Benchmarks for a future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2211102-PTS-GENOAEXT88 AMD EPYC 9554 EPYC 9654 Benchmarks Genoa - Phoronix Test Suite AMD EPYC 9554 EPYC 9654 Benchmarks Genoa Benchmarks for a future article.
HTML result view exported from: https://openbenchmarking.org/result/2211102-PTS-GENOAEXT88&sor&grr .
AMD EPYC 9554 EPYC 9654 Benchmarks Genoa Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Vulkan Compiler File-System Screen Resolution EPYC 9654 2P EPYC 9654 2P Repeat EPYC 9654 2P - Perf M EPYC 9654 EPYC 9654 Repeat EPYC 9654 Power 9654 Power AMD EPYC 75F3 32-Core 75F32 9554 TwoP EPYC 9554 8380 2p 2 x AMD EPYC 9654 96-Core @ 3.71GHz (192 Cores / 384 Threads) AMD Titanite_4G (RTI1002E BIOS) AMD Device 14a4 1520GB 3841GB Micron_9300_MTFDHAL3T8TDP ASPEED VGA HDMI Broadcom NetXtreme BCM5720 PCIe Ubuntu 22.10 6.0.0-060000rc3daily20220904-generic (x86_64) GNOME Shell X Server 1.21.1.3 1.3.211 GCC 12.2.0 ext4 1920x1080 AMD EPYC 9654 96-Core @ 3.71GHz (96 Cores / 192 Threads) 768GB AMD EPYC 75F3 32-Core @ 2.95GHz (32 Cores / 64 Threads) AMD DAYTONA_X (RYM1009B BIOS) AMD Starship/Matisse 256GB VE228 2 x Mellanox MT27710 2 x AMD EPYC 9554 64-Core @ 3.76GHz (128 Cores / 256 Threads) AMD Titanite_4G (RTI1002E BIOS) AMD Device 14a4 1520GB VGA HDMI Broadcom NetXtreme BCM5720 PCIe AMD EPYC 9554 64-Core @ 3.76GHz (64 Cores / 128 Threads) 768GB 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads) Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) Intel Ice Lake IEH 512GB VE228 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - EPYC 9654 2P: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110d - EPYC 9654 2P Repeat: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110d - EPYC 9654 2P - Perf M: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110d - EPYC 9654: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110d - EPYC 9654 Repeat: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110d - EPYC 9654 Power: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110d - 9654 Power: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110d - AMD EPYC 75F3 32-Core: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173 - 75F32: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173 - 9554 TwoP: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110d - EPYC 9554: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110d - 8380 2p: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0xd000375 Java Details - EPYC 9654 2P, AMD EPYC 75F3 32-Core, 75F32, 9554 TwoP, EPYC 9554, 8380 2p: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1) Python Details - Python 3.10.6 Security Details - EPYC 9654 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9654 2P Repeat: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9654 2P - Perf M: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9654: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9654 Repeat: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9654 Power: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - 9654 Power: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - AMD EPYC 75F3 32-Core: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - 75F32: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - 9554 TwoP: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9554: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - 8380 2p: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Not affected + 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
AMD EPYC 9554 EPYC 9654 Benchmarks Genoa hbase: 1000000 - Increment - 500 hbase: 1000000 - Increment - 500 hbase: 1000000 - Increment - 256 hbase: 1000000 - Increment - 256 tensorflow: CPU - 512 - VGG-16 tensorflow: CPU - 256 - VGG-16 tensorflow: CPU - 512 - ResNet-50 hammerdb-mariadb: 64 - 250 hammerdb-mariadb: 64 - 250 hammerdb-mariadb: 64 - 500 hammerdb-mariadb: 64 - 500 hammerdb-mariadb: 64 - 100 hammerdb-mariadb: 64 - 100 smhasher: SHA3-256 smhasher: SHA3-256 tensorflow: CPU - 256 - ResNet-50 openfoam: drivaerFastback, Medium Mesh Size - Execution Time openfoam: drivaerFastback, Medium Mesh Size - Mesh Time hbase: 1000000 - Scan - 1 hbase: 10000 - Scan - 1 jpegxl: JPEG - 100 jpegxl: PNG - 100 ffmpeg: libx264 - Upload ffmpeg: libx264 - Upload hbase: 10000 - Increment - 500 hbase: 10000 - Increment - 500 tensorflow: CPU - 512 - GoogLeNet hbase: 10000 - Rand Read - 500 hbase: 10000 - Rand Read - 500 tensorflow: CPU - 64 - VGG-16 ffmpeg: libx264 - Platform ffmpeg: libx264 - Platform build-linux-kernel: allmodconfig ffmpeg: libx264 - Video On Demand ffmpeg: libx264 - Video On Demand blender: Barbershop - CPU-Only ffmpeg: libx265 - Upload ffmpeg: libx265 - Upload ffmpeg: libx265 - Platform ffmpeg: libx265 - Platform ffmpeg: libx265 - Video On Demand ffmpeg: libx265 - Video On Demand openradioss: Bird Strike on Windshield tensorflow: CPU - 64 - ResNet-50 tensorflow: CPU - 256 - GoogLeNet build-nodejs: Time To Compile tensorflow: CPU - 32 - VGG-16 hbase: 10000 - Increment - 256 hbase: 10000 - Increment - 256 hbase: 10000 - Rand Read - 256 hbase: 10000 - Rand Read - 256 jpegxl: JPEG - 80 hbase: 10000 - Rand Write - 256 openradioss: INIVOL and Fluid Structure Interaction Drop Container jpegxl: PNG - 80 jpegxl: JPEG - 90 tensorflow: CPU - 512 - AlexNet jpegxl: PNG - 90 hbase: 10000 - Rand Write - 256 tensorflow: CPU - 32 - ResNet-50 openradioss: Rubber O-Ring Seal Installation hbase: 1000000 - Increment - 1 hbase: 1000000 - Increment - 1 openradioss: Bumper Beam tensorflow: CPU - 16 - VGG-16 avifenc: 0 hbase: 1000000 - Rand Read - 1 hbase: 1000000 - Rand Read - 1 tensorflow: CPU - 16 - ResNet-50 ffmpeg: libx265 - Live ffmpeg: libx265 - Live deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream blender: Pabellon Barcelona - CPU-Only openfoam: drivaerFastback, Small Mesh Size - Execution Time openfoam: drivaerFastback, Small Mesh Size - Mesh Time deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream jpegxl-decode: 1 tensorflow: CPU - 256 - AlexNet deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - 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: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream tensorflow: CPU - 64 - GoogLeNet blender: Classroom - CPU-Only ffmpeg: libx264 - Live ffmpeg: libx264 - Live deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream spacy: en_core_web_trf spacy: en_core_web_lg hbase: 1000000 - Scan - 256 deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream cpuminer-opt: Myriad-Groestl deepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Stream deepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Stream clickhouse: 100M Rows Web Analytics Dataset, First Run / Cold Cache clickhouse: 100M Rows Web Analytics Dataset, Second Run clickhouse: 100M Rows Web Analytics Dataset, Third Run build-godot: Time To Compile deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream avifenc: 2 xmrig: Monero - 1M openradioss: Cell Phone Drop Test cpuminer-opt: Garlicoin compress-7zip: Decompression Rating compress-7zip: Compression Rating tensorflow: CPU - 32 - GoogLeNet stress-ng: Atomic cpuminer-opt: Ringcoin stress-ng: Context Switching stress-ng: Glibc C String Functions stress-ng: Malloc stress-ng: IO_uring stress-ng: Futex stress-ng: CPU Cache stress-ng: System V Message Passing stress-ng: NUMA stress-ng: Socket Activity stress-ng: Mutex stress-ng: MEMFD stress-ng: CPU Stress cpuminer-opt: Quad SHA-256, Pyrite stress-ng: Crypto stress-ng: SENDFILE stress-ng: Forking stress-ng: Vector Math stress-ng: MMAP cpuminer-opt: scrypt stress-ng: Matrix Math stress-ng: Glibc Qsort Data Sorting stress-ng: Semaphores stress-ng: Memory Copying cpuminer-opt: Deepcoin cpuminer-opt: Triple SHA-256, Onecoin cpuminer-opt: Blake-2 S cpuminer-opt: x25x cpuminer-opt: Magi cpuminer-opt: LBC, LBRY Credits cpuminer-opt: Skeincoin xmrig: Wownero - 1M build-linux-kernel: defconfig blender: Fishy Cat - CPU-Only tensorflow: CPU - 16 - GoogLeNet jpegxl-decode: All x265: Bosphorus 4K build-mesa: Time To Compile tensorflow: CPU - 64 - AlexNet blender: BMW27 - CPU-Only tensorflow: CPU - 32 - AlexNet y-cruncher: 1B openfoam: motorBike - Execution Time smhasher: FarmHash128 smhasher: FarmHash128 smhasher: MeowHash x86_64 AES-NI smhasher: MeowHash x86_64 AES-NI tensorflow: CPU - 16 - AlexNet y-cruncher: 500M x264: Bosphorus 4K smhasher: Spooky32 smhasher: Spooky32 smhasher: FarmHash32 x86_64 AVX smhasher: FarmHash32 x86_64 AVX x265: Bosphorus 1080p smhasher: fasthash32 smhasher: fasthash32 smhasher: t1ha2_atonce smhasher: t1ha2_atonce smhasher: t1ha0_aes_avx2 x86_64 smhasher: t1ha0_aes_avx2 x86_64 hbase: 10000 - Increment - 1 hbase: 10000 - Increment - 1 avifenc: 6, Lossless hbase: 10000 - Rand Read - 1 hbase: 10000 - Rand Read - 1 smhasher: wyhash smhasher: wyhash avifenc: 10, Lossless hbase: 10000 - Rand Write - 1 hbase: 10000 - Rand Write - 1 x264: Bosphorus 1080p avifenc: 6 EPYC 9654 2P EPYC 9654 2P Repeat EPYC 9654 2P - Perf M EPYC 9654 EPYC 9654 Repeat