Microsoft Azure EPYC 7003 HBv3 Benchmarks

Azure HBv3 vs. Azure HBv2 benchmarks.

HTML result view exported from: https://openbenchmarking.org/result/2104116-PTS-AZURE71063&sro.

Microsoft Azure EPYC 7003 HBv3 BenchmarksProcessorMotherboardMemoryDiskGraphicsOSKernelCompilerFile-SystemScreen ResolutionSystem LayerAzure HBv3Azure HBv22 x AMD EPYC 7V13 64-Core (120 Cores)Microsoft Virtual Machine (Hyper-V UEFI v4.1 BIOS)442GB2 x 960GB Microsoft NVMe Direct Disk + 32GB Virtual Disk + 515GB Virtual Diskhyperv_fbCentOS Linux 84.18.0-147.8.1.el8_1.x86_64 (x86_64)GCC 8.3.1 20190507nfs1152x864microsoft2 x AMD EPYC 7V12 64-Core (120 Cores)Microsoft Virtual Machine (Hyper-V UEFI v4.0 BIOS)450GB960GB Microsoft NVMe Direct Disk + 32GB Virtual Disk + 515GB 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- Azure HBv3: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline STIBP: disabled RSB filling + tsx_async_abort: Not affected - Azure HBv2: itlb_multihit: Not affected + 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 Full generic retpoline STIBP: disabled RSB filling + tsx_async_abort: Not affected

Microsoft Azure EPYC 7003 HBv3 Benchmarksquantlib: hpcg: npb: LU.Cminife: Smallcloverleaf: Lagrangian-Eulerian Hydrodynamicsrodinia: OpenMP LavaMDrodinia: OpenMP HotSpot3Drodinia: OpenMP Leukocyterodinia: OpenMP CFD Solverrodinia: OpenMP Streamclusternamd: ATPase Simulation - 327,506 Atomspennant: sedovbigpennant: leblancbighmmer: Pfam Database Searchincompact3d: X3D-benchmarking input.i3dmafft: Multiple Sequence Alignment - LSU RNAlulesh: gmpbench: Total Timecompress-zstd: 8 - Compression Speedcompress-zstd: 19 - Compression Speedcompress-zstd: 19 - Decompression Speedcompress-zstd: 8, Long Mode - Compression Speedcompress-zstd: 8, Long Mode - Decompression Speedcompress-zstd: 19, Long Mode - Compression Speedcompress-zstd: 19, Long Mode - Decompression Speedbotan: KASUMIbotan: KASUMI - Decryptbotan: AES-256botan: AES-256 - Decryptbotan: Twofishbotan: Twofish - Decryptbotan: Blowfishbotan: Blowfish - Decryptbotan: CAST-256botan: CAST-256 - Decryptbotan: ChaCha20Poly1305botan: ChaCha20Poly1305 - Decryptsvt-av1: Enc Mode 0 - 1080psvt-av1: Enc Mode 4 - 1080psvt-av1: Enc Mode 8 - 1080psvt-hevc: 1 - Bosphorus 1080psvt-hevc: 7 - Bosphorus 1080psvt-hevc: 10 - Bosphorus 1080psvt-vp9: VMAF Optimized - Bosphorus 1080psvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080psvt-vp9: Visual Quality Optimized - Bosphorus 1080pbuild-linux-kernel: Time To Compilebuild-llvm: Time To Compilebuild-nodejs: Time To Compileonednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUfinancebench: Repo OpenMPfinancebench: Bonds OpenMPgromacs: Water Benchmarktensorflow-lite: SqueezeNetmnn: SqueezeNetV1.0mnn: resnet-v2-50mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3ncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - shufflenet-v2ncnn: CPU - efficientnet-b0ncnn: CPU - vgg16ncnn: CPU - alexnetncnn: CPU - resnet50tnn: CPU - SqueezeNet v1.1plaidml: No - Inference - VGG16 - CPUplaidml: No - Inference - VGG19 - CPUplaidml: No - Inference - ResNet 50 - CPUkripke: Azure HBv3Azure HBv22299.339.062056682.8213785.316.6637.80382.48949.3538.4607.3790.275665.8334193.337201175.239287.59950814.32641636.6034893.43184.278.23717.5771.94256.836.33727.587.48084.0595412.1315407.477346.319345.776424.738425.158133.691133.665667.765658.3700.16112.27594.02845.39378.01548.33357.06376.91337.7142.008163.760111.3270.8813073.212040.3838550.5752389.504451.581820.4066860.455682875.166530.898962.336561.7730.255501843.103540.1940.44522359196.546875104884.2942719.04166320.48.22429.0864.7823.95034.71027.8723.2413.7121.0447.676.8930.03272.61438.3934.536.27823418651725.237.268653829.3413165.0923.7839.198107.97657.04013.04212.9120.300566.0264493.486503207.867318.90500916.06434803.5394155.52653.169.52631.0588.03037.533.42674.273.17571.1013934.4013938.444280.902283.257348.425349.147113.600113.724615.795610.8610.1249.51278.10436.12166.90379.91140.30163.51140.5944.922174.743118.9691.124849.683210.4410120.58198112.10511.595571.0319420.7321301314.00778.3051287.03791.4600.3503471294.53796.8160.52473775154.257813133719.3281258.45874885.414.13652.53312.5278.03055.35652.5637.2021.3932.42133.7810.8064.80323.61525.5723.125.6043855550OpenBenchmarking.org

