Microsoft Azure HBv4 HPC Comparison Benchmarks

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

HTML result view exported from: https://openbenchmarking.org/result/2307054-PTS-AZUREHPC63&rdt&grw.

Microsoft Azure HBv4 HPC Comparison BenchmarksProcessorMotherboardMemoryDiskGraphicsOSKernelCompilerFile-SystemScreen ResolutionSystem LayerHBv4HBv3HBv2HC2 x AMD EPYC 9V33X 96-Core (176 Cores)Microsoft Virtual Machine (Hyper-V UEFI v4.1 BIOS)1 GB + 59 GB + 116 GB + 176 GB + 176 GB + 176 GB2 x 1920GB Microsoft NVMe Direct Disk + 32GB Virtual Disk + 515GB Virtual Diskhyperv_fbAlmaLinux 8.84.18.0-425.3.1.el8.x86_64 (x86_64)GCC 8.5.0 20210514 + CUDA 12.1nfs1024x768microsoft2 x AMD EPYC 7V73X 64-Core (120 Cores)1 GB + 59 GB + 54 GB + 114 GB + 114 GB + 114 GB2 x 960GB Microsoft NVMe Direct Disk + 32GB Virtual Disk + 515GB Virtual DiskAlmaLinux 8.72 x AMD EPYC 7V12 64-Core (120 Cores)960GB Microsoft NVMe Direct Disk + 32GB Virtual Disk + 515GB Virtual Disk2 x Intel Xeon Platinum 8168 (44 Cores)1 GB + 60928 MB + 118272 MB + 176 GB32GB Virtual Disk + 752GB Virtual DiskOpenBenchmarking.orgKernel Details- Transparent Huge Pages: alwaysCompiler Details- --build=x86_64-redhat-linux --disable-libmpx --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-gcc-major-version-only --with-isl --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver Processor Details- CPU Microcode: 0xffffffffPython Details- Python 3.6.8Security Details- 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 - 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 - 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 - 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

