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -pedantic -O2 -fopenmp -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -march=core-avx2

Intel Open Image Denoise

Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.0Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-OnlyHBv2HBv3HBv4HC0.69981.39962.09942.79923.499SE +/- 0.01, N = 3SE +/- 0.02, N = 4SE +/- 0.03, N = 3SE +/- 0.01, N = 32.031.723.111.85

Intel Open Image Denoise

Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.0Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-OnlyHBv2HBv3HBv4HC0.6931.3862.0792.7723.465SE +/- 0.01, N = 3SE +/- 0.01, N = 15SE +/- 0.02, N = 3SE +/- 0.00, N = 32.011.693.081.85

Intel Open Image Denoise

Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.0Run: RTLightmap.hdr.4096x4096 - Device: CPU-OnlyHBv2HBv3HBv4HC0.2970.5940.8911.1881.485SE +/- 0.01, N = 15SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 30.960.801.320.87

OSPRay

Benchmark: particle_volume/ao/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/ao/real_timeHBv2HBv3HBv4HC816243240SE +/- 0.00858, N = 3SE +/- 0.00987, N = 3SE +/- 0.04011, N = 3SE +/- 0.01510, N = 322.3668024.4710036.654808.99618

OSPRay

Benchmark: particle_volume/scivis/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/scivis/real_timeHBv2HBv3HBv4HC816243240SE +/- 0.02944, N = 3SE +/- 0.00564, N = 3SE +/- 0.05762, N = 3SE +/- 0.05412, N = 322.1747024.2197036.544608.87831

OSPRay

Benchmark: particle_volume/pathtracer/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/pathtracer/real_timeHBv2HBv3HBv4HC50100150200250SE +/- 0.83, N = 3SE +/- 1.50, N = 7SE +/- 0.81, N = 3SE +/- 7.22, N = 9162.45167.50208.0596.76

OSPRay

Benchmark: gravity_spheres_volume/dim_512/ao/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/ao/real_timeHBv2HBv3HBv4HC918273645SE +/- 0.15055, N = 15SE +/- 0.01464, N = 3SE +/- 0.02835, N = 3SE +/- 0.03191, N = 38.6688811.7501038.076909.52293

OSPRay

Benchmark: gravity_spheres_volume/dim_512/scivis/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeHBv2HBv3HBv4HC918273645SE +/- 0.13284, N = 15SE +/- 0.02977, N = 3SE +/- 0.12574, N = 3SE +/- 0.01641, N = 38.3232311.1723037.062409.02689

OSPRay

Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeHBv2HBv3HBv4HC816243240SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 313.9414.6132.5810.06

Laghos

Test: Triple Point Problem

OpenBenchmarking.orgMajor Kernels Total Rate, More Is BetterLaghos 3.1Test: Triple Point ProblemHBv2HBv3HBv4HC50100150200250SE +/- 0.57, N = 3SE +/- 0.38, N = 3SE +/- 1.25, N = 3SE +/- 0.08, N = 3183.82192.74228.15156.521. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -pthread -lmpi

Laghos

Test: Sedov Blast Wave, ube_922_hex.mesh

OpenBenchmarking.orgMajor Kernels Total Rate, More Is BetterLaghos 3.1Test: Sedov Blast Wave, ube_922_hex.meshHBv2HBv3HBv4HC90180270360450SE +/- 3.57, N = 5SE +/- 0.15, N = 3SE +/- 0.78, N = 3SE +/- 1.35, N = 3345.14361.81402.94247.491. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -pthread -lmpi

PETSc

Test: Streams

OpenBenchmarking.orgMB/s, More Is BetterPETSc 3.19Test: StreamsHBv2HBv3HBv4HC130K260K390K520K650KSE +/- 12025.83, N = 6SE +/- 2674.31, N = 7SE +/- 46271.80, N = 9SE +/- 256.75, N = 3197895.47284001.92598417.70151286.251. (CXX) g++ options: -O3 -std=gnu++17 -fPIC -include -m64

7-Zip Compression

Test: Compression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingHBv2HBv3HBv4HC200K400K600K800K1000KSE +/- 3504.63, N = 3SE +/- 7198.45, N = 3SE +/- 4158.65, N = 3SE +/- 672.17, N = 350153456659510835232164511. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