QuantLib

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.21Azure HBv2Azure HBv35001000150020002500SE +/- 0.77, N = 3SE +/- 4.80, N = 31725.22299.31. (CXX) g++ options: -O3 -march=native -O2 -rdynamic -lboost_timer -lboost_system -lboost_chrono

High Performance Conjugate Gradient

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1Azure HBv2Azure HBv3918273645SE +/- 0.06, N = 3SE +/- 0.06, N = 337.2739.061. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -fexceptions -pthread -lmpi_cxx -lmpi

NAS Parallel Benchmarks

Test / Class: LU.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CAzure HBv2Azure HBv312K24K36K48K60KSE +/- 21.24, N = 3SE +/- 428.57, N = 1453829.3456682.821. (F9X) gfortran options: -O3 -march=native -fexceptions -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

miniFE

Problem Size: Small

OpenBenchmarking.orgCG Mflops, More Is BetterminiFE 2.2Problem Size: SmallAzure HBv2Azure HBv33K6K9K12K15KSE +/- 608.74, N = 12SE +/- 387.39, N = 1513165.0913785.301. (CXX) g++ options: -O3 -fopenmp -fexceptions -pthread -lmpi_cxx -lmpi

CloverLeaf

Lagrangian-Eulerian Hydrodynamics

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeafLagrangian-Eulerian HydrodynamicsAzure HBv2Azure HBv3612182430SE +/- 0.45, N = 12SE +/- 0.83, N = 1523.7816.661. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

Rodinia

Test: OpenMP LavaMD

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDAzure HBv2Azure HBv3918273645SE +/- 0.20, N = 3SE +/- 0.23, N = 339.2037.801. (CXX) g++ options: -O2 -lOpenCL

Rodinia

Test: OpenMP HotSpot3D

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3DAzure HBv2Azure HBv320406080100SE +/- 0.89, N = 3SE +/- 1.18, N = 15107.9882.491. (CXX) g++ options: -O2 -lOpenCL

Rodinia

Test: OpenMP Leukocyte

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LeukocyteAzure HBv2Azure HBv31326395265SE +/- 0.57, N = 3SE +/- 0.43, N = 857.0449.351. (CXX) g++ options: -O2 -lOpenCL

Rodinia

Test: OpenMP CFD Solver

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD SolverAzure HBv2Azure HBv33691215SE +/- 0.748, N = 12SE +/- 0.801, N = 1213.0428.4601. (CXX) g++ options: -O2 -lOpenCL

Rodinia

Test: OpenMP Streamcluster

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP StreamclusterAzure HBv2Azure HBv33691215SE +/- 0.453, N = 15SE +/- 0.196, N = 1512.9127.3791. (CXX) g++ options: -O2 -lOpenCL

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsAzure HBv2Azure HBv30.06760.13520.20280.27040.338SE +/- 0.00059, N = 3SE +/- 0.00027, N = 30.300560.27566

Pennant

Test: sedovbig

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigAzure HBv2Azure HBv3246810SE +/- 0.012548, N = 3SE +/- 0.003905, N = 36.0264495.8334191. (CXX) g++ options: -fopenmp -fexceptions -pthread -lmpi_cxx -lmpi

Pennant

Test: leblancbig

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigAzure HBv2Azure HBv30.78451.5692.35353.1383.9225SE +/- 0.009939, N = 3SE +/- 0.017738, N = 33.4865033.3372011. (CXX) g++ options: -fopenmp -fexceptions -pthread -lmpi_cxx -lmpi