Microsoft Azure HBv4 HPC Comparison Benchmarksheffte: r2c - FFTW - double - 512heffte: r2c - Stock - float - 512hpcg: 144 144 144 - 60heffte: r2c - Stock - double-long - 512heffte: r2c - FFTW - float - 256heffte: c2c - FFTW - double - 128hpcg: 160 160 160 - 60heffte: c2c - FFTW - float - 256npb: BT.Cnpb: CG.Cnpb: EP.Dnpb: FT.Cnpb: IS.Dnpb: MG.Conednn: IP Shapes 1D - f32 - CPUheffte: r2c - Stock - double - 256npb: SP.Cheffte: c2c - FFTW - float - 512namd: ATPase Simulation - 327,506 Atomsheffte: r2c - FFTW - float - 512libxsmm: 128heffte: c2c - FFTW - double - 256libxsmm: 256heffte: c2c - Stock - double-long - 512libxsmm: 32heffte: r2c - FFTW - double - 256libxsmm: 64heffte: r2c - Stock - float - 256laghos: Triple Point Problemheffte: c2c - Stock - double - 128laghos: Sedov Blast Wave, ube_922_hex.meshheffte: c2c - Stock - double - 512heffte: c2c - FFTW - double - 512onednn: IP Shapes 3D - f32 - CPUheffte: r2c - FFTW - double-long - 512heffte: c2c - Stock - float - 256heffte: c2c - Stock - float-long - 512heffte: r2c - FFTW - double-long - 256heffte: c2c - FFTW - double-long - 512heffte: c2c - Stock - float-long - 256heffte: c2c - FFTW - double-long - 128heffte: c2c - FFTW - double-long - 256heffte: r2c - FFTW - float-long - 512heffte: r2c - FFTW - float-long - 256heffte: c2c - FFTW - float-long - 512heffte: c2c - FFTW - float-long - 256onednn: Convolution Batch Shapes Auto - f32 - CPUheffte: c2c - Stock - double-long - 256heffte: c2c - Stock - float - 512heffte: r2c - Stock - double-long - 256heffte: c2c - Stock - double - 256onednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUheffte: r2c - Stock - double - 512onednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUmt-dgemm: Sustained Floating-Point Rateremhos: Sample Remap Examplepennant: sedovbigpennant: leblancbigcompress-7zip: Compression Ratingcompress-7zip: Decompression Ratingbuild-linux-kernel: allmodconfigheffte: r2c - Stock - float-long - 256blender: BMW27 - CPU-Onlyblender: Classroom - CPU-Onlyblender: Fishy Cat - CPU-Onlyblender: Barbershop - CPU-Onlyblender: Pabellon Barcelona - CPU-Onlyoidn: 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_timeheffte: r2c - Stock - float-long - 512build-nodejs: Time To Compileliquid-dsp: 1 - 256 - 32liquid-dsp: 32 - 256 - 32liquid-dsp: 32 - 256 - 57liquid-dsp: 128 - 256 - 32liquid-dsp: 128 - 256 - 57liquid-dsp: 176 - 256 - 32liquid-dsp: 176 - 256 - 57liquid-dsp: 176 - 256 - 512pgbench: 1 - 500 - Read Onlypgbench: 1 - 500 - Read Only - Average Latencypgbench: 1 - 800 - Read Onlypgbench: 1 - 800 - Read Only - Average Latencypetsc: Streamshpcg: 104 104 104 - 60HBv4HBv3HBv2HC314.336596.22688.5160311.267442.82980.251487.9013256.349151067.8140326.295985.7569051.635870.00108125.860.752929264.95468819.34355.8550.14292622.5806585.6123.3916983.2154.5685006.8261.9035719.0459.918228.1587.6623402.94154.648159.1750.306141315.982244.342323.696273.121159.258247.72585.0078122.981624.951427.101355.512255.9680.276472123.408323.356258.716121.6050.582806535.853311.803401.855533.494411.23453.17569115.3703.5813912.12207410322677279951681.255467.7189.9725.2613.9696.7733.403.083.131.2936.612136.5671208.33838.076437.091832.7911590.925150.55835362667111330000013905400004426300000516823333361222333336758166667205823333331398460.15931230420.256598417.695789.3840121.283232.16638.9739118.236198.66059.381139.1106103.514762427.8621551.482879.0836619.292793.5546705.470.910091102.704631024.76135.6940.27115254.2522284.639.81172032.156.26901506.3103.24572435.6214.063192.7450.6068361.8156.216157.33070.624233120.957103.409124.595106.63257.2263105.36156.869339.3709257.419221.861135.950105.0930.55674138.5694123.242105.500338.44611.40862860.975117.731533.496886.810529.97325.10487615.2566.2771073.6493175582903975051889.463207.97419.4951.0825.47189.3062.641.681.690.7924.458624.1736168.24211.748511.184514.6067233.797185.567328173339173366671086000000336673333335163000003419533333356343333373537000023750050.21024076020.332284001.916239.609391.4802190.94936.086695.1989203.77259.424436.016791.538366829.1822314.023222.8241977.691884.2243410.711.4075893.313732495.8995.88010.26385191.7751519.550.90321444.246.9289195.191.9186411.7205.206183.8251.3955345.1446.979447.60506.8382591.429691.260193.257388.608147.369692.129061.140351.1954191.141200.03596.494190.78830.57387850.075993.792392.388350.70701.610021345.1494.5301896.8131367.73910.9375.89990314.9315.9158053.4668854894563710441782.933211.41819.4650.8626.19210.1864.142.082.031.0422.333622.1533157.1338.673278.1235613.9151189.208194.3673321166710614333331193400000392593333340459333334027100000410670000082565333324662490.20324396500.328197895.471737.041060.8804110.04925.865959.8954123.63259.144225.563558.356728794.2814356.201642.0320188.891181.4819508.000.88244660.572712907.5462.97500.52650114.0251328.430.1190898.831.5846379.957.3101731.6134.760156.5241.7345247.4931.571833.51932.0792060.820459.729257.920357.129033.554559.552758.912530.2175113.940122.77262.902758.54983.1112130.267257.764360.887230.16631.24480707.35359.8216450.247707.322442.47114.34083027.37825.0195610.645482107321481931950.626131.96250.53138.8172.57524.86176.211.821.840.888.975478.9702086.57349.494218.9872310.0490110.197330.61331796333964423333721290909151260000015724000001566133333166473333352921333313548770.36911618000.688151286.249125.9971OpenBenchmarking.org

