Tests for a future article. 2 x AMD EPYC 9684X 96-Core testing with a AMD Titanite_4G (RTI1007B BIOS) and ASPEED on Ubuntu 23.10 via the Phoronix Test Suite.
a Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10113eJava Notes: OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)Python Notes: Python 3.11.6Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
b Processor: 2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1007B BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 23.10, Kernel: 6.5.0-13-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 800x600
eps OpenBenchmarking.org Phoronix Test Suite 2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads) AMD Titanite_4G (RTI1007B BIOS) AMD Device 14a4 1520GB 3201GB Micron_7450_MTFDKCB3T2TFS ASPEED Broadcom NetXtreme BCM5720 PCIe Ubuntu 23.10 6.5.0-13-generic (x86_64) GCC 13.2.0 ext4 800x600 Processor Motherboard Chipset Memory Disk Graphics Network OS Kernel Compiler File-System Screen Resolution Eps Performance System Logs - Transparent Huge Pages: madvise - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10113e - OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10) - Python 3.11.6 - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
a vs. b Comparison Phoronix Test Suite Baseline +7.7% +7.7% +15.4% +15.4% +23.1% +23.1% +30.8% +30.8% 7.7% 5.3% 4.3% 4.3% 2.7% 2.1% 13.1% 2.3% 3.1% 9.6% 2% 2.4% 6.7% 7.4% 2.5% 2.7% 6.6% 10.5% 9.6% 4.1% 9.7% 2.7% 11.7% 3.4% 30.8% 11.9% 4.6% CPU - 256 - ResNet-152 CPU - 1 - Efficientnet_v2_l Preset 13 - Bosphorus 4K Preset 12 - Bosphorus 4K Q.1.C.E.5 3.7% CPU - 256 - ResNet-50 3.3% CPU - 1 - ResNet-152 BLAS 50 - Q21 50 - Q19 15.6% 50 - Q18 50 - Q16 5.3% 50 - Q15 50 - Q13 2.2% 50 - Q12 50 - Q11 50 - Q07 4% 50 - Q05 4.6% 50 - Q04 3.9% 50 - Q03 13.4% 50 - Q01 7.2% 10 - Q19 10 - Q18 10 - Q15 10 - Q14 10 - Q13 7.6% 10 - Q11 3.4% 10 - Q10 10 - Q09 2.8% 10 - Q08 10 - Q06 10 - Q05 14.7% 10 - Q04 10 - Q03 2.3% 10 - Q01 1 - Q22 5.9% 1 - Q19 8.5% 1 - Q18 1 - Q17 1 - Q16 9.9% 1 - Q15 3.4% 1 - Q14 7.1% 1 - Q13 9.6% 1 - Q12 4.2% 1 - Q11 1 - Q09 3.3% 1 - Q07 1 - Q06 1 - Q05 1 - Q04 1 - Q01 2.9% PyTorch PyTorch SVT-AV1 SVT-AV1 WebP2 Image Encode PyTorch PyTorch LeelaChessZero Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H Apache Spark TPC-H a b
eps lczero: BLAS lczero: Eigen pytorch: CPU - 256 - Efficientnet_v2_l pytorch: CPU - 16 - Efficientnet_v2_l pytorch: CPU - 32 - Efficientnet_v2_l spark-tpch: 50 - Q22 spark-tpch: 50 - Q21 spark-tpch: 50 - Q20 spark-tpch: 50 - Q19 spark-tpch: 50 - Q18 spark-tpch: 50 - Q17 spark-tpch: 50 - Q16 spark-tpch: 50 - Q15 spark-tpch: 50 - Q14 spark-tpch: 50 - Q13 spark-tpch: 50 - Q12 spark-tpch: 50 - Q11 spark-tpch: 50 - Q10 spark-tpch: 50 - Q09 spark-tpch: 50 - Q08 spark-tpch: 50 - Q07 spark-tpch: 50 - Q06 spark-tpch: 50 - Q05 spark-tpch: 50 - Q04 spark-tpch: 50 - Q03 spark-tpch: 50 - Q02 spark-tpch: 50 - Q01 spark-tpch: 50 - Geometric Mean Of All Queries spark-tpch: 10 - Q22 spark-tpch: 10 - Q21 spark-tpch: 10 - Q20 spark-tpch: 10 - Q19 spark-tpch: 10 - Q18 spark-tpch: 10 - Q17 spark-tpch: 10 - Q16 spark-tpch: 10 - Q15 spark-tpch: 10 - Q14 spark-tpch: 10 - Q13 spark-tpch: 10 - Q12 spark-tpch: 10 - Q11 spark-tpch: 10 - Q10 spark-tpch: 10 - Q09 spark-tpch: 10 - Q08 spark-tpch: 10 - Q07 spark-tpch: 10 - Q06 spark-tpch: 10 - Q05 spark-tpch: 10 - Q04 spark-tpch: 10 - Q03 spark-tpch: 10 - Q02 spark-tpch: 10 - Q01 spark-tpch: 10 - Geometric Mean Of All Queries pytorch: CPU - 32 - ResNet-152 pytorch: CPU - 16 - ResNet-152 pytorch: CPU - 256 - ResNet-152 webp2: Quality 100, Lossless Compression pytorch: CPU - 1 - ResNet-50 openssl: SHA512 