Timed HMMer Search

Pfam Database Search

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.1Pfam Database SearchAzure HBv2Azure HBv350100150200250SE +/- 1.08, N = 3SE +/- 1.00, N = 3207.87175.241. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm

Xcompact3d Incompact3d

Input: X3D-benchmarking input.i3d

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3dAzure HBv2Azure HBv370140210280350SE +/- 0.07, N = 3SE +/- 0.17, N = 3318.91287.601. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -fexceptions -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

Timed MAFFT Alignment

Multiple Sequence Alignment - LSU RNA

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNAAzure HBv2Azure HBv348121620SE +/- 0.06, N = 3SE +/- 0.10, N = 1516.0614.331. (CC) gcc options: -std=c99 -O3 -lm -lpthread

LULESH

OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.3Azure HBv2Azure HBv39K18K27K36K45KSE +/- 44.77, N = 3SE +/- 476.10, N = 334803.5441636.601. (CXX) g++ options: -O3 -fopenmp -lm -fexceptions -pthread -lmpi_cxx -lmpi

GNU GMP GMPbench

Total Time

OpenBenchmarking.orgGMPbench Score, More Is BetterGNU GMP GMPbench 6.2.1Total TimeAzure HBv2Azure HBv3100020003000400050004155.54893.41. (CC) gcc options: -O3 -fomit-frame-pointer -lm

Zstd Compression

Compression Level: 8 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8 - Compression SpeedAzure HBv2Azure HBv37001400210028003500SE +/- 33.03, N = 15SE +/- 45.10, N = 32653.13184.21. (CC) gcc options: -O3 -pthread -lz -llzma

Zstd Compression

Compression Level: 19 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19 - Compression SpeedAzure HBv2Azure HBv320406080100SE +/- 1.18, N = 15SE +/- 0.71, N = 1569.578.21. (CC) gcc options: -O3 -pthread -lz -llzma

Zstd Compression

Compression Level: 19 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19 - Decompression SpeedAzure HBv2Azure HBv38001600240032004000SE +/- 1.17, N = 15SE +/- 6.14, N = 152631.03717.51. (CC) gcc options: -O3 -pthread -lz -llzma

Zstd Compression

Compression Level: 8, Long Mode - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8, Long Mode - Compression SpeedAzure HBv2Azure HBv3170340510680850SE +/- 0.81, N = 3SE +/- 6.99, N = 7588.0771.91. (CC) gcc options: -O3 -pthread -lz -llzma

Zstd Compression

Compression Level: 8, Long Mode - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8, Long Mode - Decompression SpeedAzure HBv2Azure HBv39001800270036004500SE +/- 4.57, N = 3SE +/- 4.89, N = 73037.54256.81. (CC) gcc options: -O3 -pthread -lz -llzma

Zstd Compression

Compression Level: 19, Long Mode - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19, Long Mode - Compression SpeedAzure HBv2Azure HBv3816243240SE +/- 0.38, N = 15SE +/- 0.34, N = 1533.436.31. (CC) gcc options: -O3 -pthread -lz -llzma

Zstd Compression

Compression Level: 19, Long Mode - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19, Long Mode - Decompression SpeedAzure HBv2Azure HBv38001600240032004000SE +/- 2.70, N = 15SE +/- 12.70, N = 152674.23727.51. (CC) gcc options: -O3 -pthread -lz -llzma

Botan

Test: KASUMI

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMIAzure HBv2Azure HBv320406080100SE +/- 0.07, N = 3SE +/- 0.04, N = 373.1887.481. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Botan

Test: KASUMI - Decrypt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMI - DecryptAzure HBv2Azure HBv320406080100SE +/- 0.04, N = 3SE +/- 0.02, N = 371.1084.061. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Botan

Test: AES-256

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-256Azure HBv2Azure HBv312002400360048006000SE +/- 2.68, N = 3SE +/- 3.73, N = 33934.405412.131. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Botan

Test: AES-256 - Decrypt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-256 - DecryptAzure HBv2Azure HBv312002400360048006000SE +/- 3.26, N = 3SE +/- 7.85, N = 33938.445407.481. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Botan

Test: Twofish

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: TwofishAzure HBv2Azure HBv380160240320400SE +/- 0.15, N = 3SE +/- 1.10, N = 3280.90346.321. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Botan