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: 512HBv4HBv3HBv2HC70140210280350SE +/- 0.50, N = 3SE +/- 0.86, N = 3SE +/- 0.15, N = 3SE +/- 0.05, N = 3314.34121.2891.4860.881. (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: 512HBv4HBv3HBv2HC130260390520650SE +/- 2.14, N = 3SE +/- 1.85, N = 3SE +/- 2.04, N = 3SE +/- 0.06, N = 3596.23232.17190.95110.051. (CXX) g++ options: -O3 -pthread

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: 60HBv4HBv3HBv2HC20406080100SE +/- 0.11, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 388.5238.9736.0925.871. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi

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: 512HBv4HBv3HBv2HC70140210280350SE +/- 0.81, N = 3SE +/- 0.49, N = 3SE +/- 0.16, N = 3SE +/- 0.03, N = 3311.27118.2495.2059.901. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

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

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: FFTW - Precision: float - X Y Z: 256HBv4HBv3HBv2HC100200300400500SE +/- 14.97, N = 12SE +/- 5.11, N = 15SE +/- 1.85, N = 3SE +/- 0.52, N = 3442.83198.66203.77123.631. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: c2c - Backend: FFTW - Precision: double - X Y Z: 128

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: FFTW - Precision: double - X Y Z: 128HBv4HBv3HBv2HC20406080100SE +/- 3.67, N = 15SE +/- 1.84, N = 15SE +/- 1.72, N = 15SE +/- 0.65, N = 580.2559.3859.4259.141. (CXX) g++ options: -O3 -pthread

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: 60HBv4HBv3HBv2HC20406080100SE +/- 0.12, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 387.9039.1136.0225.561. (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: 256HBv4HBv3HBv2HC60120180240300SE +/- 1.07, N = 3SE +/- 1.41, N = 15SE +/- 0.67, N = 15SE +/- 0.07, N = 3256.35103.5191.5458.361. (CXX) g++ options: -O3 -pthread

NAS Parallel Benchmarks

Test / Class: BT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CHBv4HBv3HBv2HC30K60K90K120K150KSE +/- 760.56, N = 3SE +/- 36.56, N = 3SE +/- 32.07, N = 3SE +/- 15.19, N = 3151067.8162427.8666829.1828794.281. (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.CHBv4HBv3HBv2HC9K18K27K36K45KSE +/- 77.41, N = 3SE +/- 20.87, N = 3SE +/- 108.02, N = 3SE +/- 233.39, N = 1540326.2921551.4822314.0214356.201. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

NAS Parallel Benchmarks

Test / Class: EP.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DHBv4HBv3HBv2HC13002600390052006500SE +/- 37.41, N = 3SE +/- 80.22, N = 12SE +/- 32.15, N = 6SE +/- 1.76, N = 35985.752879.083222.821642.031. (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.CHBv4HBv3HBv2HC15K30K45K60K75KSE +/- 745.61, N = 3SE +/- 194.34, N = 3SE +/- 219.43, N = 3SE +/- 13.57, N = 369051.6336619.2941977.6920188.891. (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.DHBv4HBv3HBv2HC13002600390052006500SE +/- 17.88, N = 3SE +/- 22.55, N = 3SE +/- 11.15, N = 3SE +/- 2.10, N = 35870.002793.551884.221181.481. (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.CHBv4HBv3HBv2HC20K40K60K80K100KSE +/- 748.94, N = 13SE +/- 613.84, N = 15SE +/- 354.81, N = 3SE +/- 24.47, N = 3108125.8646705.4743410.7119508.001. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

oneDNN

Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUHBv4HBv3HBv2HC0.31670.63340.95011.26681.5835SE +/- 0.001421, N = 3SE +/- 0.013826, N = 12SE +/- 0.014464, N = 3SE +/- 0.000702, N = 30.7529290.9100911.4075800.882446MIN: 0.69MIN: 0.76MIN: 1.11MIN: 0.831. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: 256HBv4HBv3HBv2HC60120180240300SE +/- 4.27, N = 12SE +/- 0.80, N = 15SE +/- 1.10, N = 4SE +/- 0.08, N = 3264.95102.7093.3160.571. (CXX) g++ options: -O3 -pthread

NAS Parallel Benchmarks

Test / Class: SP.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CHBv4HBv3HBv2HC15K30K45K60K75KSE +/- 954.46, N = 12SE +/- 273.09, N = 8SE +/- 34.59, N = 3SE +/- 12.00, N = 368819.3431024.7632495.8912907.541. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