EPYC 9654 Power 9654 Power AMD EPYC 75F3 32-Core 75F32 9554 TwoP EPYC 9554 8380 2p 1993 127105 122.13 111.05 147.32 1829.798 216.01 111.54 107.85826 133.96745 0.73 0.8 1599 149429 441.71 468 339482 81.58 100.41 72.86 208.98 57.85 322.23 95.541 60.45 864 155246 270 388592 9.29 75.6 9.57 9.23 1672.89 9.48 39.57 124.51 69 14345 76.4 41 63.562 55 17925 21.51 964.8329 98.0408 22.88 19.919399 24.847602 974.0153 97.4788 48.53 1279.03 144.0459 663.579 114.3987 836.9886 157.71 17.65 2515 13481 72.6323 1318.3224 99.0265 967.2269 43.0112 2227.4198 33.863 34.654 16.87 1323090 940574 108.56 19.725 10.56 62.44 275.97 22.94 20.089 475.54 7.53 296.29 10.154 47.828 21167.17 45.11 54190.54 153.29 4.925 104.77 26.855 20577.15 39795.99 26.387 22.076 8803.42 20135.2 20.097 20.472 102425.27 181 5319 5.323 142 6698 31218.05 13.988 4.322 36 25907 2.422 123.2 113.24 147.82 1829.043 216.02 110.01 104.23027 118.67648 0.7 0.79 443.93 79.43 100.525 72.78 208.25 59.49 327.47 95.425 59.82 9.32 76.15 9.49 9.05 1669.87 9.47 40.61 126.01 75.76 40.06 63.108 22.48 969.4243 97.2856 23.28 19.631093 25.539527 966.6015 97.6967 48.51 1326.14 142.5791 671.4008 113.9772 840.234 11.3456 88.0745 27.2902 36.633 27.2133 36.7364 166.76 17.75 9.866 101.3021 2461 13467 72.544 1320.4156 97.5018 982.4985 5.1748 193.0775 42.6258 2244.1857 5.0334 198.4991 33.335 5.2274 191.2068 34.526 17.06 1309354 930946 108.94 19.658 10.46 62.69 275.75 24.3 20.131 545.59 7.47 286.45 10.13 5.98052 47.825 21167.48 45.11 54192.22 161.41 4.947 104.56 27.617 20580.28 39794.95 26.387 72.76 22.077 8803.35 19789.96 20.097 20.472 101829.9 5.21 31247.36 13.968 4.288 265.96 2.415 110.75 104.39 145.44 1829.207 216.15 108.07 112.69451 141.1001 0.73 0.8 437.65 75.72 108.584 81.91 216.62 58.76 320.99 98.302 55.34 9.29 82.52 9.68 9.28 1587.05 9.62 39.86 131.11 82.83 40.86 63.078 22.29 1132.3775 84.4798 25.67 23.083579 27.078221 1131.6891 84.2018 49.02 1198.78 155.2956 616.4604 125.4096 763.1827 11.7502 85.044 29.4073 33.9949 28.9745 34.5036 168.86 20.11 10.0306 99.6372 2585 13415 80.0948 1195.8283 111.4821 858.8745 5.4359 183.7787 49.1409 1949.0047 5.2709 189.5308 33.419 5.2827 189.2062 35.074 18.64 1176187 908312 108.71 20.486 11.51 63.05 284.19 22.86 20.01 535.77 8.47 289.65 10.164 5.90181 47.829 21167.29 45.114 54144.85 160.4 4.983 65.37 26.662 20576.77 39795.43 26.387 70.5 22.078 8803.4 20135.14 20.097 20.472 102396.46 5.241 31248.91 14.215 4.244 200.65 2.422 69.57 66.42 165 1829.749 216.08 146.3 246.8784 119.71925 0.77 0.82 530.05 61.53 173.494 143.42 120.27 99.93 473.4 122.911 57.61 9.68 103.31 9.95 9.57 1373.02 9.9 76.17 68.04 73.39 51.31 62.299 52.44 1115.4963 43.0051 48.75 29.738615 23.919399 1110.0037 42.2142 49.78 1258.48 150.6057 318.5908 119.0525 402.574 11.4651 87.1775 28.104 35.5748 28.0193 35.6818 295.82 38.67 9.8478 101.5028 3234 13551 76.6433 625.932 106.5518 449.3802 5.2236 191.3244 47.4746 1010.1033 5.2151 191.6061 33.124 5.2064 191.9953 33.75 22.99 652935 677342 227.88 24.519 20.38 130.47 317.83 31.16 20.75 834.42 15.69 581.17 6.516 4.301 47.825 21167.64 45.11 54220.23 360.18 3.969 65.8 26.703 20581.55 39796.13 26.387 91.88 22.077 8803.52 20134.69 20.097 20.472 102376.03 5.161 31198.52 13.968 4.124 211.7 2.29 69.54 66.49 164.66 1871.004 211.82 146.45 246.82702 131.63939 0.73 0.82 529.62 61.54 174.426 143.56 121.04 100.91 471.92 122.749 57.45 9.68 104.23 9.94 9.58 1369.54 9.87 75.61 66.59 77.93 51.6 62.274 52.44 1115.9013 42.9884 49.15 28.791715 26.389312 1112.4846 43.1327 49.83 1257.65 151.3705 316.9094 119.5359 400.7293 11.4062 87.6256 28.2158 35.4341 28.0928 35.5886 310.69 38.71 9.8059 101.9321 3307 13517 76.8488 624.2323 107.668 444.9684 5.2613 189.9258 47.5377 1008.1787 5.212 191.7217 33.399 5.1744 193.1856 33.835 22.73 653127 673198 225.06 24.63 20.83 144.38 316.47 31.32 20.828 838.94 15.43 580.97 6.54 4.35122 47.825 21166.21 45.112 54212.96 358.82 3.959 109.74 26.663 20582.57 39795.04 26.387 91.8 22.077 8775.9 20135.19 20.097 20.472 102315.37 5.226 31201.2 13.968 4.427 265.77 2.321 73.65 70.93 172.75 1830.336 216.13 150.26 237.49597 113.75167 0.73 0.82 558.92 65.62 157.734 127.45 113.86 100.8 495.44 117.06 60.63 9.7 90.53 9.95 9.62 1467.71 9.9 77.29 61.49 70.82 53.71 61.731 53.4 971.9156 48.8409 43.61 24.509173 23.774357 972.4797 49.0518 49.71 1331.08 142.1002 337.0033 112.8884 424.4335 11.2064 89.1886 26.6697 37.4876 26.8063 37.2968 316.07 33.63 9.77 102.3074 3186 13527 72.331 662.79 96.2264 497.6848 5.1375 194.4994 42.5217 1127.3599 5.0333 198.5208 32.438 5.2442 190.6164 33.7 20.45 737688 717647 214.98 23.195 18.21 145.11 318.9 31.57 20.398 870.59 14 599.98 6.47 4.352 47.825 21168.01 45.112 54202.27 366.73 3.872 65.5 26.683 20582.79 39795.02 26.387 93.54 22.08 8802.19 20135.17 20.097 20.477 102400.95 5.083 31197.92 13.968 4.078 221.25 2.311 73.86 70.84 172.84 1829.028 216.08 149.71 240.38495 111.27604 0.74 0.81 557.52 65.84 157.455 127.78 111.68 100.73 495.35 117.309 61.12 9.77 90.38 10.05 9.64 1461.6 9.98 76.49 61.51 69.93 53.84 62.037 52.97 970.5421 48.8566 43.73 25.756809 25.707768 972.1192 48.9538 50.7 1332.68 141.0342 339.5245 112.4239 426.3633 305.7 33.55 3314 13526 72.0102 666.0508 95.9686 499.0893 42.3645 1131.4819 32.76 33.771 20.25 739434 719579 229 23.248 18.14 144.15 320.16 31.33 20.496 866.54 13.73 600.31 6.354 47.824 21167.11 45.106 54175.08 367.14 3.917 66.6 27.617 20577.01 39794.11 26.387 22.079 8803.73 20135.1 20.097 20.472 102394 5.227 31245.47 13.984 4.099 2.297 4352 113983 2062 123070 8.39 8.32 22.81 22.08 662.50325 140.04797 0.69 0.75 1821 154170 66.93 529 306869 7.99 390.846 417.12 143.06 20.64 65.83 230.153 7.76 981 141825 377 298877 9.59 1953 197.46 10.02 9.51 155.16 9.86 367796 20.11 68.23 74 13341 91.01 7.41 77.929 54 18216 18.53 658.3907 24.1673 131.98 56.44901 27.369771 658.9745 24.2269 47.4 148.12 155.2589 102.8223 161.2269 98.9738 19.7391 50.6446 61.3288 16.3037 61.4394 16.2744 64.47 106.78 25.4781 39.2348 1894 13654 79.3471 201.3251 117.105 136.3518 10.467 95.4844 59.4734 268.728 5323.29 11.716 85.317 376.51 402.41 387.02 52.216 6.9821 143.1656 40.949 24698.1 38.53 4386.9 247362 280572 65.28 160435.98 3864.56 14657098.15 5593873.2 140011498.66 67389.93 2573853.71 88.14 8704140.32 926.64 52568.44 18586817.03 1076.68 85344.04 285840 55423.94 645248.68 80179.88 202508.2 508.45 554.99 141942.95 434.57 6533513.16 6643.95 31770 645080 1493100 1399.59 1432.98 89790 287340 25865.2 41.343 52.15 57.67 332.73 28.64 26.151 129.35 41.47 113.41 14.505 4.66741 92.21 7.151 59.01 84.07 237 4097 6.536 186 5189 4.725 34 26954 205.05 3.265 4409 112527 2026 125256 8.39 8.33 22.61 21.95 664.54696 138.87709 131234 23753 0.71 0.75 1702 153938 66.56 589 278941 8 393.153 418.91 141.83 20.52 65.33 230.015 7.8 1139 129941 445 266084 9.45 1871 197.96 9.77 9.33 154.55 9.68 507877 19.97 68.47 90 11071 92.1 7.4 77.848 76 13108 18.5 660.7807 24.0973 130.92 56.24677 28.369974 660.9895 24.1165 46.7 148.28 156.1934 102.1985 161.3526 98.9457 19.844 50.378 61.4289 16.2774 61.2586 16.3224 65.21 106.73 25.5925 39.0595 1873 13644 58887584 79.53 200.8362 117.0188 136.5358 10.5574 94.6742 59.3301 269.3961 69090 11.7042 85.4021 377.33 401.99 383.67 52.07 6.9796 143.2164 41.024 24506.8 38.96 2988.41 247381 277568 65.53 165666.65 3795.43 14724434.09 5591675.77 139310693.59 67158.17 2708005.03 100.49 8711498.67 925.07 52321.47 18679911.5 1078.69 85478.88 286410 55510.14 648949.28 80711.89 202547.6 511.98 554.88 141780.31 432.8 6558615.43 6634.24 31760 644780 1476790 1398.47 1433.6 89690 287340 25841.1 41.401 52.23 58.27 320.16 28.73 26.319 129.43 41.41 112.33 14.462 4.66676 93.37 7.118 73.97 84.18 267 3631 6.651 189 5071 4.945 34 27027 217.75 3.304 97.32 92.72 163.93 28707 12322 26791 11578 86231 37109 2331.753 169.55 127.49 129.83749 116.48849 0.69 0.82 12.69 198.928088198 494.2 79.07 48.96 154.70927612 113.862 49.11 154.245416515 97.12 27.78 90.87735054 56.56 133.931322421 55.92 135.461286189 165.5 69.01 378.96 99.523 65.82 9.53 87.86 9.72 9.29 1649.63 9.64 46.75 79.68 72.64 50.73 62.262 29.83 127.92 39.477733078 911.1053 70.2107 32.04 20.906018 22.631593 909.1243 68.5689 48.88 1366.71 124.8089 511.6331 101.4258 629.9053 11.4 87.6574 38.2116 26.165 38.3383 26.0786 194.59 24.2 220.66 22.885944059 10.8598 92.0024 2118 13540 64.009 997.8874 90.0851 709.1653 6.002 166.3935 39.7045 1608.9891 9939.68 5.3104 188.1361 32.41 3.921 254.8952 34.94 82027.7 17.27 58240 945724 776447 138.44 241171.38 591.17 7907313.68 28081271 576947450.43 65946.55 3307879.37 33.95 8962692.12 904.2 79908.39 77897090.19 2624.53 366719.77 1795800 250785.92 2643264.33 2370 832532.65 4187.21 3939.46 683986.91 2210.09 19242578.69 20141.24 122790 2560590 8659890 6438.59 6463.85 854630 1631830 97285.7 20.122 13.6 87.38 278.06 23.42 20.195 645.23 9.93 387.92 7.996 5.92274 61.345 16608.92 57.74 42531.56 219.45 4.389 97.7 34.264 16145.69 31226.87 33.661 69.28 28.349 6903.87 15798.76 26.81 26.258 80341.36 5.316 24475.93 18.19 4.25 262.79 2.404 2331.575 169.57 298.96059 103.94225 0.75 0.81 54.32 186.87 108.81 133.459 51.51 