openssl: SHA256 pytorch: CPU - 1 - Efficientnet_v2_l pytorch: CPU - 1 - ResNet-152 pytorch: CPU - 256 - ResNet-50 pytorch: CPU - 32 - ResNet-50 pytorch: CPU - 16 - ResNet-50 deepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Stream spark-tpch: 1 - Q22 spark-tpch: 1 - Q21 spark-tpch: 1 - Q20 spark-tpch: 1 - Q19 spark-tpch: 1 - Q18 spark-tpch: 1 - Q17 spark-tpch: 1 - Q16 spark-tpch: 1 - Q15 spark-tpch: 1 - Q14 spark-tpch: 1 - Q13 spark-tpch: 1 - Q12 spark-tpch: 1 - Q11 spark-tpch: 1 - Q10 spark-tpch: 1 - Q09 spark-tpch: 1 - Q08 spark-tpch: 1 - Q07 spark-tpch: 1 - Q06 spark-tpch: 1 - Q05 spark-tpch: 1 - Q04 spark-tpch: 1 - Q03 spark-tpch: 1 - Q02 spark-tpch: 1 - Q01 spark-tpch: 1 - Geometric Mean Of All Queries openssl: RSA4096 openssl: RSA4096 webp2: Quality 95, Compression Effort 7 deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream deepsparse: ResNet-50, Baseline - Asynchronous Multi-Stream deepsparse: ResNet-50, Baseline - Asynchronous Multi-Stream deepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Stream deepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Stream deepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Stream deepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: ResNet-50, Baseline - Synchronous Single-Stream deepsparse: ResNet-50, Baseline - Synchronous Single-Stream svt-av1: Preset 13 - Bosphorus 4K xmrig: GhostRider - 1M webp2: Quality 75, Compression Effort 7 java-scimark2: Composite svt-av1: Preset 4 - Bosphorus 4K svt-av1: Preset 4 - Bosphorus 1080p svt-av1: Preset 8 - Bosphorus 4K xmrig: CryptoNight-Heavy - 1M xmrig: CryptoNight-Femto UPX2 - 1M xmrig: Monero - 1M xmrig: KawPow - 1M xmrig: Wownero - 1M svt-av1: Preset 12 - Bosphorus 4K svt-av1: Preset 8 - Bosphorus 1080p webp2: Quality 100, Compression Effort 5 webp2: Default svt-av1: Preset 12 - Bosphorus 1080p svt-av1: Preset 13 - Bosphorus 1080p java-scimark2: Jacobi Successive Over-Relaxation java-scimark2: Dense LU Matrix Factorization java-scimark2: Sparse Matrix Multiply java-scimark2: Fast Fourier Transform java-scimark2: Monte Carlo a b 853 704 2.32 2.32 2.32 10.69325638 87.89528910 20.79876137 10.45287259 34.51305643 24.30927912 14.21570397 9.77733866 12.70455011 12.75901413 19.40537771 13.58028253 24.36003748 36.66458511 26.73535283 24.85711161 5.90309207 29.83627891 20.99598312 26.18788719 14.25487200 12.00795619 19.58745807 6.05411895 32.90715027 11.43560823 6.20677837 18.46971194 12.77044550 6.87131294 5.84138076 7.07622369 7.37728373 9.94400438 8.00292349 15.17488098 21.90670204 15.51824761 14.65200933 2.05104745 16.44365629 12.34571203 13.97308763 7.43104283 7.58889151 10.72150208 8.90 8.93 8.96 0.11 23.57 91630925473 281869895760 6.40 10.16 21.29 21.00 21.16 31.2154 32.0229 607.5664 156.4159 1.00769047 9.64531231 3.05739617 0.79092395 5.62853845 2.95993924 1.38147259 2.50185966 2.06485331 1.58815936 2.17542648 1.27338135 3.81359665 5.70969407 2.65584644 4.01044806 0.46822915 4.13122161 3.92525745 3.86442184 2.06179071 4.32006081 2.44964916 3244390.3 98622.0 0.45 5.2377 190.7999 715.0362 132.6580 36.7508 2608.0090 719.2814 132.0485 17.3023 5540.6268 20.6157 48.4917 14.6422 68.2655 20.6345 48.4476 383.2004 248.5770 84.2519 1136.7105 15.3183 65.2070 4.4503 224.5798 122.0312 784.5178 120.2065 796.0713 54.5064 1758.5931 1.2413 804.1784 5.5955 17108.4634 54.4097 1761.4041 4.7188 211.7448 4.7126 212.0955 4.8022 208.1200 4.7637 209.7998 176.670 31859.7 0.83 3984.62 8.248 21.424 86.434 123041.6 123199.0 123352.8 123558.6 131141.9 178.910 165.104 6.51 9.48 571.875 635.810 1703.42 13358.53 2809.01 420.74 1631.42 871 715 2.28 2.34 2.32 10.87410069 77.70675659 