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: 512HBv4HBv3HBv2HC80160240320400SE +/- 1.24, N = 3SE +/- 0.93, N = 3SE +/- 0.47, N = 3SE +/- 0.04, N = 3355.86135.6995.8862.981. (CXX) g++ options: -O3 -pthread

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsHBv4HBv3HBv2HC0.11850.2370.35550.4740.5925SE +/- 0.00035, N = 3SE +/- 0.00027, N = 3SE +/- 0.00045, N = 3SE +/- 0.00096, N = 30.142920.271150.263850.52650

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: 512HBv4HBv3HBv2HC130260390520650SE +/- 2.25, N = 3SE +/- 2.52, N = 6SE +/- 1.03, N = 3SE +/- 0.09, N = 3622.58254.25191.78114.031. (CXX) g++ options: -O3 -pthread

libxsmm

M N K: 128

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 128HBv4HBv3HBv2HC14002800420056007000SE +/- 59.85, N = 3SE +/- 29.40, N = 3SE +/- 153.42, N = 6SE +/- 11.02, N = 36585.62284.61519.51328.4-msse4.2-fopenmp -march=core-avx2-msse4.2-fopenmp -march=core-avx21. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lpthread -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden

HeFFTe - Highly Efficient FFT for Exascale

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

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: FFTW - Precision: double - X Y Z: 256HBv4HBv3HBv2HC306090120150SE +/- 1.65, N = 3SE +/- 0.14, N = 3SE +/- 0.55, N = 3SE +/- 0.08, N = 3123.3939.8150.9030.121. (CXX) g++ options: -O3 -pthread

libxsmm

M N K: 256

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 256HBv4HBv3HBv2HC15003000450060007500SE +/- 63.60, N = 3SE +/- 23.34, N = 3SE +/- 51.69, N = 9SE +/- 13.41, N = 126983.22032.11444.2898.8-msse4.2-fopenmp -march=core-avx2-msse4.2-fopenmp -march=core-avx21. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lpthread -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden

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: 512HBv4HBv3HBv2HC306090120150SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 3154.5756.2746.9331.581. (CXX) g++ options: -O3 -pthread

libxsmm

M N K: 32

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 32HBv4HBv3HBv2HC11002200330044005500SE +/- 443.26, N = 12SE +/- 32.59, N = 14SE +/- 3.90, N = 12SE +/- 2.82, N = 115006.81506.3195.1379.9-msse4.2-fopenmp -march=core-avx21. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lpthread -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden

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: 256HBv4HBv3HBv2HC60120180240300SE +/- 5.66, N = 15SE +/- 0.75, N = 15SE +/- 1.31, N = 3SE +/- 0.25, N = 3261.90103.2591.9257.311. (CXX) g++ options: -O3 -pthread

libxsmm

M N K: 64

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 64HBv4HBv3HBv2HC12002400360048006000SE +/- 226.33, N = 12SE +/- 17.54, N = 12SE +/- 18.03, N = 13SE +/- 5.15, N = 155719.02435.6411.7731.6-msse4.2-fopenmp -march=core-avx2-fopenmp -march=core-avx21. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lpthread -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden

HeFFTe - Highly Efficient FFT for Exascale

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

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: Stock - Precision: float - X Y Z: 256HBv4HBv3HBv2HC100200300400500SE +/- 14.34, N = 15SE +/- 5.19, N = 15SE +/- 2.79, N = 12SE +/- 0.57, N = 3459.92214.06205.21134.761. (CXX) g++ options: -O3 -pthread

Laghos

Test: Triple Point Problem

OpenBenchmarking.orgMajor Kernels Total Rate, More Is BetterLaghos 3.1Test: Triple Point ProblemHBv4HBv3HBv2HC50100150200250SE +/- 1.25, N = 3SE +/- 0.38, N = 3SE +/- 0.57, N = 3SE +/- 0.08, N = 3228.15192.74183.82156.521. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -pthread -lmpi

HeFFTe - Highly Efficient FFT for Exascale

Test: c2c - Backend: Stock - Precision: double - X Y Z: 128

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: Stock - Precision: double - X Y Z: 128HBv4HBv3HBv2HC20406080100SE +/- 3.68, N = 14SE +/- 1.12, N = 15SE +/- 1.33, N = 15SE +/- 0.30, N = 387.6650.6151.4041.731. (CXX) g++ options: -O3 -pthread