7-Zip Compression

Test: Decompression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingHBv2HBv3HBv4HC160K320K480K640K800KSE +/- 10621.28, N = 3SE +/- 3365.82, N = 3SE +/- 8621.97, N = 3SE +/- 300.63, N = 33885774065167428591508411. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Liquid-DSP

Threads: 128 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 57HBv2HBv3HBv4HC1200M2400M3600M4800M6000MSE +/- 14518991.39, N = 3SE +/- 6263474.36, N = 3SE +/- 24008123.63, N = 3SE +/- 4733333.33, N = 343091333334216966667541290000015706333331. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 176 - Buffer Length: 256 - Filter Length: 32

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 176 - Buffer Length: 256 - Filter Length: 32HBv2HBv3HBv4HC1300M2600M3900M5200M6500MSE +/- 25439885.57, N = 3SE +/- 2858321.19, N = 3SE +/- 6999365.05, N = 3SE +/- 8873431.00, N = 342755333333864000000618176666715366333331. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 176 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 176 - Buffer Length: 256 - Filter Length: 57HBv2HBv3HBv4HC1500M3000M4500M6000M7500MSE +/- 8195730.60, N = 3SE +/- 8996542.55, N = 3SE +/- 36788419.07, N = 3SE +/- 7033807.25, N = 343501000004281533333709503333316830333331. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 176 - Buffer Length: 256 - Filter Length: 512

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 176 - Buffer Length: 256 - Filter Length: 512HBv2HBv3HBv4HC500M1000M1500M2000M2500MSE +/- 3265385.80, N = 3SE +/- 1919487.78, N = 3SE +/- 5336145.09, N = 3SE +/- 2270626.44, N = 392424333381495000022219666675446266671. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

NAS Parallel Benchmarks

Test / Class: BT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CHBv2HBv3HBv4HC160K320K480K640K800KSE +/- 108.10, N = 3SE +/- 2034.04, N = 3SE +/- 6061.11, N = 3SE +/- 62.47, N = 3241509.88313813.98744413.90106230.521. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

NAS Parallel Benchmarks

Test / Class: CG.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CHBv2HBv3HBv4HC16K32K48K64K80KSE +/- 778.45, N = 15SE +/- 503.29, N = 3SE +/- 599.32, N = 3SE +/- 218.98, N = 336367.3536681.4374101.9427619.051. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

NAS Parallel Benchmarks

Test / Class: FT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CHBv2HBv3HBv4HC50K100K150K200K250KSE +/- 320.45, N = 3SE +/- 339.33, N = 3SE +/- 1773.50, N = 3SE +/- 131.36, N = 398485.23102122.36230164.7955288.191. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

NAS Parallel Benchmarks

Test / Class: IS.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DHBv2HBv3HBv4HC3K6K9K12K15KSE +/- 35.84, N = 7SE +/- 67.99, N = 4SE +/- 308.75, N = 15SE +/- 7.55, N = 33977.025730.0112967.371864.681. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

NAS Parallel Benchmarks

Test / Class: MG.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CHBv2HBv3HBv4HC90K180K270K360K450KSE +/- 768.30, N = 3SE +/- 1313.15, N = 15SE +/- 5249.92, N = 15SE +/- 149.23, N = 3108985.72131635.41437417.1663404.011. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

NAS Parallel Benchmarks

Test / Class: SP.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CHBv2HBv3HBv4HC90K180K270K360K450KSE +/- 324.54, N = 3SE +/- 1576.20, N = 3SE +/- 2970.97, N = 15SE +/- 105.69, N = 3104771.90205795.59427298.9941543.941. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

PostgreSQL

Scaling Factor: 1 - Clients: 500 - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 500 - Mode: Read OnlyHBv2HBv3HBv4HC700K1400K2100K2800K3500KSE +/- 4710.42, N = 3SE +/- 28428.57, N = 4SE +/- 3042.04, N = 3SE +/- 2849.38, N = 324673282434749316184813535101. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL

Scaling Factor: 1 - Clients: 800 - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 800 - Mode: Read OnlyHBv2HBv3HBv4HC700K1400K2100K2800K3500KSE +/- 9212.17, N = 3SE +/- 13675.06, N = 3SE +/- 2972.36, N = 3SE +/- 2818.34, N = 324813202478917314617311594921. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsHBv2HBv3HBv4HC0.11860.23720.35580.47440.593SE +/- 0.00069, N = 3SE +/- 0.00015, N = 3SE +/- 0.00011, N = 3SE +/- 0.00060, N = 30.265050.271110.143800.52697

Pennant

Test: sedovbig

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigHBv2HBv3HBv4HC612182430SE +/- 0.011742, N = 3SE +/- 0.027453, N = 3SE +/- 0.018282, N = 3SE +/- 0.026763, N = 35.9158056.2771073.58139125.0195601. (CXX) g++ options: -fopenmp -pthread -lmpi

Pennant

Test: leblancbig

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigHBv2HBv3HBv4HC3691215SE +/- 0.009233, N = 3SE +/- 0.006682, N = 3SE +/- 0.029043, N = 3SE +/- 0.017495, N = 33.4668853.6493172.12207410.6454801. (CXX) g++ options: -fopenmp -pthread -lmpi

oneDNN

Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUHBv2HBv3HBv4HC30060090012001500SE +/- 13.52, N = 15SE +/- 6.66, N = 3SE +/- 1.90, N = 3SE +/- 1.51, N = 31367.73886.81533.49707.32MIN: 849.06MIN: 518.68MIN: 687.141. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUHBv2HBv3HBv4HC2004006008001000SE +/- 9.54, N = 15SE +/- 4.36, N = 3SE +/- 3.60, N = 8SE +/- 1.89, N = 3910.94529.97411.23442.47MIN: 469.93MIN: 429.931. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

PostgreSQL

Scaling Factor: 1 - Clients: 500 - Mode: Read Only - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 500 - Mode: Read Only - Average LatencyHBv2HBv3HBv4HC0.0830.1660.2490.3320.415SE +/- 0.000, N = 3SE +/- 0.002, N = 4SE +/- 0.000, N = 3SE +/- 0.001, N = 30.2030.2060.1580.3691. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL

Scaling Factor: 1 - Clients: 800 - Mode: Read Only - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 800 - Mode: Read Only - Average LatencyHBv2HBv3HBv4HC0.15530.31060.46590.62120.7765SE +/- 0.001, N = 3SE +/- 0.002, N = 3SE +/- 0.000, N = 3SE +/- 0.002, N = 30.3230.3230.2540.6901. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Timed Node.js Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 19.8.1Time To CompileHBv2HBv3HBv4HC70140210280350SE +/- 1.32, N = 3SE +/- 1.46, N = 3SE +/- 2.23, N = 12SE +/- 2.37, N = 3194.37185.57150.56330.61

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: BMW27 - Compute: CPU-OnlyHBv2HBv3HBv4HC1122334455SE +/- 0.16, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 3SE +/- 0.36, N = 319.5819.4310.1149.95

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Classroom - Compute: CPU-OnlyHBv2HBv3HBv4HC306090120150SE +/- 0.15, N = 3SE +/- 0.06, N = 3SE +/- 0.11, N = 3SE +/- 0.04, N = 350.9550.7125.61138.51

Blender

Blend File: Fishy Cat - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Fishy Cat - Compute: CPU-OnlyHBv2HBv3HBv4HC1632486480SE +/- 0.04, N = 3SE +/- 0.15, N = 3SE +/- 0.09, N = 3SE +/- 0.23, N = 326.4325.5913.7471.76

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Barbershop - Compute: CPU-OnlyHBv2HBv3HBv4HC110220330440550SE +/- 0.22, N = 3SE +/- 0.38, N = 3SE +/- 0.47, N = 3SE +/- 1.15, N = 3211.46188.9697.52526.93

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Pabellon Barcelona - Compute: CPU-OnlyHBv2HBv3HBv4HC4080120160200SE +/- 0.28, N = 3SE +/- 0.45, N = 3SE +/- 0.12, N = 3SE +/- 0.33, N = 364.8462.9033.01175.07

Phoronix Test Suite v10.8.5