Test: Twofish - Decrypt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofish - DecryptAzure HBv2Azure HBv380160240320400SE +/- 0.22, N = 3SE +/- 0.77, N = 3283.26345.781. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Botan

Test: Blowfish

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: BlowfishAzure HBv2Azure HBv390180270360450SE +/- 0.42, N = 3SE +/- 0.47, N = 3348.43424.741. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Botan

Test: Blowfish - Decrypt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfish - DecryptAzure HBv2Azure HBv390180270360450SE +/- 0.56, N = 3SE +/- 0.42, N = 3349.15425.161. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Botan

Test: CAST-256

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256Azure HBv2Azure HBv3306090120150SE +/- 0.07, N = 3SE +/- 0.03, N = 3113.60133.691. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Botan

Test: CAST-256 - Decrypt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256 - DecryptAzure HBv2Azure HBv3306090120150SE +/- 0.01, N = 3SE +/- 0.02, N = 3113.72133.671. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Botan

Test: ChaCha20Poly1305

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305Azure HBv2Azure HBv3140280420560700SE +/- 0.90, N = 3SE +/- 0.27, N = 3615.80667.771. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Botan

Test: ChaCha20Poly1305 - Decrypt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305 - DecryptAzure HBv2Azure HBv3140280420560700SE +/- 0.78, N = 3SE +/- 0.06, N = 3610.86658.371. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

SVT-AV1

Encoder Mode: Enc Mode 0 - Input: 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 0 - Input: 1080pAzure HBv2Azure HBv30.03620.07240.10860.14480.181SE +/- 0.001, N = 3SE +/- 0.000, N = 30.1240.1611. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

SVT-AV1

Encoder Mode: Enc Mode 4 - Input: 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pAzure HBv2Azure HBv33691215SE +/- 0.218, N = 15SE +/- 0.031, N = 39.51212.2751. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

SVT-AV1

Encoder Mode: Enc Mode 8 - Input: 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pAzure HBv2Azure HBv320406080100SE +/- 0.65, N = 3SE +/- 0.34, N = 378.1094.031. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

SVT-HEVC

Tuning: 1 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pAzure HBv2Azure HBv31020304050SE +/- 0.13, N = 3SE +/- 0.60, N = 336.1245.391. (CC) gcc options: -fPIE -fPIC -O2 -O3 -pie -rdynamic -lpthread -lrt

SVT-HEVC

Tuning: 7 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pAzure HBv2Azure HBv380160240320400SE +/- 6.53, N = 12SE +/- 4.22, N = 3166.90378.011. (CC) gcc options: -fPIE -fPIC -O2 -O3 -pie -rdynamic -lpthread -lrt

SVT-HEVC

Tuning: 10 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pAzure HBv2Azure HBv3120240360480600SE +/- 21.86, N = 15SE +/- 7.76, N = 3379.91548.331. (CC) gcc options: -fPIE -fPIC -O2 -O3 -pie -rdynamic -lpthread -lrt

SVT-VP9

Tuning: VMAF Optimized - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pAzure HBv2Azure HBv380160240320400SE +/- 5.31, N = 15SE +/- 23.14, N = 12140.30357.061. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -O2 -pie -rdynamic -lpthread -lrt -lm

SVT-VP9

Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pAzure HBv2Azure HBv380160240320400SE +/- 9.44, N = 12SE +/- 5.29, N = 15163.51376.911. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -O2 -pie -rdynamic -lpthread -lrt -lm

SVT-VP9

Tuning: Visual Quality Optimized - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pAzure HBv2Azure HBv370140210280350SE +/- 0.20, N = 3SE +/- 4.36, N = 3140.59337.711. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -O2 -pie -rdynamic -lpthread -lrt -lm

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.10.20Time To CompileAzure HBv2Azure HBv31020304050SE +/- 0.58, N = 13SE +/- 0.58, N = 1544.9242.01

Timed LLVM Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 10.0Time To CompileAzure HBv2Azure HBv34080120160200SE +/- 1.99, N = 3SE +/- 1.89, N = 3174.74163.76

Timed Node.js Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 15.11Time To CompileAzure HBv2Azure HBv3306090120150SE +/- 0.83, N = 3SE +/- 1.09, N = 3118.97111.33