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.meshHBv4HBv3HBv2HC90180270360450SE +/- 0.78, N = 3SE +/- 0.15, N = 3SE +/- 3.57, N = 5SE +/- 1.35, N = 3402.94361.81345.14247.491. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -pthread -lmpi

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: 512HBv4HBv3HBv2HC306090120150SE +/- 0.27, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3154.6556.2246.9831.571. (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: 512HBv4HBv3HBv2HC4080120160200SE +/- 0.34, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3159.1857.3347.6133.521. (CXX) g++ options: -O3 -pthread

oneDNN

Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUHBv4HBv3HBv2HC246810SE +/- 0.002422, N = 3SE +/- 0.039917, N = 15SE +/- 0.032665, N = 3SE +/- 0.093711, N = 120.3061410.6242336.8382502.079200MIN: 5.97MIN: 1.411. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: 512HBv4HBv3HBv2HC70140210280350SE +/- 1.65, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3315.98120.9691.4360.821. (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: 256HBv4HBv3HBv2HC50100150200250SE +/- 3.04, N = 4SE +/- 0.77, N = 15SE +/- 0.61, N = 15SE +/- 0.02, N = 3244.34103.4191.2659.731. (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: 512HBv4HBv3HBv2HC70140210280350SE +/- 0.96, N = 3SE +/- 0.05, N = 3SE +/- 0.23, N = 3SE +/- 0.06, N = 3323.70124.6093.2657.921. (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: 256HBv4HBv3HBv2HC60120180240300SE +/- 4.03, N = 14SE +/- 1.05, N = 3SE +/- 1.12, N = 15SE +/- 0.12, N = 3273.12106.6388.6157.131. (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: 512HBv4HBv3HBv2HC4080120160200SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3159.2657.2347.3733.551. (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: 256HBv4HBv3HBv2HC50100150200250SE +/- 4.85, N = 15SE +/- 1.07, N = 6SE +/- 1.33, N = 3SE +/- 0.27, N = 3247.73105.3692.1359.551. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

Test: c2c - Backend: FFTW - Precision: double-long - X Y Z: 128

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: FFTW - Precision: double-long - X Y Z: 128HBv4HBv3HBv2HC20406080100SE +/- 4.77, N = 15SE +/- 0.34, N = 3SE +/- 1.30, N = 15SE +/- 0.23, N = 385.0156.8761.1458.911. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

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

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: FFTW - Precision: double-long - X Y Z: 256HBv4HBv3HBv2HC306090120150SE +/- 1.21, N = 15SE +/- 0.33, N = 3SE +/- 0.57, N = 3SE +/- 0.05, N = 3122.9839.3751.2030.221. (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: 512HBv4HBv3HBv2HC130260390520650SE +/- 4.23, N = 3SE +/- 2.91, N = 3SE +/- 1.39, N = 3SE +/- 0.18, N = 3624.95257.42191.14113.941. (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: 256HBv4HBv3HBv2HC90180270360450SE +/- 10.91, N = 15SE +/- 3.45, N = 15SE +/- 3.34, N = 12SE +/- 0.53, N = 3427.10221.86200.04122.771. (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: 512HBv4HBv3HBv2HC80160240320400SE +/- 1.18, N = 3SE +/- 0.58, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3355.51135.9596.4962.901. (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: 256HBv4HBv3HBv2HC60120180240300SE +/- 3.64, N = 15SE +/- 1.13, N = 3SE +/- 0.74, N = 15SE +/- 0.16, N = 3255.97105.0990.7958.551. (CXX) g++ options: -O3 -pthread

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUHBv4HBv3HBv2HC0.71.42.12.83.5SE +/- 0.000440, N = 3SE +/- 0.001799, N = 3SE +/- 0.002431, N = 3SE +/- 0.015370, N = 30.2764720.5567410.5738783.111210MIN: 0.5MIN: 0.47MIN: 1.731. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