9.79 117.93 10.08 9.71 10.01 49.82 70.48 47.62 61.171 29.848701 23.813094 50.48 34.607 33.475 23.19 527376 565650 25.377 341.13 31.73 20.721 6.36 61.351 16609.29 57.732 42535.23 426.56 3.3 58.79 34.268 16149.3 31226.57 33.656 28.329 6907.82 15799.09 25.759 26.258 80231.04 5.247 24509.44 18.085 4.106 2.342 37.04 35.78 83.01 107938 46470 102799 44267 108494 46690 1876.363 208.31 80.79 365.30704 165.08078 0.56 0.58 10.54 239.53 298.78 33.85 40.44 187.34 228.529 40.56 186.74 244.02 21.69 116.41 43.09 175.804151458 43.37 174.66 144.33 75.88 291.08 170.992 32.24 7.52 146.63 7.74 7.42 701.27 7.74 67.33 82.15 86.3 28.64 79.667 54.51 114.06 44.27 837.5412 47.7486 77.12 42.117751 34.432062 836.9029 47.6525 36.94 654.98 181.3562 220.229 185.2793 215.8094 19.139 52.2285 51.4766 19.4232 50.7774 19.6909 249.3 61.97 182.45 27.68 12.8394 77.83 3868 11140 88.3012 452.3605 120.3456 331.5339 9.9106 100.8229 48.3411 826.8057 42780 8.3167 120.0709 382.29 414.29 398.03 44.984 4.4386 224.8469 44.407 26231.6 33.59 31390 363204 403978 209.5 197789.23 4737 4007912.58 9412669.51 210690160.09 64705.57 1294371.34 15.96 6498292.38 693.4 8958.77 43926099.15 3857.49 213661.33 909470 85416.53 958441.04 64952.62 304766.81 3557.26 2222.77 320154.03 900.61 12534447.06 10739.63 63270 1323260 4384310 2657.99 2250.31 416520 622200 40987 30.556 31.11 167.05 246.91 24.77 26.702 498.31 23.57 402.14 10.499 50.218 19206.25 51.419 45558.18 306.58 5.324 51.8 37.699 17883.71 32568.14 31.909 74.49 28.831 8453.99 20601.61 25.897 25.687 64712.67 7.447 27859.54 19.627 5.806 193.65 3.365 OpenBenchmarking.org
Apache HBase Rows: 1000000 - Test: Increment - Clients: 500 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.5.0 Rows: 1000000 - Test: Increment - Clients: 500 AMD EPYC 75F3 32-Core 75F32 900 1800 2700 3600 4500 4352 4409
Apache HBase Rows: 1000000 - Test: Increment - Clients: 500 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.5.0 Rows: 1000000 - Test: Increment - Clients: 500 AMD EPYC 75F3 32-Core 75F32 20K 40K 60K 80K 100K 113983 112527
Apache HBase Rows: 1000000 - Test: Increment - Clients: 256 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.5.0 Rows: 1000000 - Test: Increment - Clients: 256 EPYC 9654 2P 75F32 AMD EPYC 75F3 32-Core 400 800 1200 1600 2000 1993 2026 2062
Apache HBase Rows: 1000000 - Test: Increment - Clients: 256 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.5.0 Rows: 1000000 - Test: Increment - Clients: 256 EPYC 9654 2P 75F32 AMD EPYC 75F3 32-Core 30K 60K 90K 120K 150K 127105 125256 123070
TensorFlow Device: CPU - Batch Size: 512 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 512 - Model: VGG-16 EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 2P - Perf M 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat 8380 2p 75F32 AMD EPYC 75F3 32-Core 30 60 90 120 150 123.20 122.13 110.75 97.32 73.86 73.65 69.57 69.54 37.04 8.39 8.39
TensorFlow Device: CPU - Batch Size: 256 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: VGG-16 EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 2P - Perf M 9554 TwoP EPYC 9654 Power 9654 Power EPYC 9654 Repeat EPYC 9654 8380 2p 75F32 AMD EPYC 75F3 32-Core 30 60 90 120 150 113.24 111.05 104.39 92.72 70.93 70.84 66.49 66.42 35.78 8.33 8.32
TensorFlow Device: CPU - Batch Size: 512 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 512 - Model: ResNet-50 9654 Power EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat 9554 TwoP EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 2P - Perf M 8380 2p AMD EPYC 75F3 32-Core 75F32 40 80 120 160 200 172.84 172.75 165.00 164.66 163.93 147.82 147.32 145.44 83.01 22.81 22.61
HammerDB - MariaDB Virtual Users: 64 - Warehouses: 250 OpenBenchmarking.org Transactions Per Minute, More Is Better HammerDB - MariaDB 10.9.3 Virtual Users: 64 - Warehouses: 250 8380 2p 9554 TwoP 20K 40K 60K 80K 100K 107938 28707 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
HammerDB - MariaDB Virtual Users: 64 - Warehouses: 250 OpenBenchmarking.org New Orders Per Minute, More Is Better HammerDB - MariaDB 10.9.3 Virtual Users: 64 - Warehouses: 250 8380 2p 9554 TwoP 10K 20K 30K 40K 50K 46470 12322 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
HammerDB - MariaDB Virtual Users: 64 - Warehouses: 500 OpenBenchmarking.org Transactions Per Minute, More Is Better HammerDB - MariaDB 10.9.3 Virtual Users: 64 - Warehouses: 500 8380 2p 9554 TwoP 20K 40K 60K 80K 100K 102799 26791 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
HammerDB - MariaDB Virtual Users: 64 - Warehouses: 500 OpenBenchmarking.org New Orders Per Minute, More Is Better HammerDB - MariaDB 10.9.3 Virtual Users: 64 - Warehouses: 500 8380 2p 9554 TwoP 9K 18K 27K 36K 45K 44267 11578 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
HammerDB - MariaDB Virtual Users: 64 - Warehouses: 100 OpenBenchmarking.org Transactions Per Minute, More Is Better HammerDB - MariaDB 10.9.3 Virtual Users: 64 - Warehouses: 100 8380 2p 9554 TwoP 20K 40K 60K 80K 100K 108494 86231 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
HammerDB - MariaDB Virtual Users: 64 - Warehouses: 100 OpenBenchmarking.org New Orders Per Minute, More Is Better HammerDB - MariaDB 10.9.3 Virtual Users: 64 - Warehouses: 100 8380 2p 9554 TwoP 10K 20K 30K 40K 50K 46690 37109 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
SMHasher Hash: SHA3-256 OpenBenchmarking.org cycles/hash, Fewer Is Better SMHasher 2022-08-22 Hash: SHA3-256 9654 Power EPYC 9654 2P Repeat EPYC 9654 2P - Perf M EPYC 9654 EPYC 9654 2P EPYC 9654 Power EPYC 9654 Repeat 8380 2p EPYC 9554 9554 TwoP 500 1000 1500 2000 2500 1829.03 1829.04 1829.21 1829.75 1829.80 1830.34 1871.00 1876.36 2331.58 2331.75 1. (CXX) g++ options: -march=native -O3 -flto=auto -fno-fat-lto-objects
SMHasher Hash: SHA3-256 OpenBenchmarking.org MiB/sec, More Is Better SMHasher 2022-08-22 Hash: SHA3-256 EPYC 9654 2P - Perf M EPYC 9654 Power 9654 Power EPYC 9654 EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 Repeat 8380 2p EPYC 9554 9554 TwoP 50 100 150 200 250 216.15 216.13 216.08 216.08 216.02 216.01 211.82 208.31 169.57 169.55 1. (CXX) g++ options: -march=native -O3 -flto=auto -fno-fat-lto-objects
TensorFlow Device: CPU - Batch Size: 256 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: ResNet-50 EPYC 9654 Power 9654 Power EPYC 9654 Repeat EPYC 9654 9554 TwoP EPYC 9654 2P EPYC 9654 2P Repeat EPYC 9654 2P - Perf M 8380 2p AMD EPYC 75F3 32-Core 75F32 30 60 90 120 150 150.26 149.71 146.45 146.30 127.49 111.54 110.01 108.07 80.79 22.08 21.95
OpenFOAM Input: drivaerFastback, Medium Mesh Size - Execution Time OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Medium Mesh Size - Execution Time EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 2P - Perf M 9554 TwoP EPYC 9654 Power 9654 Power EPYC 9654 Repeat EPYC 9654 EPYC 9554 8380 2p AMD EPYC 75F3 32-Core 75F32 140 280 420 560 700 104.23 107.86 112.69 129.84 237.50 240.38 246.83 246.88 298.96 365.31 662.50 664.55 -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfoamToVTK -ldynamicMesh -lfileFormats -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -llagrangian -lgenericPatchFields -lOpenFOAM -ldl -lm
OpenFOAM Input: drivaerFastback, Medium Mesh Size - Mesh Time OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Medium Mesh Size - Mesh Time EPYC 9554 9654 Power EPYC 9654 Power 9554 TwoP EPYC 9654 2P Repeat EPYC 9654 EPYC 9654 Repeat EPYC 9654 2P 75F32 AMD EPYC 75F3 32-Core EPYC 9654 2P - Perf M 8380 2p 40 80 120 160 200 103.94 111.28 113.75 116.49 118.68 119.72 131.64 133.97 138.88 140.05 141.10 165.08 -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfoamToVTK -ldynamicMesh -lfileFormats 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -llagrangian -lgenericPatchFields -lOpenFOAM -ldl -lm
Apache HBase Rows: 1000000 - Test: Scan - Clients: 1 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.5.0 Rows: 1000000 - Test: Scan - Clients: 1 75F32 30K 60K 90K 120K 150K 131234
Apache HBase Rows: 10000 - Test: Scan - Clients: 1 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.5.0 Rows: 10000 - Test: Scan - Clients: 1 75F32 5K 10K 15K 20K 25K 23753
JPEG XL libjxl Input: JPEG - Quality: 100 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: JPEG - Quality: 100 EPYC 9654 EPYC 9554 9654 Power EPYC 9654 Power EPYC 9654 Repeat EPYC 9654 2P - Perf M EPYC 9654 2P 75F32 EPYC 9654 2P Repeat 9554 TwoP AMD EPYC 75F3 32-Core 8380 2p 0.1733 0.3466 0.5199 0.6932 0.8665 0.77 0.75 0.74 0.73 0.73 0.73 0.73 0.71 0.70 0.69 0.69 0.56 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic
JPEG XL libjxl Input: PNG - Quality: 100 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: PNG - Quality: 100 9554 TwoP EPYC 9654 Power EPYC 9654 Repeat EPYC 9654 EPYC 9554 9654 Power EPYC 9654 2P - Perf M EPYC 9654 2P EPYC 9654 2P Repeat 75F32 AMD EPYC 75F3 32-Core 8380 2p 0.1845 0.369 0.5535 0.738 0.9225 0.82 0.82 0.82 0.82 0.81 0.81 0.80 0.80 0.79 0.75 0.75 0.58 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic
FFmpeg Encoder: libx264 - Scenario: Upload OpenBenchmarking.org FPS, More Is Better FFmpeg 5.1.2 Encoder: libx264 - Scenario: Upload 9554 TwoP 8380 2p 3 6 9 12 15 12.69 10.54 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
FFmpeg Encoder: libx264 - Scenario: Upload OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 5.1.2 Encoder: libx264 - Scenario: Upload 9554 TwoP 8380 2p 50 100 150 200 250 198.93 239.53 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Apache HBase Rows: 10000 - Test: Increment - Clients: 500 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.5.0 Rows: 10000 - Test: Increment - Clients: 500 EPYC 9654 2P 75F32 AMD EPYC 75F3 32-Core 400 800 1200 1600 2000 1599 1702 1821
Apache HBase Rows: 10000 - Test: Increment - Clients: 500 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.5.0 Rows: 10000 - Test: Increment - Clients: 500 AMD EPYC 75F3 32-Core 75F32 EPYC 9654 2P 30K 60K 90K 120K 150K 154170 153938 149429
TensorFlow Device: CPU - Batch Size: 512 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 512 - Model: GoogLeNet EPYC 9654 Power 9654 Power EPYC 9654 EPYC 9654 Repeat 9554 TwoP EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 2P - Perf M 8380 2p AMD EPYC 75F3 32-Core 75F32 120 240 360 480 600 558.92 557.52 530.05 529.62 494.20 443.93 441.71 437.65 298.78 66.93 66.56
Apache HBase Rows: 10000 - Test: Random Read - Clients: 500 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.5.0 Rows: 10000 - Test: Random Read - Clients: 500 EPYC 9654 2P AMD EPYC 75F3 32-Core 75F32 130 260 390 520 650 468 529 589
Apache HBase Rows: 10000 - Test: Random Read - Clients: 500 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.5.0 Rows: 10000 - Test: Random Read - Clients: 500 EPYC 9654 2P AMD EPYC 75F3 32-Core 75F32 70K 140K 210K 280K 350K 339482 306869 278941
TensorFlow Device: CPU - Batch Size: 64 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: VGG-16 EPYC 9654 2P EPYC 9654 2P Repeat 9554 TwoP EPYC 9654 2P - Perf M 9654 Power EPYC 9654 Power EPYC 9654 Repeat EPYC 9654 EPYC 9554 8380 2p 75F32 AMD EPYC 75F3 32-Core 20 40 60 80 100 81.58 79.43 79.07 75.72 65.84 65.62 61.54 61.53 54.32 33.85 8.00 7.99
FFmpeg Encoder: libx264 - Scenario: Platform OpenBenchmarking.org FPS, More Is Better FFmpeg 5.1.2 Encoder: libx264 - Scenario: Platform 9554 TwoP 8380 2p 11 22 33 44 55 48.96 40.44 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
FFmpeg Encoder: libx264 - Scenario: Platform OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 5.1.2 Encoder: libx264 - Scenario: Platform 9554 TwoP 8380 2p 40 80 120 160 200 154.71 187.34 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Timed Linux Kernel Compilation Build: allmodconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.18 Build: allmodconfig EPYC 9654 2P EPYC 9654 2P Repeat EPYC 9654 2P - Perf M 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat EPYC 9554 8380 2p AMD EPYC 75F3 32-Core 75F32 90 180 270 360 450 100.41 100.53 108.58 113.86 157.46 157.73 173.49 174.43 186.87 228.53 390.85 393.15
FFmpeg Encoder: libx264 - Scenario: Video On Demand OpenBenchmarking.org FPS, More Is Better FFmpeg 5.1.2 Encoder: libx264 - Scenario: Video On Demand 9554 TwoP 8380 2p 11 22 33 44 55 49.11 40.56 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
FFmpeg Encoder: libx264 - Scenario: Video On Demand OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 5.1.2 Encoder: libx264 - Scenario: Video On Demand 9554 TwoP 8380 2p 40 80 120 160 200 154.25 186.74 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: Barbershop - Compute: CPU-Only EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 2P - Perf M 9554 TwoP EPYC 9654 Power 9654 Power EPYC 9654 EPYC 9654 Repeat 8380 2p AMD EPYC 75F3 32-Core 75F32 90 180 270 360 450 72.78 72.86 81.91 97.12 127.45 127.78 143.42 143.56 244.02 417.12 418.91
FFmpeg Encoder: libx265 - Scenario: Upload OpenBenchmarking.org FPS, More Is Better FFmpeg 5.1.2 Encoder: libx265 - Scenario: Upload 9554 TwoP 8380 2p 7 14 21 28 35 27.78 21.69 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
FFmpeg Encoder: libx265 - Scenario: Upload OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 5.1.2 Encoder: libx265 - Scenario: Upload 9554 TwoP 8380 2p 30 60 90 120 150 90.88 116.41 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
FFmpeg Encoder: libx265 - Scenario: Platform OpenBenchmarking.org FPS, More Is Better FFmpeg 5.1.2 Encoder: libx265 - Scenario: Platform 9554 TwoP 8380 2p 13 26 39 52 65 56.56 43.09 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
FFmpeg Encoder: libx265 - Scenario: Platform OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 5.1.2 Encoder: libx265 - Scenario: Platform 9554 TwoP 8380 2p 40 80 120 160 200 133.93 175.80 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
FFmpeg Encoder: libx265 - Scenario: Video On Demand OpenBenchmarking.org FPS, More Is Better FFmpeg 5.1.2 Encoder: libx265 - Scenario: Video On Demand 9554 TwoP 8380 2p 13 26 39 52 65 55.92 43.37 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
FFmpeg Encoder: libx265 - Scenario: Video On Demand OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 5.1.2 Encoder: libx265 - Scenario: Video On Demand 9554 TwoP 8380 2p 40 80 120 160 200 135.46 174.66 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenRadioss Model: Bird Strike on Windshield OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2022.10.13 Model: Bird Strike on Windshield EPYC 9554 9654 Power EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat 75F32 AMD EPYC 75F3 32-Core 8380 2p 9554 TwoP EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 2P - Perf M 50 100 150 200 250 108.81 111.68 113.86 120.27 121.04 141.83 143.06 144.33 165.50 208.25 208.98 216.62
TensorFlow Device: CPU - Batch Size: 64 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: ResNet-50 EPYC 9654 Repeat EPYC 9654 Power 9654 Power EPYC 9654 8380 2p 9554 TwoP EPYC 9654 2P Repeat EPYC 9654 2P - Perf M EPYC 9654 2P AMD EPYC 75F3 32-Core 75F32 20 40 60 80 100 100.91 100.80 100.73 99.93 75.88 69.01 59.49 58.76 57.85 20.64 20.52
TensorFlow Device: CPU - Batch Size: 256 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: GoogLeNet EPYC 9654 Power 9654 Power EPYC 9654 EPYC 9654 Repeat 9554 TwoP EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 2P - Perf M 8380 2p AMD EPYC 75F3 32-Core 75F32 110 220 330 440 550 495.44 495.35 473.40 471.92 378.96 327.47 322.23 320.99 291.08 65.83 65.33
Timed Node.js Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 18.8 Time To Compile EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 2P - Perf M 9554 TwoP EPYC 9654 Power 9654 Power EPYC 9654 Repeat EPYC 9654 EPYC 9554 8380 2p 75F32 AMD EPYC 75F3 32-Core 50 100 150 200 250 95.43 95.54 98.30 99.52 117.06 117.31 122.75 122.91 133.46 170.99 230.02 230.15
TensorFlow Device: CPU - Batch Size: 32 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: VGG-16 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 2P EPYC 9654 2P Repeat EPYC 9654 EPYC 9654 Repeat EPYC 9654 2P - Perf M EPYC 9554 8380 2p 75F32 AMD EPYC 75F3 32-Core 15 30 45 60 75 65.82 61.12 60.63 60.45 59.82 57.61 57.45 55.34 51.51 32.24 7.80 7.76
Apache HBase Rows: 10000 - Test: Increment - Clients: 256 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.5.0 Rows: 10000 - Test: Increment - Clients: 256 EPYC 9654 2P AMD EPYC 75F3 32-Core 75F32 200 400 600 800 1000 864 981 1139
Apache HBase Rows: 10000 - Test: Increment - Clients: 256 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.5.0 Rows: 10000 - Test: Increment - Clients: 256 EPYC 9654 2P AMD EPYC 75F3 32-Core 75F32 30K 60K 90K 120K 150K 155246 141825 129941
Apache HBase Rows: 10000 - Test: Random Read - Clients: 256 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.5.0 Rows: 10000 - Test: Random Read - Clients: 256 EPYC 9654 2P AMD EPYC 75F3 32-Core 75F32 100 200 300 400 500 270 377 445
Apache HBase Rows: 10000 - Test: Random Read - Clients: 256 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.5.0 Rows: 10000 - Test: Random Read - Clients: 256 EPYC 9654 2P AMD EPYC 75F3 32-Core 75F32 80K 160K 240K 320K 400K 388592 298877 266084
JPEG XL libjxl Input: JPEG - Quality: 80 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: JPEG - Quality: 80 EPYC 9554 9654 Power EPYC 9654 Power EPYC 9654 Repeat EPYC 9654 AMD EPYC 75F3 32-Core 9554 TwoP 75F32 EPYC 9654 2P Repeat EPYC 9654 2P - Perf M EPYC 9654 2P 8380 2p 3 6 9 12 15 9.79 9.77 9.70 9.68 9.68 9.59 9.53 9.45 9.32 9.29 9.29 7.52 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic
Apache HBase Rows: 10000 - Test: Random Write - Clients: 256 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.5.0 Rows: 10000 - Test: Random Write - Clients: 256 75F32 AMD EPYC 75F3 32-Core 400 800 1200 1600 2000 1871 1953