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUAzure HBv2Azure HBv30.25310.50620.75931.01241.2655SE +/- 0.011740, N = 15SE +/- 0.012358, N = 31.1248400.881307MIN: 1.01MIN: 0.761. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUAzure HBv2Azure HBv33691215SE +/- 0.28898, N = 15SE +/- 0.02162, N = 39.683213.21204MIN: 5.56MIN: 2.581. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

oneDNN

Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUAzure HBv2Azure HBv30.09920.19840.29760.39680.496SE +/- 0.003995, N = 7SE +/- 0.009558, N = 120.4410120.383855MIN: 0.4MIN: 0.321. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUAzure HBv2Azure HBv30.13090.26180.39270.52360.6545SE +/- 0.000573, N = 3SE +/- 0.005232, N = 30.5819810.575238MIN: 0.53MIN: 0.51. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUAzure HBv2Azure HBv33691215SE +/- 0.11811, N = 6SE +/- 0.09389, N = 312.105109.50445MIN: 5.8MIN: 4.191. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUAzure HBv2Azure HBv30.3590.7181.0771.4361.795SE +/- 0.01470, N = 3SE +/- 0.00509, N = 31.595571.58182MIN: 1.5MIN: 1.491. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUAzure HBv2Azure HBv30.23220.46440.69660.92881.161SE +/- 0.030825, N = 15SE +/- 0.004961, N = 31.0319420.406686MIN: 0.83MIN: 0.351. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUAzure HBv2Azure HBv30.16470.32940.49410.65880.8235SE +/- 0.002363, N = 3SE +/- 0.002442, N = 30.7321300.455682MIN: 0.65MIN: 0.381. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUAzure HBv2Azure HBv330060090012001500SE +/- 16.54, N = 15SE +/- 25.25, N = 121314.00875.17MIN: 1140.59MIN: 727.381. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUAzure HBv2Azure HBv32004006008001000SE +/- 8.13, N = 3SE +/- 8.62, N = 15778.31530.90MIN: 738.78MIN: 458.961. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

oneDNN

Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUAzure HBv2Azure HBv330060090012001500SE +/- 13.52, N = 15SE +/- 102.39, N = 141287.03962.34MIN: 1149.25MIN: 722.131. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUAzure HBv2Azure HBv32004006008001000SE +/- 5.73, N = 15SE +/- 8.80, N = 15791.46561.77MIN: 718.74MIN: 471.831. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUAzure HBv2Azure HBv30.07880.15760.23640.31520.394SE +/- 0.006544, N = 12SE +/- 0.000278, N = 30.3503470.255501MIN: 0.3MIN: 0.221. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUAzure HBv2Azure HBv330060090012001500SE +/- 11.10, N = 15SE +/- 14.29, N = 151294.53843.10MIN: 1179.19MIN: 711.661. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUAzure HBv2Azure HBv32004006008001000SE +/- 6.35, N = 15SE +/- 8.06, N = 15796.82540.19MIN: 726.18MIN: 462.71. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUAzure HBv2Azure HBv30.11810.23620.35430.47240.5905SE +/- 0.004967, N = 3SE +/- 0.004912, N = 40.5247370.445223MIN: 0.48MIN: 0.391. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

FinanceBench

Benchmark: Repo OpenMP

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Repo OpenMPAzure HBv2Azure HBv316K32K48K64K80KSE +/- 166.77, N = 3SE +/- 228.72, N = 375154.2659196.551. (CXX) g++ options: -O3 -march=native -fopenmp

FinanceBench

Benchmark: Bonds OpenMP

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Bonds OpenMPAzure HBv2Azure HBv330K60K90K120K150KSE +/- 476.22, N = 3SE +/- 454.05, N = 3133719.33104884.291. (CXX) g++ options: -O3 -march=native -fopenmp

GROMACS

Water Benchmark

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.3Water BenchmarkAzure HBv2Azure HBv33691215SE +/- 0.009, N = 3SE +/- 0.009, N = 38.4589.0411. (CXX) g++ options: -O2 -pthread -lrt -lpthread -lm

TensorFlow Lite

Model: SqueezeNet

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetAzure HBv2Azure HBv316K32K48K64K80KSE +/- 1151.94, N = 15SE +/- 2854.14, N = 1574885.466320.4

Mobile Neural Network

Model: SqueezeNetV1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: SqueezeNetV1.0Azure HBv2Azure HBv348121620SE +/- 0.657, N = 12SE +/- 0.113, N = 1514.1368.224MIN: 10.98 / MAX: 78.48MIN: 5.66 / MAX: 54.171. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -O2 -rdynamic -pthread -ldl