HeFFTe - Highly Efficient FFT for Exascale

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

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: Stock - Precision: double-long - X Y Z: 256HBv4HBv3HBv2HC306090120150SE +/- 1.16, N = 3SE +/- 0.14, N = 3SE +/- 0.55, N = 3SE +/- 0.03, N = 3123.4138.5750.0830.271. (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: 512HBv4HBv3HBv2HC70140210280350SE +/- 0.80, N = 3SE +/- 0.73, N = 3SE +/- 0.34, N = 3SE +/- 0.02, N = 3323.36123.2493.7957.761. (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: 256HBv4HBv3HBv2HC60120180240300SE +/- 2.84, N = 15SE +/- 0.81, N = 15SE +/- 1.27, N = 3SE +/- 0.19, N = 3258.72105.5092.3960.891. (CXX) g++ options: -O3 -pthread

HeFFTe - Highly Efficient FFT for Exascale

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

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: Stock - Precision: double - X Y Z: 256HBv4HBv3HBv2HC306090120150SE +/- 1.20, N = 3SE +/- 0.29, N = 11SE +/- 0.29, N = 3SE +/- 0.08, N = 3121.6138.4550.7130.171. (CXX) g++ options: -O3 -pthread

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUHBv4HBv3HBv2HC0.36230.72461.08691.44921.8115SE +/- 0.001551, N = 3SE +/- 0.003506, N = 3SE +/- 0.021847, N = 3SE +/- 0.002723, N = 30.5828061.4086201.6100201.244800MIN: 0.56MIN: 1.36MIN: 1.49MIN: 1.221. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUHBv4HBv3HBv2HC30060090012001500SE +/- 3.26, N = 3SE +/- 3.89, N = 3SE +/- 13.31, N = 3SE +/- 1.60, N = 3535.85860.981345.14707.35MIN: 521.12MIN: 814.31MIN: 1237.17MIN: 689.521. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: 512HBv4HBv3HBv2HC70140210280350SE +/- 1.60, N = 3SE +/- 0.40, N = 3SE +/- 0.25, N = 3SE +/- 0.05, N = 3311.80117.7394.5359.821. (CXX) g++ options: -O3 -pthread

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUHBv4HBv3HBv2HC2004006008001000SE +/- 1.40, N = 3SE +/- 4.61, N = 15SE +/- 9.52, N = 15SE +/- 4.72, N = 3401.86533.50896.81450.25MIN: 388.53MIN: 469.44MIN: 799.26MIN: 432.991. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: CPUHBv4HBv3HBv2HC30060090012001500SE +/- 1.90, N = 3SE +/- 6.66, N = 3SE +/- 13.52, N = 15SE +/- 1.51, N = 3533.49886.811367.73707.32MIN: 518.68MIN: 849.06MIN: 1212.94MIN: 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: CPUHBv4HBv3HBv2HC2004006008001000SE +/- 3.60, N = 8SE +/- 4.36, N = 3SE +/- 9.54, N = 15SE +/- 1.89, N = 3411.23529.97910.94442.47MIN: 384.83MIN: 469.93MIN: 799.88MIN: 429.931. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

ACES DGEMM

Sustained Floating-Point Rate

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateHBv4HBv3HBv2HC1224364860SE +/- 0.359007, N = 3SE +/- 0.132089, N = 3SE +/- 0.272351, N = 15SE +/- 0.199669, N = 1553.17569125.1048765.89990314.3408301. (CC) gcc options: -O3 -march=native -fopenmp

Remhos

Test: Sample Remap Example

OpenBenchmarking.orgSeconds, Fewer Is BetterRemhos 1.0Test: Sample Remap ExampleHBv4HBv3HBv2HC612182430SE +/- 0.14, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 315.3715.2614.9327.381. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -pthread -lmpi

Pennant

Test: sedovbig

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigHBv4HBv3HBv2HC612182430SE +/- 0.018282, N = 3SE +/- 0.027453, N = 3SE +/- 0.011742, N = 3SE +/- 0.026763, N = 33.5813916.2771075.91580525.0195601. (CXX) g++ options: -fopenmp -pthread -lmpi

Pennant

Test: leblancbig

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigHBv4HBv3HBv2HC3691215SE +/- 0.029043, N = 3SE +/- 0.006682, N = 3SE +/- 0.009233, N = 3SE +/- 0.017495, N = 32.1220743.6493173.46688510.6454801. (CXX) g++ options: -fopenmp -pthread -lmpi

7-Zip Compression

Test: Compression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingHBv4HBv3HBv2HC200K400K600K800K1000KSE +/- 7680.08, N = 15SE +/- 6724.92, N = 3SE +/- 2650.49, N = 3SE +/- 748.55, N = 310322675582904894562107321. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