OpenRadioss Model: INIVOL and Fluid Structure Interaction Drop Container OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2022.10.13 Model: INIVOL and Fluid Structure Interaction Drop Container EPYC 9654 2P EPYC 9654 2P Repeat EPYC 9654 2P - Perf M 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat EPYC 9554 8380 2p AMD EPYC 75F3 32-Core 75F32 40 80 120 160 200 75.60 76.15 82.52 87.86 90.38 90.53 103.31 104.23 117.93 146.63 197.46 197.96
JPEG XL libjxl Input: PNG - Quality: 80 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: PNG - Quality: 80 EPYC 9554 9654 Power AMD EPYC 75F3 32-Core EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat 75F32 9554 TwoP EPYC 9654 2P - Perf M EPYC 9654 2P EPYC 9654 2P Repeat 8380 2p 3 6 9 12 15 10.08 10.05 10.02 9.95 9.95 9.94 9.77 9.72 9.68 9.57 9.49 7.74 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic
JPEG XL libjxl Input: JPEG - Quality: 90 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: JPEG - Quality: 90 EPYC 9554 9654 Power EPYC 9654 Power EPYC 9654 Repeat EPYC 9654 AMD EPYC 75F3 32-Core 75F32 9554 TwoP EPYC 9654 2P - Perf M EPYC 9654 2P EPYC 9654 2P Repeat 8380 2p 3 6 9 12 15 9.71 9.64 9.62 9.58 9.57 9.51 9.33 9.29 9.28 9.23 9.05 7.42 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic
TensorFlow Device: CPU - Batch Size: 512 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 512 - Model: AlexNet EPYC 9654 2P EPYC 9654 2P Repeat 9554 TwoP EPYC 9654 2P - Perf M EPYC 9654 Power 9654 Power EPYC 9654 EPYC 9654 Repeat 8380 2p AMD EPYC 75F3 32-Core 75F32 400 800 1200 1600 2000 1672.89 1669.87 1649.63 1587.05 1467.71 1461.60 1373.02 1369.54 701.27 155.16 154.55
JPEG XL libjxl Input: PNG - Quality: 90 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: PNG - Quality: 90 EPYC 9554 9654 Power EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat AMD EPYC 75F3 32-Core 75F32 9554 TwoP EPYC 9654 2P - Perf M EPYC 9654 2P EPYC 9654 2P Repeat 8380 2p 3 6 9 12 15 10.01 9.98 9.90 9.90 9.87 9.86 9.68 9.64 9.62 9.48 9.47 7.74 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic
Apache HBase Rows: 10000 - Test: Random Write - Clients: 256 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.5.0 Rows: 10000 - Test: Random Write - Clients: 256 75F32 AMD EPYC 75F3 32-Core 110K 220K 330K 440K 550K 507877 367796
TensorFlow Device: CPU - Batch Size: 32 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: ResNet-50 EPYC 9654 Power 9654 Power EPYC 9654 EPYC 9654 Repeat 8380 2p 9554 TwoP EPYC 9654 2P Repeat EPYC 9654 2P - Perf M EPYC 9654 2P AMD EPYC 75F3 32-Core 75F32 20 40 60 80 100 77.29 76.49 76.17 75.61 67.33 46.75 40.61 39.86 39.57 20.11 19.97
OpenRadioss Model: Rubber O-Ring Seal Installation OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2022.10.13 Model: Rubber O-Ring Seal Installation EPYC 9554 EPYC 9654 Power 9654 Power EPYC 9654 Repeat EPYC 9654 AMD EPYC 75F3 32-Core 75F32 9554 TwoP 8380 2p EPYC 9654 2P EPYC 9654 2P Repeat EPYC 9654 2P - Perf M 30 60 90 120 150 49.82 61.49 61.51 66.59 68.04 68.23 68.47 79.68 82.15 124.51 126.01 131.11
Apache HBase Rows: 1000000 - Test: Increment - Clients: 1 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.5.0 Rows: 1000000 - Test: Increment - Clients: 1 EPYC 9654 2P AMD EPYC 75F3 32-Core 75F32 20 40 60 80 100 69 74 90
Apache HBase Rows: 1000000 - Test: Increment - Clients: 1 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.5.0 Rows: 1000000 - Test: Increment - Clients: 1 EPYC 9654 2P AMD EPYC 75F3 32-Core 75F32 3K 6K 9K 12K 15K 14345 13341 11071
OpenRadioss Model: Bumper Beam OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2022.10.13 Model: Bumper Beam 9654 Power EPYC 9554 EPYC 9654 Power 9554 TwoP EPYC 9654 EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 Repeat EPYC 9654 2P - Perf M 8380 2p AMD EPYC 75F3 32-Core 75F32 20 40 60 80 100 69.93 70.48 70.82 72.64 73.39 75.76 76.40 77.93 82.83 86.30 91.01 92.10
TensorFlow Device: CPU - Batch Size: 16 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: VGG-16 9654 Power EPYC 9654 Power EPYC 9654 Repeat EPYC 9654 9554 TwoP EPYC 9554 EPYC 9654 2P EPYC 9654 2P - Perf M EPYC 9654 2P Repeat 8380 2p AMD EPYC 75F3 32-Core 75F32 12 24 36 48 60 53.84 53.71 51.60 51.31 50.73 47.62 41.00 40.86 40.06 28.64 7.41 7.40
libavif avifenc Encoder Speed: 0 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 0 EPYC 9554 EPYC 9654 Power 9654 Power 9554 TwoP EPYC 9654 Repeat EPYC 9654 EPYC 9654 2P - Perf M EPYC 9654 2P Repeat EPYC 9654 2P 75F32 AMD EPYC 75F3 32-Core 8380 2p 20 40 60 80 100 61.17 61.73 62.04 62.26 62.27 62.30 63.08 63.11 63.56 77.85 77.93 79.67 1. (CXX) g++ options: -O3 -fPIC -lm
Apache HBase Rows: 1000000 - Test: Random Read - Clients: 1 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.5.0 Rows: 1000000 - Test: Random Read - Clients: 1 AMD EPYC 75F3 32-Core EPYC 9654 2P 75F32 20 40 60 80 100 54 55 76
Apache HBase Rows: 1000000 - Test: Random Read - Clients: 1 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.5.0 Rows: 1000000 - Test: Random Read - Clients: 1 AMD EPYC 75F3 32-Core EPYC 9654 2P 75F32 4K 8K 12K 16K 20K 18216 17925 13108
TensorFlow Device: CPU - Batch Size: 16 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: ResNet-50 8380 2p EPYC 9654 Power 9654 Power EPYC 9654 Repeat EPYC 9654 9554 TwoP EPYC 9654 2P Repeat EPYC 9654 2P - Perf M EPYC 9654 2P AMD EPYC 75F3 32-Core 75F32 12 24 36 48 60 54.51 53.40 52.97 52.44 52.44 29.83 22.48 22.29 21.51 18.53 18.50
FFmpeg Encoder: libx265 - Scenario: Live OpenBenchmarking.org FPS, More Is Better FFmpeg 5.1.2 Encoder: libx265 - Scenario: Live 9554 TwoP 8380 2p 30 60 90 120 150 127.92 114.06 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
FFmpeg Encoder: libx265 - Scenario: Live OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 5.1.2 Encoder: libx265 - Scenario: Live 9554 TwoP 8380 2p 10 20 30 40 50 39.48 44.27 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream AMD EPYC 75F3 32-Core 75F32 8380 2p 9554 TwoP EPYC 9654 2P EPYC 9654 2P Repeat 9654 Power EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat EPYC 9654 2P - Perf M 200 400 600 800 1000 658.39 660.78 837.54 911.11 964.83 969.42 970.54 971.92 1115.50 1115.90 1132.38
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream EPYC 9654 2P EPYC 9654 2P Repeat EPYC 9654 2P - Perf M 9554 TwoP 9654 Power EPYC 9654 Power 8380 2p EPYC 9654 EPYC 9654 Repeat AMD EPYC 75F3 32-Core 75F32 20 40 60 80 100 98.04 97.29 84.48 70.21 48.86 48.84 47.75 43.01 42.99 24.17 24.10
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: Pabellon Barcelona - Compute: CPU-Only EPYC 9654 2P EPYC 9654 2P Repeat EPYC 9654 2P - Perf M 9554 TwoP EPYC 9654 Power 9654 Power EPYC 9654 EPYC 9654 Repeat 8380 2p 75F32 AMD EPYC 75F3 32-Core 30 60 90 120 150 22.88 23.28 25.67 32.04 43.61 43.73 48.75 49.15 77.12 130.92 131.98
OpenFOAM Input: drivaerFastback, Small Mesh Size - Execution Time OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Execution Time EPYC 9654 2P Repeat EPYC 9654 2P 9554 TwoP EPYC 9654 2P - Perf M EPYC 9654 Power 9654 Power EPYC 9654 Repeat EPYC 9654 EPYC 9554 8380 2p 75F32 AMD EPYC 75F3 32-Core 13 26 39 52 65 19.63 19.92 20.91 23.08 24.51 25.76 28.79 29.74 29.85 42.12 56.25 56.45 -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfoamToVTK -ldynamicMesh -lfileFormats -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -llagrangian -lgenericPatchFields -lOpenFOAM -ldl -lm
OpenFOAM Input: drivaerFastback, Small Mesh Size - Mesh Time OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Mesh Time 9554 TwoP EPYC 9654 Power EPYC 9554 EPYC 9654 EPYC 9654 2P EPYC 9654 2P Repeat 9654 Power EPYC 9654 Repeat EPYC 9654 2P - Perf M AMD EPYC 75F3 32-Core 75F32 8380 2p 8 16 24 32 40 22.63 23.77 23.81 23.92 24.85 25.54 25.71 26.39 27.08 27.37 28.37 34.43 -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfoamToVTK -ldynamicMesh -lfileFormats 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -llagrangian -lgenericPatchFields -lOpenFOAM -ldl -lm
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream AMD EPYC 75F3 32-Core 75F32 8380 2p 9554 TwoP EPYC 9654 2P Repeat 9654 Power EPYC 9654 Power EPYC 9654 2P EPYC 9654 EPYC 9654 Repeat EPYC 9654 2P - Perf M 200 400 600 800 1000 658.97 660.99 836.90 909.12 966.60 972.12 972.48 974.02 1110.00 1112.48 1131.69
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 2P - Perf M 9554 TwoP EPYC 9654 Power 9654 Power 8380 2p EPYC 9654 Repeat EPYC 9654 AMD EPYC 75F3 32-Core 75F32 20 40 60 80 100 97.70 97.48 84.20 68.57 49.05 48.95 47.65 43.13 42.21 24.23 24.12
JPEG XL Decoding libjxl CPU Threads: 1 OpenBenchmarking.org MP/s, More Is Better JPEG XL Decoding libjxl 0.7 CPU Threads: 1 9654 Power EPYC 9554 EPYC 9654 Repeat EPYC 9654 EPYC 9654 Power EPYC 9654 2P - Perf M 9554 TwoP EPYC 9654 2P EPYC 9654 2P Repeat AMD EPYC 75F3 32-Core 75F32 8380 2p 11 22 33 44 55 50.70 50.48 49.83 49.78 49.71 49.02 48.88 48.53 48.51 47.40 46.70 36.94
TensorFlow Device: CPU - Batch Size: 256 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: AlexNet 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 EPYC 9654 Repeat EPYC 9654 2P - Perf M 8380 2p 75F32 AMD EPYC 75F3 32-Core 300 600 900 1200 1500 1366.71 1332.68 1331.08 1326.14 1279.03 1258.48 1257.65 1198.78 654.98 148.28 148.12