21.05384445 12.08592796 33.74198151 24.55788994 14.97535801 9.48287773 12.56767082 13.04496479 17.70001793 13.31200027 24.68585587 36.66526794 26.62909508 25.86055183 5.88382483 31.20059776 21.8167572 29.68590546 14.53046799 12.86835003 19.56475658 6.04430914 32.70154953 11.53966141 6.0604167 17.31370163 13.01374149 6.95270681 5.43870592 6.90602303 7.94083786 10.03829002 8.27814293 14.77719498 22.52552795 14.55769348 14.89605904 1.8559593 18.86129189 11.26242161 14.28984642 7.39245987 7.28826714 10.65793942 8.98 8.97 9.65 0.11 23.12 91835961470 282211175400 6.74 10.43 20.60 21.09 21.57 31.2575 31.9795 607.5735 156.4283 1.06679213 9.55909538 3.05001688 0.85797596 5.13171148 2.88348198 1.51779914 2.58714175 2.21146965 1.74074161 2.26641607 1.13998687 3.81245542 5.89775848 2.60907817 3.87790275 0.35801557 3.69217634 3.75427246 3.86610818 2.08224201 4.44657946 2.49517747 3243345.2 98528.8 0.45 5.2296 191.0971 717.5936 132.2719 36.9146 2596.0961 717.9791 132.4219 17.3019 5540.517 20.6837 48.332 14.6426 68.2636 20.686 48.3264 382.5561 249.4983 84.2491 1136.6439 15.3653 65.0079 4.4341 225.4047 121.6067 786.8905 120.0373 797.4124 54.5546 1756.5569 1.2404 804.7528 5.6159 17047.639 54.4859 1759.0746 4.718 211.7729 4.7117 212.1305 4.7775 209.1955 4.829 206.969 184.347 31728.9 0.82 3996.76 8.208 21.313 86.841 123777.7 122070.3 122971 123411.1 131613.6 186.609 162.561 6.28 9.63 569.955 639.088 1703.25 13434.09 2792.09 421.91 1632.45 OpenBenchmarking.org
PyTorch OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_l a b 0.522 1.044 1.566 2.088 2.61 SE +/- 0.00, N = 3 2.32 2.28 MIN: 1.83 / MAX: 2.8 MIN: 1.71 / MAX: 2.84
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_l a b 0.5265 1.053 1.5795 2.106 2.6325 SE +/- 0.01, N = 3 2.32 2.34 MIN: 1.77 / MAX: 2.81 MIN: 1.78 / MAX: 2.78
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_l a b 0.522 1.044 1.566 2.088 2.61 SE +/- 0.01, N = 3 2.32 2.32 MIN: 1.86 / MAX: 2.8 MIN: 1.93 / MAX: 2.71
Apache Spark TPC-H This is a benchmark of Apache Spark using TPC-H data-set. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmarks the Apache Spark in a single-system configuration using spark-submit. The test makes use of https://github.com/ssavvides/tpch-spark/ for facilitating the TPC-H benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q22 a b 3 6 9 12 15 SE +/- 0.12, N = 3 10.69 10.87
PyTorch OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 32 - Model: ResNet-152 a b 3 6 9 12 15 SE +/- 0.10, N = 3 8.90 8.98 MIN: 4.8 / MAX: 9.23 MIN: 5.1 / MAX: 9.29
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 16 - Model: ResNet-152 a b 3 6 9 12 15 SE +/- 0.10, N = 3 8.93 8.97 MIN: 4.75 / MAX: 9.39 MIN: 4.96 / MAX: 9.11
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 256 - Model: ResNet-152 a b 3 6 9 12 15 SE +/- 0.05, N = 3 8.96 9.65 MIN: 4.84 / MAX: 9.24 MIN: 4.98 / MAX: 9.85
WebP2 Image Encode This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better WebP2 Image Encode 20220823 Encode Settings: Quality 100, Lossless Compression a b 0.0248 0.0496 0.0744 0.0992 0.124 SE +/- 0.00, N = 3 0.11 0.11 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
PyTorch OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 1 - Model: ResNet-50 a b 6 12 18 24 30 SE +/- 0.19, N = 15 23.57 23.12 MIN: 11.38 / MAX: 25.62 MIN: 12.17 / MAX: 24.33
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. The system/openssl test profiles relies on benchmarking the system/OS-supplied openssl binary rather than the pts/openssl test profile that uses the locally-built OpenSSL for benchmarking. Learn more via the OpenBenchmarking.org test page.