7-Zip Compression

Test: Decompression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingHBv4HBv3HBv2HC160K320K480K640K800KSE +/- 8360.33, N = 15SE +/- 19127.89, N = 3SE +/- 2438.40, N = 3SE +/- 256.58, N = 37279953975053710441481931. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Timed Linux Kernel Compilation

Build: allmodconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: allmodconfigHBv4HBv3HBv2HC400800120016002000SE +/- 32.03, N = 9SE +/- 22.02, N = 3SE +/- 22.46, N = 3SE +/- 7.59, N = 31681.261889.461782.931950.63

HeFFTe - Highly Efficient FFT for Exascale

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

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: Stock - Precision: float-long - X Y Z: 256HBv4HBv3HBv2HC100200300400500SE +/- 17.46, N = 12SE +/- 7.34, N = 15SE +/- 2.37, N = 15SE +/- 0.90, N = 3467.72207.97211.42131.961. (CXX) g++ options: -O3 -pthread

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: BMW27 - Compute: CPU-OnlyHBv4HBv3HBv2HC1122334455SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.11, N = 3SE +/- 0.65, N = 159.9719.4919.4650.53

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Classroom - Compute: CPU-OnlyHBv4HBv3HBv2HC306090120150SE +/- 0.11, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.49, N = 325.2651.0850.86138.81

Blender

Blend File: Fishy Cat - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Fishy Cat - Compute: CPU-OnlyHBv4HBv3HBv2HC1632486480SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.48, N = 313.9625.4726.1972.57

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Barbershop - Compute: CPU-OnlyHBv4HBv3HBv2HC110220330440550SE +/- 0.12, N = 3SE +/- 0.45, N = 3SE +/- 0.01, N = 3SE +/- 2.13, N = 396.77189.30210.18524.86

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Pabellon Barcelona - Compute: CPU-OnlyHBv4HBv3HBv2HC4080120160200SE +/- 0.06, N = 3SE +/- 0.24, N = 3SE +/- 0.10, N = 3SE +/- 1.13, N = 333.4062.6464.14176.21

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-OnlyHBv4HBv3HBv2HC0.6931.3862.0792.7723.465SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 33.081.682.081.82

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-OnlyHBv4HBv3HBv2HC0.70431.40862.11292.81723.5215SE +/- 0.01, N = 3SE +/- 0.01, N = 15SE +/- 0.02, N = 9SE +/- 0.01, N = 33.131.692.031.84

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-OnlyHBv4HBv3HBv2HC0.29030.58060.87091.16121.4515SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 31.290.791.040.88

OSPRay

Benchmark: particle_volume/ao/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/ao/real_timeHBv4HBv3HBv2HC816243240SE +/- 0.04053, N = 3SE +/- 0.01755, N = 3SE +/- 0.00495, N = 3SE +/- 0.01225, N = 336.6121024.4586022.333608.97547

OSPRay

Benchmark: particle_volume/scivis/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/scivis/real_timeHBv4HBv3HBv2HC816243240SE +/- 0.03598, N = 3SE +/- 0.01956, N = 3SE +/- 0.01671, N = 3SE +/- 0.00763, N = 336.5671024.1736022.153308.97020

OSPRay

Benchmark: particle_volume/pathtracer/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/pathtracer/real_timeHBv4HBv3HBv2HC50100150200250SE +/- 0.07, N = 3SE +/- 0.23, N = 3SE +/- 3.07, N = 12SE +/- 8.14, N = 12208.34168.24157.1386.57

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_timeHBv4HBv3HBv2HC918273645SE +/- 0.03610, N = 3SE +/- 0.03837, N = 3SE +/- 0.13915, N = 12SE +/- 0.02906, N = 338.0764011.748508.673279.49421

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_timeHBv4HBv3HBv2HC918273645SE +/- 0.11164, N = 3SE +/- 0.01165, N = 3SE +/- 0.12026, N = 15SE +/- 0.03491, N = 337.0918011.184508.123568.98723

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_timeHBv4HBv3HBv2HC816243240SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 332.7914.6113.9210.05

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: 512HBv4HBv3HBv2HC130260390520650SE +/- 2.49, N = 3SE +/- 0.15, N = 3SE +/- 1.02, N = 3SE +/- 0.10, N = 3590.93233.80189.21110.201. (CXX) g++ options: -O3 -pthread