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 EPYC 9654 Repeat AMD EPYC 75F3 32-Core EPYC 9654 2P - Perf M 75F32 8380 2p 40 80 120 160 200 124.81 141.03 142.10 142.58 144.05 150.61 151.37 155.26 155.30 156.19 181.36
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 2P - Perf M 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat 8380 2p AMD EPYC 75F3 32-Core 75F32 140 280 420 560 700 671.40 663.58 616.46 511.63 339.52 337.00 318.59 316.91 220.23 102.82 102.20
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 EPYC 9654 Repeat EPYC 9654 2P - Perf M AMD EPYC 75F3 32-Core 75F32 8380 2p 40 80 120 160 200 101.43 112.42 112.89 113.98 114.40 119.05 119.54 125.41 161.23 161.35 185.28
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 2P - Perf M 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat 8380 2p AMD EPYC 75F3 32-Core 75F32 200 400 600 800 1000 840.23 836.99 763.18 629.91 426.36 424.43 402.57 400.73 215.81 98.97 98.95
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream EPYC 9654 Power EPYC 9654 2P Repeat 9554 TwoP EPYC 9654 Repeat EPYC 9654 EPYC 9654 2P - Perf M 8380 2p AMD EPYC 75F3 32-Core 75F32 5 10 15 20 25 11.21 11.35 11.40 11.41 11.47 11.75 19.14 19.74 19.84
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream EPYC 9654 Power EPYC 9654 2P Repeat 9554 TwoP EPYC 9654 Repeat EPYC 9654 EPYC 9654 2P - Perf M 8380 2p AMD EPYC 75F3 32-Core 75F32 20 40 60 80 100 89.19 88.07 87.66 87.63 87.18 85.04 52.23 50.64 50.38
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream EPYC 9654 Power EPYC 9654 2P Repeat EPYC 9654 EPYC 9654 Repeat EPYC 9654 2P - Perf M 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 14 28 42 56 70 26.67 27.29 28.10 28.22 29.41 38.21 51.48 61.33 61.43
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream EPYC 9654 Power EPYC 9654 2P Repeat EPYC 9654 EPYC 9654 Repeat EPYC 9654 2P - Perf M 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 9 18 27 36 45 37.49 36.63 35.57 35.43 33.99 26.17 19.42 16.30 16.28
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream EPYC 9654 Power EPYC 9654 2P Repeat EPYC 9654 EPYC 9654 Repeat EPYC 9654 2P - Perf M 9554 TwoP 8380 2p 75F32 AMD EPYC 75F3 32-Core 14 28 42 56 70 26.81 27.21 28.02 28.09 28.97 38.34 50.78 61.26 61.44
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream EPYC 9654 Power EPYC 9654 2P Repeat EPYC 9654 EPYC 9654 Repeat EPYC 9654 2P - Perf M 9554 TwoP 8380 2p 75F32 AMD EPYC 75F3 32-Core 9 18 27 36 45 37.30 36.74 35.68 35.59 34.50 26.08 19.69 16.32 16.27
TensorFlow Device: CPU - Batch Size: 64 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: GoogLeNet EPYC 9654 Power EPYC 9654 Repeat 9654 Power EPYC 9654 8380 2p 9554 TwoP EPYC 9654 2P - Perf M EPYC 9654 2P Repeat EPYC 9654 2P 75F32 AMD EPYC 75F3 32-Core 70 140 210 280 350 316.07 310.69 305.70 295.82 249.30 194.59 168.86 166.76 157.71 65.21 64.47
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: Classroom - Compute: CPU-Only EPYC 9654 2P EPYC 9654 2P Repeat EPYC 9654 2P - Perf M 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat 8380 2p 75F32 AMD EPYC 75F3 32-Core 20 40 60 80 100 17.65 17.75 20.11 24.20 33.55 33.63 38.67 38.71 61.97 106.73 106.78
FFmpeg Encoder: libx264 - Scenario: Live OpenBenchmarking.org FPS, More Is Better FFmpeg 5.1.2 Encoder: libx264 - Scenario: Live 9554 TwoP 8380 2p 50 100 150 200 250 220.66 182.45 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
FFmpeg Encoder: libx264 - Scenario: Live OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 5.1.2 Encoder: libx264 - Scenario: Live 9554 TwoP 8380 2p 7 14 21 28 35 22.89 27.68 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream EPYC 9654 Power EPYC 9654 Repeat EPYC 9654 EPYC 9654 2P Repeat EPYC 9654 2P - Perf M 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 6 12 18 24 30 9.7700 9.8059 9.8478 9.8660 10.0306 10.8598 12.8394 25.4781 25.5925
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream EPYC 9654 Power EPYC 9654 Repeat EPYC 9654 EPYC 9654 2P Repeat EPYC 9654 2P - Perf M 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 20 40 60 80 100 102.31 101.93 101.50 101.30 99.64 92.00 77.83 39.23 39.06
spaCy Model: en_core_web_trf OpenBenchmarking.org tokens/sec, More Is Better spaCy 3.4.1 Model: en_core_web_trf 8380 2p 9654 Power EPYC 9654 Repeat EPYC 9654 EPYC 9654 Power EPYC 9654 2P - Perf M EPYC 9654 2P EPYC 9654 2P Repeat 9554 TwoP AMD EPYC 75F3 32-Core 75F32 800 1600 2400 3200 4000 3868 3314 3307 3234 3186 2585 2515 2461 2118 1894 1873
spaCy Model: en_core_web_lg OpenBenchmarking.org tokens/sec, More Is Better spaCy 3.4.1 Model: en_core_web_lg AMD EPYC 75F3 32-Core 75F32 EPYC 9654 9554 TwoP EPYC 9654 Power 9654 Power EPYC 9654 Repeat EPYC 9654 2P EPYC 9654 2P Repeat EPYC 9654 2P - Perf M 8380 2p 3K 6K 9K 12K 15K 13654 13644 13551 13540 13527 13526 13517 13481 13467 13415 11140
Apache HBase Rows: 1000000 - Test: Scan - Clients: 256 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.5.0 Rows: 1000000 - Test: Scan - Clients: 256 75F32 13M 26M 39M 52M 65M 58887584
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 EPYC 9654 Repeat AMD EPYC 75F3 32-Core 75F32 EPYC 9654 2P - Perf M 8380 2p 20 40 60 80 100 64.01 72.01 72.33 72.54 72.63 76.64 76.85 79.35 79.53 80.09 88.30
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 2P - Perf M 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat 8380 2p AMD EPYC 75F3 32-Core 75F32 300 600 900 1200 1500 1320.42 1318.32 1195.83 997.89 666.05 662.79 625.93 624.23 452.36 201.33 200.84
Neural Magic DeepSparse Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 EPYC 9654 Repeat EPYC 9654 2P - Perf M 75F32 AMD EPYC 75F3 32-Core 8380 2p 30 60 90 120 150 90.09 95.97 96.23 97.50 99.03 106.55 107.67 111.48 117.02 117.11 120.35
Neural Magic DeepSparse Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 2P - Perf M 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat 8380 2p 75F32 AMD EPYC 75F3 32-Core 200 400 600 800 1000 982.50 967.23 858.87 709.17 499.09 497.68 449.38 444.97 331.53 136.54 136.35
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream EPYC 9654 Power EPYC 9654 2P Repeat EPYC 9654 EPYC 9654 Repeat EPYC 9654 2P - Perf M 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 3 6 9 12 15 5.1375 5.1748 5.2236 5.2613 5.4359 6.0020 9.9106 10.4670 10.5574
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream EPYC 9654 Power EPYC 9654 2P Repeat EPYC 9654 EPYC 9654 Repeat EPYC 9654 2P - Perf M 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 40 80 120 160 200 194.50 193.08 191.32 189.93 183.78 166.39 100.82 95.48 94.67
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 EPYC 9654 Repeat 8380 2p EPYC 9654 2P - Perf M 75F32 AMD EPYC 75F3 32-Core 13 26 39 52 65 39.70 42.36 42.52 42.63 43.01 47.47 47.54 48.34 49.14 59.33 59.47
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 2P - Perf M 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat 8380 2p 75F32 AMD EPYC 75F3 32-Core 500 1000 1500 2000 2500 2244.19 2227.42 1949.00 1608.99 1131.48 1127.36 1010.10 1008.18 826.81 269.40 268.73
Cpuminer-Opt Algorithm: Myriad-Groestl OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Myriad-Groestl 75F32 8380 2p 9554 TwoP AMD EPYC 75F3 32-Core 15K 30K 45K 60K 75K 69090.00 42780.00 9939.68 5323.29 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Neural Magic DeepSparse Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream EPYC 9654 Power EPYC 9654 2P Repeat EPYC 9654 Repeat EPYC 9654 EPYC 9654 2P - Perf M 9554 TwoP 8380 2p 75F32 AMD EPYC 75F3 32-Core 3 6 9 12 15 5.0333 5.0334 5.2120 5.2151 5.2709 5.3104 8.3167 11.7042 11.7160
Neural Magic DeepSparse Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream EPYC 9654 Power EPYC 9654 2P Repeat EPYC 9654 Repeat EPYC 9654 EPYC 9654 2P - Perf M 9554 TwoP 8380 2p 75F32 AMD EPYC 75F3 32-Core 40 80 120 160 200 198.52 198.50 191.72 191.61 189.53 188.14 120.07 85.40 85.32
ClickHouse 100M Rows Web Analytics Dataset, First Run / Cold Cache OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, First Run / Cold Cache 8380 2p 75F32 AMD EPYC 75F3 32-Core 80 160 240 320 400 383.28 377.33 376.51 MIN: 56.76 / MAX: 15000 MIN: 37.85 / MAX: 10000 MIN: 37.24 / MAX: 10000 1. ClickHouse server version 22.5.4.19 (official build).
ClickHouse 100M Rows Web Analytics Dataset, Second Run OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, Second Run 8380 2p AMD EPYC 75F3 32-Core 75F32 90 180 270 360 450 414.29 402.41 401.99 MIN: 66.74 / MAX: 30000 MIN: 43.07 / MAX: 20000 MIN: 43.7 / MAX: 20000 1. ClickHouse server version 22.5.4.19 (official build).
ClickHouse 100M Rows Web Analytics Dataset, Third Run OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, Third Run 8380 2p AMD EPYC 75F3 32-Core 75F32 90 180 270 360 450 400.65 387.02 383.67 MIN: 63.56 / MAX: 20000 MIN: 41.29 / MAX: 8571.43 MIN: 43.35 / MAX: 8571.43 1. ClickHouse server version 22.5.4.19 (official build).