Algorithm: AES-256-GCM
a: The test run did not produce a result. E: 40270E64087F0000:error:1C800066:Provider routines:ossl_gcm_stream_update:cipher operation failed:../providers/implementations/ciphers/ciphercommon_gcm.c:320:
b: The test run did not produce a result. E: 408712FE017F0000:error:1C800066:Provider routines:ossl_gcm_stream_update:cipher operation failed:../providers/implementations/ciphers/ciphercommon_gcm.c:320:
Algorithm: AES-128-GCM
a: The test run did not produce a result. E: 4097A6F7B77F0000:error:1C800066:Provider routines:ossl_gcm_stream_update:cipher operation failed:../providers/implementations/ciphers/ciphercommon_gcm.c:320:
b: The test run did not produce a result. E: 40B7EFA3BE7F0000:error:1C800066:Provider routines:ossl_gcm_stream_update:cipher operation failed:../providers/implementations/ciphers/ciphercommon_gcm.c:320:
OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: SHA512 a b 20000M 40000M 60000M 80000M 100000M SE +/- 191332047.54, N = 3 91630925473 91835961470 1. OpenSSL 3.0.10 1 Aug 2023 (Library: OpenSSL 3.0.10 1 Aug 2023)
Algorithm: ChaCha20-Poly1305
a: The test run did not produce a result.
b: The test run did not produce a result.
Algorithm: ChaCha20
a: The test run did not produce a result.
b: The test run did not produce a result.
OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: SHA256 a b 60000M 120000M 180000M 240000M 300000M SE +/- 548972949.20, N = 3 281869895760 282211175400 1. OpenSSL 3.0.10 1 Aug 2023 (Library: OpenSSL 3.0.10 1 Aug 2023)
PyTorch OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_l a b 2 4 6 8 10 SE +/- 0.05, N = 3 6.40 6.74 MIN: 2.93 / MAX: 6.73 MIN: 3.48 / MAX: 6.89
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 1 - Model: ResNet-152 a b 3 6 9 12 15 SE +/- 0.08, N = 3 10.16 10.43 MIN: 4.56 / MAX: 10.94 MIN: 4.8 / MAX: 11.36
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 256 - Model: ResNet-50 a b 5 10 15 20 25 SE +/- 0.31, N = 3 21.29 20.60 MIN: 13.22 / MAX: 22.39 MIN: 13.89 / MAX: 21.35
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 32 - Model: ResNet-50 a b 5 10 15 20 25 SE +/- 0.20, N = 3 21.00 21.09 MIN: 11.39 / MAX: 21.87 MIN: 13.93 / MAX: 21.71
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 16 - Model: ResNet-50 a b 5 10 15 20 25 SE +/- 0.25, N = 3 21.16 21.57 MIN: 12.26 / MAX: 22.24 MIN: 14.06 / MAX: 22.29
Apache Spark TPC-H This is a benchmark of Apache Spark using TPC-H data-set. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmarks the Apache Spark in a single-system configuration using spark-submit. The test makes use of https://github.com/ssavvides/tpch-spark/ for facilitating the TPC-H benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q22 a b 0.24 0.48 0.72 0.96 1.2 SE +/- 0.03222070, N = 3 1.00769047 1.06679213
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. The system/openssl test profiles relies on benchmarking the system/OS-supplied openssl binary rather than the pts/openssl test profile that uses the locally-built OpenSSL for benchmarking. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org verify/s, More Is Better OpenSSL Algorithm: RSA4096 a b 700K 1400K 2100K 2800K 3500K SE +/- 1292.47, N = 3 3244390.3 3243345.2 1. OpenSSL 3.0.10 1 Aug 2023 (Library: OpenSSL 3.0.10 1 Aug 2023)
OpenBenchmarking.org sign/s, More Is Better OpenSSL Algorithm: RSA4096 a b 20K 40K 60K 80K 100K SE +/- 53.45, N = 3 98622.0 98528.8 1. OpenSSL 3.0.10 1 Aug 2023 (Library: OpenSSL 3.0.10 1 Aug 2023)
WebP2 Image Encode This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better WebP2 Image Encode 20220823 Encode Settings: Quality 95, Compression Effort 7 a b 0.1013 0.2026 0.3039 0.4052 0.5065 SE +/- 0.00, N = 3 0.45 0.45 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
Neural Magic DeepSparse This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.6 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream a b 1.1785 2.357 3.5355 4.714 5.8925 SE +/- 0.0015, N = 3 5.2377 5.2296