Mobile Neural Network

Model: resnet-v2-50

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: resnet-v2-50Azure HBv2Azure HBv31224364860SE +/- 1.18, N = 12SE +/- 0.25, N = 1552.5329.09MIN: 41.27 / MAX: 326.88MIN: 25.79 / MAX: 252.291. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -O2 -rdynamic -pthread -ldl

Mobile Neural Network

Model: MobileNetV2_224

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: MobileNetV2_224Azure HBv2Azure HBv33691215SE +/- 0.587, N = 12SE +/- 0.085, N = 1512.5274.782MIN: 7.24 / MAX: 67.34MIN: 3.71 / MAX: 61.381. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -O2 -rdynamic -pthread -ldl

Mobile Neural Network

Model: mobilenet-v1-1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: mobilenet-v1-1.0Azure HBv2Azure HBv3246810SE +/- 0.500, N = 12SE +/- 0.151, N = 158.0303.950MIN: 4.5 / MAX: 15.23MIN: 2.55 / MAX: 5.411. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -O2 -rdynamic -pthread -ldl

Mobile Neural Network

Model: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: inception-v3Azure HBv2Azure HBv31224364860SE +/- 0.95, N = 12SE +/- 0.24, N = 1555.3634.71MIN: 47.56 / MAX: 509.74MIN: 31.09 / MAX: 427.771. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -O2 -rdynamic -pthread -ldl

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mobilenetAzure HBv2Azure HBv31224364860SE +/- 2.25, N = 12SE +/- 1.74, N = 952.5627.87MIN: 40.97 / MAX: 511.3MIN: 21.41 / MAX: 63.521. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v2-v2 - Model: mobilenet-v2Azure HBv2Azure HBv3918273645SE +/- 2.17, N = 12SE +/- 3.10, N = 937.2023.24MIN: 13.35 / MAX: 4343.96MIN: 10.66 / MAX: 3825.911. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: shufflenet-v2Azure HBv2Azure HBv3510152025SE +/- 1.32, N = 12SE +/- 0.83, N = 921.3913.71MIN: 14.34 / MAX: 1188.39MIN: 9.5 / MAX: 286.311. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: efficientnet-b0Azure HBv2Azure HBv3816243240SE +/- 1.94, N = 12SE +/- 3.62, N = 932.4221.04MIN: 20.32 / MAX: 786.11MIN: 12.75 / MAX: 4928.421. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: vgg16Azure HBv2Azure HBv3306090120150SE +/- 6.58, N = 12SE +/- 2.09, N = 9133.7847.67MIN: 82.15 / MAX: 2364.48MIN: 40.11 / MAX: 1444.131. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: alexnetAzure HBv2Azure HBv33691215SE +/- 0.21, N = 12SE +/- 0.57, N = 910.806.89MIN: 9.2 / MAX: 35.44MIN: 5.85 / MAX: 759.551. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet50Azure HBv2Azure HBv31428425670SE +/- 2.16, N = 12SE +/- 0.90, N = 964.8030.03MIN: 44.36 / MAX: 2196.77MIN: 25.77 / MAX: 962.031. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

TNN

Target: CPU - Model: SqueezeNet v1.1

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.1Azure HBv2Azure HBv370140210280350SE +/- 0.19, N = 3SE +/- 0.15, N = 3323.62272.61MIN: 322.04 / MAX: 326.05MIN: 272.1 / MAX: 273.51. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O2 -rdynamic -ldl

PlaidML

FP16: No - Mode: Inference - Network: VGG16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUAzure HBv2Azure HBv3918273645SE +/- 0.21, N = 3SE +/- 0.39, N = 325.5738.39

PlaidML

FP16: No - Mode: Inference - Network: VGG19 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPUAzure HBv2Azure HBv3816243240SE +/- 0.31, N = 15SE +/- 0.42, N = 423.1234.53

PlaidML

FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUAzure HBv2Azure HBv3246810SE +/- 0.03, N = 3SE +/- 0.16, N = 95.606.27

Kripke

OpenBenchmarking.orgThroughput FoM, More Is BetterKripke 1.2.4Azure HBv2Azure HBv320M40M60M80M100MSE +/- 812916.11, N = 15SE +/- 1839362.01, N = 1543855550823418651. (CXX) g++ options: -O2 -fopenmp

Phoronix Test Suite v10.8.4