Timed Godot Game Engine Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 3.2.3 Time To Compile 9554 TwoP EPYC 9654 Power 9654 Power EPYC 9654 EPYC 9654 2P Repeat EPYC 9654 Repeat EPYC 9654 2P - Perf M EPYC 9654 2P EPYC 9554 8380 2p 75F32 AMD EPYC 75F3 32-Core 12 24 36 48 60 32.41 32.44 32.76 33.12 33.34 33.40 33.42 33.86 34.61 44.98 52.07 52.22
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream 9554 TwoP 8380 2p EPYC 9654 Repeat EPYC 9654 EPYC 9654 2P Repeat EPYC 9654 Power EPYC 9654 2P - Perf M 75F32 AMD EPYC 75F3 32-Core 2 4 6 8 10 3.9210 4.4386 5.1744 5.2064 5.2274 5.2442 5.2827 6.9796 6.9821
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream 9554 TwoP 8380 2p EPYC 9654 Repeat EPYC 9654 EPYC 9654 2P Repeat EPYC 9654 Power EPYC 9654 2P - Perf M 75F32 AMD EPYC 75F3 32-Core 60 120 180 240 300 254.90 224.85 193.19 192.00 191.21 190.62 189.21 143.22 143.17
libavif avifenc Encoder Speed: 2 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 2 EPYC 9554 EPYC 9654 Power EPYC 9654 9654 Power EPYC 9654 Repeat EPYC 9654 2P Repeat EPYC 9654 2P 9554 TwoP EPYC 9654 2P - Perf M AMD EPYC 75F3 32-Core 75F32 8380 2p 10 20 30 40 50 33.48 33.70 33.75 33.77 33.84 34.53 34.65 34.94 35.07 40.95 41.02 44.41 1. (CXX) g++ options: -O3 -fPIC -lm
Xmrig Variant: Monero - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.18.1 Variant: Monero - Hash Count: 1M 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 20K 40K 60K 80K 100K 82027.7 26231.6 24698.1 24506.8 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenRadioss Model: Cell Phone Drop Test OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2022.10.13 Model: Cell Phone Drop Test EPYC 9654 2P EPYC 9654 2P Repeat 9554 TwoP EPYC 9654 2P - Perf M 9654 Power EPYC 9654 Power EPYC 9654 Repeat EPYC 9654 EPYC 9554 8380 2p AMD EPYC 75F3 32-Core 75F32 9 18 27 36 45 16.87 17.06 17.27 18.64 20.25 20.45 22.73 22.99 23.19 33.59 38.53 38.96
Cpuminer-Opt Algorithm: Garlicoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Garlicoin 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 12K 24K 36K 48K 60K 58240.00 31390.00 4386.90 2988.41 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
7-Zip Compression Test: Decompression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Decompression Rating EPYC 9654 2P EPYC 9654 2P Repeat EPYC 9654 2P - Perf M 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 Repeat EPYC 9654 EPYC 9554 8380 2p 75F32 AMD EPYC 75F3 32-Core 300K 600K 900K 1200K 1500K 1323090 1309354 1176187 945724 739434 737688 653127 652935 527376 363204 247381 247362 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
7-Zip Compression Test: Compression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Compression Rating EPYC 9654 2P EPYC 9654 2P Repeat EPYC 9654 2P - Perf M 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat EPYC 9554 8380 2p AMD EPYC 75F3 32-Core 75F32 200K 400K 600K 800K 1000K 940574 930946 908312 776447 719579 717647 677342 673198 565650 403978 280572 277568 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
TensorFlow Device: CPU - Batch Size: 32 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: GoogLeNet 9654 Power EPYC 9654 EPYC 9654 Repeat EPYC 9654 Power 8380 2p 9554 TwoP EPYC 9654 2P Repeat EPYC 9654 2P - Perf M EPYC 9654 2P 75F32 AMD EPYC 75F3 32-Core 50 100 150 200 250 229.00 227.88 225.06 214.98 209.50 138.44 108.94 108.71 108.56 65.53 65.28
Stress-NG Test: Atomic OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Atomic 9554 TwoP 8380 2p 75F32 AMD EPYC 75F3 32-Core 50K 100K 150K 200K 250K 241171.38 197789.23 165666.65 160435.98 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Cpuminer-Opt Algorithm: Ringcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Ringcoin 8380 2p AMD EPYC 75F3 32-Core 75F32 9554 TwoP 1000 2000 3000 4000 5000 4737.00 3864.56 3795.43 591.17 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Context Switching 75F32 AMD EPYC 75F3 32-Core 9554 TwoP 8380 2p 3M 6M 9M 12M 15M 14724434.09 14657098.15 7907313.68 4007912.58 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: Glibc C String Functions OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Glibc C String Functions 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 6M 12M 18M 24M 30M 28081271.00 9412669.51 5593873.20 5591675.77 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: Malloc OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Malloc 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 120M 240M 360M 480M 600M 576947450.43 210690160.09 140011498.66 139310693.59 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: IO_uring OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: IO_uring AMD EPYC 75F3 32-Core 75F32 9554 TwoP 8380 2p 14K 28K 42K 56K 70K 67389.93 67158.17 65946.55 64705.57 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: Futex OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Futex 9554 TwoP 75F32 AMD EPYC 75F3 32-Core 8380 2p 700K 1400K 2100K 2800K 3500K 3307879.37 2708005.03 2573853.71 1294371.34 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: CPU Cache 75F32 AMD EPYC 75F3 32-Core 9554 TwoP 8380 2p 20 40 60 80 100 100.49 88.14 33.95 15.96 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: System V Message Passing 9554 TwoP 75F32 AMD EPYC 75F3 32-Core 8380 2p 2M 4M 6M 8M 10M 8962692.12 8711498.67 8704140.32 6498292.38 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: NUMA OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: NUMA AMD EPYC 75F3 32-Core 75F32 9554 TwoP 8380 2p 200 400 600 800 1000 926.64 925.07 904.20 693.40 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Socket Activity 9554 TwoP AMD EPYC 75F3 32-Core 75F32 8380 2p 20K 40K 60K 80K 100K 79908.39 52568.44 52321.47 8958.77 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: Mutex OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Mutex 9554 TwoP 8380 2p 75F32 AMD EPYC 75F3 32-Core 20M 40M 60M 80M 100M 77897090.19 43926099.15 18679911.50 18586817.03 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: MEMFD OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: MEMFD 8380 2p 9554 TwoP 75F32 AMD EPYC 75F3 32-Core 800 1600 2400 3200 4000 3857.49 2624.53 1078.69 1076.68 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: CPU Stress 9554 TwoP 8380 2p 75F32 AMD EPYC 75F3 32-Core 80K 160K 240K 320K 400K 366719.77 213661.33 85478.88 85344.04 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Cpuminer-Opt Algorithm: Quad SHA-256, Pyrite OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Quad SHA-256, Pyrite 9554 TwoP 8380 2p 75F32 AMD EPYC 75F3 32-Core 400K 800K 1200K 1600K 2000K 1795800 909470 286410 285840 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Crypto 9554 TwoP 8380 2p 75F32 AMD EPYC 75F3 32-Core 50K 100K 150K 200K 250K 250785.92 85416.53 55510.14 55423.94 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: SENDFILE 9554 TwoP 8380 2p 75F32 AMD EPYC 75F3 32-Core 600K 1200K 1800K 2400K 3000K 2643264.33 958441.04 648949.28 645248.68 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Forking 75F32 AMD EPYC 75F3 32-Core 8380 2p 9554 TwoP 20K 40K 60K 80K 100K 80711.89 80179.88 64952.62 2370.00 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Vector Math 9554 TwoP 8380 2p 75F32 AMD EPYC 75F3 32-Core 200K 400K 600K 800K 1000K 832532.65 304766.81 202547.60 202508.20 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: MMAP OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: MMAP 9554 TwoP 8380 2p 75F32 AMD EPYC 75F3 32-Core 900 1800 2700 3600 4500 4187.21 3557.26 511.98 508.45 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Cpuminer-Opt Algorithm: scrypt OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: scrypt 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 800 1600 2400 3200 4000 3939.46 2222.77 554.99 554.88 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Matrix Math 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 150K 300K 450K 600K 750K 683986.91 320154.03 141942.95 141780.31 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: Glibc Qsort Data Sorting OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Glibc Qsort Data Sorting 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 500 1000 1500 2000 2500 2210.09 900.61 434.57 432.80 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Semaphores 9554 TwoP 8380 2p 75F32 AMD EPYC 75F3 32-Core 4M 8M 12M 16M 20M 19242578.69 12534447.06 6558615.43 6533513.16 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Memory Copying 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 4K 8K 12K 16K 20K 20141.24 10739.63 6643.95 6634.24 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Cpuminer-Opt Algorithm: Deepcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Deepcoin 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 30K 60K 90K 120K 150K 122790 63270 31770 31760 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: Triple SHA-256, Onecoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Triple SHA-256, Onecoin 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 500K 1000K 1500K 2000K 2500K 2560590 1323260 645080 644780 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: Blake-2 S OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Blake-2 S 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 2M 4M 6M 8M 10M 8659890 4384310 1493100 1476790 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: x25x OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: x25x 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 1400 2800 4200 5600 7000 6438.59 2657.99 1399.59 1398.47 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: Magi OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Magi 9554 TwoP 8380 2p 75F32 AMD EPYC 75F3 32-Core 1400 2800 4200 5600 7000 6463.85 2250.31 1433.60 1432.98 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: LBC, LBRY Credits OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: LBC, LBRY Credits 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 200K 400K 600K 800K 1000K 854630 416520 89790 89690 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: Skeincoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Skeincoin 9554 TwoP 8380 2p 75F32 AMD EPYC 75F3 32-Core 300K 600K 900K 1200K 1500K 1631830 622200 287340 287340 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Xmrig Variant: Wownero - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.18.1 Variant: Wownero - Hash Count: 1M 9554 TwoP 8380 2p AMD EPYC 75F3 32-Core 75F32 20K 40K 60K 80K 100K 97285.7 40987.0 25865.2 25841.1 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