Timed Node.js Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 19.8.1Time To CompileHBv4HBv3HBv2HC70140210280350SE +/- 2.23, N = 12SE +/- 1.46, N = 3SE +/- 1.32, N = 3SE +/- 2.37, N = 3150.56185.57194.37330.61

Liquid-DSP

Threads: 1 - Buffer Length: 256 - Filter Length: 32

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 32HBv4HBv3HBv2HC8M16M24M32M40MSE +/- 20201.76, N = 3SE +/- 4096.07, N = 3SE +/- 2185.81, N = 3SE +/- 1333.33, N = 3353626673281733333211667317963331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

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

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 32HBv4HBv3HBv2HC200M400M600M800M1000MSE +/- 1950213.66, N = 3SE +/- 2475306.94, N = 3SE +/- 33333.33, N = 3SE +/- 3947135.39, N = 3111330000091733666710614333339644233331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 32 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 57HBv4HBv3HBv2HC300M600M900M1200M1500MSE +/- 14294460.47, N = 5SE +/- 550757.05, N = 3SE +/- 472581.56, N = 3SE +/- 5360840.75, N = 111390540000108600000011934000007212909091. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 128 - Buffer Length: 256 - Filter Length: 32

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 32HBv4HBv3HBv2HC900M1800M2700M3600M4500MSE +/- 3774034.09, N = 3SE +/- 5345506.94, N = 3SE +/- 3602930.91, N = 3SE +/- 8213606.60, N = 344263000003366733333392593333315126000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

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: 57HBv4HBv3HBv2HC1100M2200M3300M4400M5500MSE +/- 10401335.38, N = 3SE +/- 6947661.48, N = 3SE +/- 4421286.89, N = 3SE +/- 8373967.60, N = 351682333333516300000404593333315724000001. (CC) gcc options: -O3 -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: 32HBv4HBv3HBv2HC1300M2600M3900M5200M6500MSE +/- 9214903.39, N = 3SE +/- 8912600.32, N = 3SE +/- 44818002.34, N = 3SE +/- 2852094.75, N = 361222333333419533333402710000015661333331. (CC) gcc options: -O3 -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: 57HBv4HBv3HBv2HC1400M2800M4200M5600M7000MSE +/- 11394345.58, N = 3SE +/- 4247482.91, N = 3SE +/- 13588352.86, N = 3SE +/- 5446813.54, N = 367581666673563433333410670000016647333331. (CC) gcc options: -O3 -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: 512HBv4HBv3HBv2HC400M800M1200M1600M2000MSE +/- 4603018.33, N = 3SE +/- 3040334.41, N = 3SE +/- 3174614.59, N = 3SE +/- 6341443.93, N = 320582333337353700008256533335292133331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

PostgreSQL

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 500 - Mode: Read OnlyHBv4HBv3HBv2HC700K1400K2100K2800K3500KSE +/- 4762.10, N = 3SE +/- 4803.91, N = 3SE +/- 8486.11, N = 3SE +/- 3475.53, N = 331398462375005246624913548771. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

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 LatencyHBv4HBv3HBv2HC0.0830.1660.2490.3320.415SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 30.1590.2100.2030.3691. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -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 OnlyHBv4HBv3HBv2HC700K1400K2100K2800K3500KSE +/- 20304.79, N = 3SE +/- 11149.78, N = 3SE +/- 4115.38, N = 3SE +/- 4936.18, N = 331230422407602243965011618001. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -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 LatencyHBv4HBv3HBv2HC0.15480.30960.46440.61920.774SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.003, N = 30.2560.3320.3280.6881. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PETSc

Test: Streams

OpenBenchmarking.orgMB/s, More Is BetterPETSc 3.19Test: StreamsHBv4HBv3HBv2HC130K260K390K520K650KSE +/- 46271.80, N = 9SE +/- 2674.31, N = 7SE +/- 12025.83, N = 6SE +/- 256.75, N = 3598417.70284001.92197895.47151286.251. (CXX) g++ options: -O3 -std=gnu++17 -fPIC -include -m64

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: 60HBv4HBv3HBv2HC20406080100SE +/- 0.26, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 389.3839.6137.0426.001. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi

Phoronix Test Suite v10.8.5