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 13 - Input: Bosphorus 4K a b 40 80 120 160 200 SE +/- 1.61, N = 15 176.67 184.35 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Xmrig Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: GhostRider - Hash Count: 1M a b 7K 14K 21K 28K 35K SE +/- 24.02, N = 3 31859.7 31728.9 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
WebP2 Image Encode This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better WebP2 Image Encode 20220823 Encode Settings: Quality 75, Compression Effort 7 a b 0.1868 0.3736 0.5604 0.7472 0.934 SE +/- 0.00, N = 3 0.83 0.82 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
Java SciMark This test runs the Java version of SciMark 2, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.2 Computational Test: Composite a b 900 1800 2700 3600 4500 SE +/- 6.24, N = 3 3984.62 3996.76
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 4 - Input: Bosphorus 4K a b 2 4 6 8 10 SE +/- 0.041, N = 3 8.248 8.208 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 4 - Input: Bosphorus 1080p a b 5 10 15 20 25 SE +/- 0.13, N = 3 21.42 21.31 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 8 - Input: Bosphorus 4K a b 20 40 60 80 100 SE +/- 0.17, N = 3 86.43 86.84 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Xmrig Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: CryptoNight-Heavy - Hash Count: 1M a b 30K 60K 90K 120K 150K SE +/- 33.09, N = 3 123041.6 123777.7 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: CryptoNight-Femto UPX2 - Hash Count: 1M a b 30K 60K 90K 120K 150K SE +/- 220.87, N = 3 123199.0 122070.3 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: Monero - Hash Count: 1M a b 30K 60K 90K 120K 150K SE +/- 404.54, N = 3 123352.8 122971.0 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: KawPow - Hash Count: 1M a b 30K 60K 90K 120K 150K SE +/- 87.00, N = 3 123558.6 123411.1 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: Wownero - Hash Count: 1M a b 30K 60K 90K 120K 150K SE +/- 621.69, N = 3 131141.9 131613.6 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 12 - Input: Bosphorus 4K a b 40 80 120 160 200 SE +/- 1.43, N = 3 178.91 186.61 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 8 - Input: Bosphorus 1080p a b 40 80 120 160 200 SE +/- 1.87, N = 3 165.10 162.56 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
WebP2 Image Encode This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better WebP2 Image Encode 20220823 Encode Settings: Quality 100, Compression Effort 5 a b 2 4 6 8 10 SE +/- 0.04, N = 3 6.51 6.28 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 12 - Input: Bosphorus 1080p a b 120 240 360 480 600 SE +/- 1.39, N = 3 571.88 569.96 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 13 - Input: Bosphorus 1080p a b 140 280 420 560 700 SE +/- 8.75, N = 3 635.81 639.09 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Java SciMark This test runs the Java version of SciMark 2, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.2 Computational Test: Jacobi Successive Over-Relaxation a b 400 800 1200 1600 2000 SE +/- 0.16, N = 3 1703.42 1703.25
a Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10113eJava Notes: OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)Python Notes: Python 3.11.6Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 24 December 2023 15:26 by user phoronix.
b Processor: 2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1007B BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 23.10, Kernel: 6.5.0-13-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 800x600
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10113eJava Notes: OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)Python Notes: Python 3.11.6Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 25 December 2023 00:19 by user phoronix.