Timed Linux Kernel Compilation Build: defconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.18 Build: defconfig EPYC 9654 2P Repeat EPYC 9654 2P 9554 TwoP EPYC 9654 2P - Perf M EPYC 9654 Power 9654 Power EPYC 9654 EPYC 9654 Repeat EPYC 9554 8380 2p AMD EPYC 75F3 32-Core 75F32 9 18 27 36 45 19.66 19.73 20.12 20.49 23.20 23.25 24.52 24.63 25.38 30.56 41.34 41.40
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: Fishy Cat - Compute: CPU-Only EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 2P - Perf M 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat 8380 2p AMD EPYC 75F3 32-Core 75F32 12 24 36 48 60 10.46 10.56 11.51 13.60 18.14 18.21 20.38 20.83 31.11 52.15 52.23
TensorFlow Device: CPU - Batch Size: 16 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: GoogLeNet 8380 2p EPYC 9654 Power EPYC 9654 Repeat 9654 Power EPYC 9654 9554 TwoP EPYC 9654 2P - Perf M EPYC 9654 2P Repeat EPYC 9654 2P 75F32 AMD EPYC 75F3 32-Core 40 80 120 160 200 167.05 145.11 144.38 144.15 130.47 87.38 63.05 62.69 62.44 58.27 57.67
JPEG XL Decoding libjxl CPU Threads: All OpenBenchmarking.org MP/s, More Is Better JPEG XL Decoding libjxl 0.7 CPU Threads: All EPYC 9554 AMD EPYC 75F3 32-Core 75F32 9654 Power EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat EPYC 9654 2P - Perf M 9554 TwoP EPYC 9654 2P EPYC 9654 2P Repeat 8380 2p 70 140 210 280 350 341.13 332.73 320.16 320.16 318.90 317.83 316.47 284.19 278.06 275.97 275.75 246.91
x265 Video Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 4K EPYC 9554 EPYC 9654 Power 9654 Power EPYC 9654 Repeat EPYC 9654 75F32 AMD EPYC 75F3 32-Core 8380 2p EPYC 9654 2P Repeat 9554 TwoP EPYC 9654 2P EPYC 9654 2P - Perf M 7 14 21 28 35 31.73 31.57 31.33 31.32 31.16 28.73 28.64 24.77 24.30 23.42 22.94 22.86 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Timed Mesa Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Mesa Compilation 21.0 Time To Compile EPYC 9654 2P - Perf M EPYC 9654 2P EPYC 9654 2P Repeat 9554 TwoP EPYC 9654 Power 9654 Power EPYC 9554 EPYC 9654 EPYC 9654 Repeat AMD EPYC 75F3 32-Core 75F32 8380 2p 6 12 18 24 30 20.01 20.09 20.13 20.20 20.40 20.50 20.72 20.75 20.83 26.15 26.32 26.70
TensorFlow Device: CPU - Batch Size: 64 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: AlexNet EPYC 9654 Power 9654 Power EPYC 9654 Repeat EPYC 9654 9554 TwoP EPYC 9654 2P Repeat EPYC 9654 2P - Perf M 8380 2p EPYC 9654 2P 75F32 AMD EPYC 75F3 32-Core 200 400 600 800 1000 870.59 866.54 838.94 834.42 645.23 545.59 535.77 498.31 475.54 129.43 129.35
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: BMW27 - Compute: CPU-Only EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 2P - Perf M 9554 TwoP 9654 Power EPYC 9654 Power EPYC 9654 Repeat EPYC 9654 8380 2p 75F32 AMD EPYC 75F3 32-Core 9 18 27 36 45 7.47 7.53 8.47 9.93 13.73 14.00 15.43 15.69 23.57 41.41 41.47
TensorFlow Device: CPU - Batch Size: 32 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: AlexNet 9654 Power EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat 8380 2p 9554 TwoP EPYC 9654 2P EPYC 9654 2P - Perf M EPYC 9654 2P Repeat AMD EPYC 75F3 32-Core 75F32 130 260 390 520 650 600.31 599.98 581.17 580.97 402.14 387.92 296.29 289.65 286.45 113.41 112.33
Y-Cruncher Pi Digits To Calculate: 1B OpenBenchmarking.org Seconds, Fewer Is Better Y-Cruncher 0.7.10.9513 Pi Digits To Calculate: 1B 9654 Power EPYC 9554 EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat 9554 TwoP EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 2P - Perf M 8380 2p 75F32 AMD EPYC 75F3 32-Core 4 8 12 16 20 6.354 6.360 6.470 6.516 6.540 7.996 10.130 10.154 10.164 10.499 14.462 14.505
OpenFOAM Input: motorBike - Execution Time OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: motorBike - Execution Time EPYC 9654 EPYC 9654 Repeat EPYC 9654 Power 75F32 AMD EPYC 75F3 32-Core EPYC 9654 2P - Perf M 9554 TwoP EPYC 9654 2P Repeat 1.3456 2.6912 4.0368 5.3824 6.728 4.30100 4.35122 4.35200 4.66676 4.66741 5.90181 5.92274 5.98052 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm
SMHasher Hash: FarmHash128 OpenBenchmarking.org cycles/hash, Fewer Is Better SMHasher 2022-08-22 Hash: FarmHash128 9654 Power EPYC 9654 2P Repeat EPYC 9654 EPYC 9654 Repeat EPYC 9654 Power EPYC 9654 2P EPYC 9654 2P - Perf M 8380 2p 9554 TwoP EPYC 9554 14 28 42 56 70 47.82 47.83 47.83 47.83 47.83 47.83 47.83 50.22 61.35 61.35 1. (CXX) g++ options: -march=native -O3 -flto=auto -fno-fat-lto-objects
SMHasher Hash: FarmHash128 OpenBenchmarking.org MiB/sec, More Is Better SMHasher 2022-08-22 Hash: FarmHash128 EPYC 9654 Power EPYC 9654 EPYC 9654 2P Repeat EPYC 9654 2P - Perf M EPYC 9654 2P 9654 Power EPYC 9654 Repeat 8380 2p EPYC 9554 9554 TwoP 5K 10K 15K 20K 25K 21168.01 21167.64 21167.48 21167.29 21167.17 21167.11 21166.21 19206.25 16609.29 16608.92 1. (CXX) g++ options: -march=native -O3 -flto=auto -fno-fat-lto-objects
SMHasher Hash: MeowHash x86_64 AES-NI OpenBenchmarking.org cycles/hash, Fewer Is Better SMHasher 2022-08-22 Hash: MeowHash x86_64 AES-NI 9654 Power EPYC 9654 2P EPYC 9654 2P Repeat EPYC 9654 EPYC 9654 Repeat EPYC 9654 Power EPYC 9654 2P - Perf M 8380 2p EPYC 9554 9554 TwoP 13 26 39 52 65 45.11 45.11 45.11 45.11 45.11 45.11 45.11 51.42 57.73 57.74 1. (CXX) g++ options: -march=native -O3 -flto=auto -fno-fat-lto-objects
SMHasher Hash: MeowHash x86_64 AES-NI OpenBenchmarking.org MiB/sec, More Is Better SMHasher 2022-08-22 Hash: MeowHash x86_64 AES-NI EPYC 9654 EPYC 9654 Repeat EPYC 9654 Power EPYC 9654 2P Repeat EPYC 9654 2P 9654 Power EPYC 9654 2P - Perf M 8380 2p EPYC 9554 9554 TwoP 12K 24K 36K 48K 60K 54220.23 54212.96 54202.27 54192.22 54190.54 54175.08 54144.85 45558.18 42535.23 42531.56 1. (CXX) g++ options: -march=native -O3 -flto=auto -fno-fat-lto-objects
TensorFlow Device: CPU - Batch Size: 16 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: AlexNet EPYC 9554 9654 Power EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat 8380 2p 9554 TwoP EPYC 9654 2P Repeat EPYC 9654 2P - Perf M EPYC 9654 2P 75F32 AMD EPYC 75F3 32-Core 90 180 270 360 450 426.56 367.14 366.73 360.18 358.82 306.58 219.45 161.41 160.40 153.29 93.37 92.21
Y-Cruncher Pi Digits To Calculate: 500M OpenBenchmarking.org Seconds, Fewer Is Better Y-Cruncher 0.7.10.9513 Pi Digits To Calculate: 500M EPYC 9554 EPYC 9654 Power 9654 Power EPYC 9654 Repeat EPYC 9654 9554 TwoP EPYC 9654 2P EPYC 9654 2P Repeat EPYC 9654 2P - Perf M 8380 2p 75F32 AMD EPYC 75F3 32-Core 2 4 6 8 10 3.300 3.872 3.917 3.959 3.969 4.389 4.925 4.947 4.983 5.324 7.118 7.151
x264 Video Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better x264 2022-02-22 Video Input: Bosphorus 4K EPYC 9654 Repeat EPYC 9654 2P EPYC 9654 2P Repeat 9554 TwoP 75F32 9654 Power EPYC 9654 EPYC 9654 Power EPYC 9654 2P - Perf M AMD EPYC 75F3 32-Core EPYC 9554 8380 2p 20 40 60 80 100 109.74 104.77 104.56 97.70 73.97 66.60 65.80 65.50 65.37 59.01 58.79 51.80 1. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -flto
SMHasher Hash: Spooky32 OpenBenchmarking.org cycles/hash, Fewer Is Better SMHasher 2022-08-22 Hash: Spooky32 EPYC 9654 2P - Perf M EPYC 9654 Repeat EPYC 9654 Power EPYC 9654 EPYC 9654 2P EPYC 9654 2P Repeat 9654 Power 9554 TwoP EPYC 9554 8380 2p 9 18 27 36 45 26.66 26.66 26.68 26.70 26.86 27.62 27.62 34.26 34.27 37.70 1. (CXX) g++ options: -march=native -O3 -flto=auto -fno-fat-lto-objects
SMHasher Hash: Spooky32 OpenBenchmarking.org MiB/sec, More Is Better SMHasher 2022-08-22 Hash: Spooky32 EPYC 9654 Power EPYC 9654 Repeat EPYC 9654 EPYC 9654 2P Repeat EPYC 9654 2P 9654 Power EPYC 9654 2P - Perf M 8380 2p EPYC 9554 9554 TwoP 4K 8K 12K 16K 20K 20582.79 20582.57 20581.55 20580.28 20577.15 20577.01 20576.77 17883.71 16149.30 16145.69 1. (CXX) g++ options: -march=native -O3 -flto=auto -fno-fat-lto-objects
SMHasher Hash: FarmHash32 x86_64 AVX OpenBenchmarking.org MiB/sec, More Is Better SMHasher 2022-08-22 Hash: FarmHash32 x86_64 AVX EPYC 9654 EPYC 9654 2P EPYC 9654 2P - Perf M EPYC 9654 Repeat EPYC 9654 Power EPYC 9654 2P Repeat 9654 Power 8380 2p 9554 TwoP EPYC 9554 9K 18K 27K 36K 45K 39796.13 39795.99 39795.43 39795.04 39795.02 39794.95 39794.11 32568.14 31226.87 31226.57 1. (CXX) g++ options: -march=native -O3 -flto=auto -fno-fat-lto-objects
SMHasher Hash: FarmHash32 x86_64 AVX OpenBenchmarking.org cycles/hash, Fewer Is Better SMHasher 2022-08-22 Hash: FarmHash32 x86_64 AVX EPYC 9654 2P EPYC 9654 2P Repeat EPYC 9654 2P - Perf M EPYC 9654 EPYC 9654 Repeat EPYC 9654 Power 9654 Power 8380 2p EPYC 9554 9554 TwoP 8 16 24 32 40 26.39 26.39 26.39 26.39 26.39 26.39 26.39 31.91 33.66 33.66 1. (CXX) g++ options: -march=native -O3 -flto=auto -fno-fat-lto-objects
x265 Video Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 1080p EPYC 9654 Power EPYC 9654 EPYC 9654 Repeat 75F32 AMD EPYC 75F3 32-Core 8380 2p EPYC 9654 2P Repeat EPYC 9654 2P - Perf M 9554 TwoP 20 40 60 80 100 93.54 91.88 91.80 84.18 84.07 74.49 72.76 70.50 69.28 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
SMHasher Hash: fasthash32 OpenBenchmarking.org cycles/hash, Fewer Is Better SMHasher 2022-08-22 Hash: fasthash32 EPYC 9654 2P EPYC 9654 2P Repeat EPYC 9654 EPYC 9654 Repeat EPYC 9654 2P - Perf M 9654 Power EPYC 9654 Power EPYC 9554 9554 TwoP 8380 2p 7 14 21 28 35 22.08 22.08 22.08 22.08 22.08 22.08 22.08 28.33 28.35 28.83 1. (CXX) g++ options: -march=native -O3 -flto=auto -fno-fat-lto-objects
SMHasher Hash: fasthash32 OpenBenchmarking.org MiB/sec, More Is Better SMHasher 2022-08-22 Hash: fasthash32 9654 Power EPYC 9654 EPYC 9654 2P EPYC 9654 2P - Perf M EPYC 9654 2P Repeat EPYC 9654 Power EPYC 9654 Repeat 8380 2p EPYC 9554 9554 TwoP 2K 4K 6K 8K 10K 8803.73 8803.52 8803.42 8803.40 8803.35 8802.19 8775.90 8453.99 6907.82 6903.87 1. (CXX) g++ options: -march=native -O3 -flto=auto -fno-fat-lto-objects
SMHasher Hash: t1ha2_atonce OpenBenchmarking.org MiB/sec, More Is Better SMHasher 2022-08-22 Hash: t1ha2_atonce 8380 2p EPYC 9654 2P EPYC 9654 Repeat EPYC 9654 Power EPYC 9654 2P - Perf M 9654 Power EPYC 9654 EPYC 9654 2P Repeat EPYC 9554 9554 TwoP 4K 8K 12K 16K 20K 20601.61 20135.20 20135.19 20135.17 20135.14 20135.10 20134.69 19789.96 15799.09 15798.76 1. (CXX) g++ options: -march=native -O3 -flto=auto -fno-fat-lto-objects
SMHasher Hash: t1ha2_atonce OpenBenchmarking.org cycles/hash, Fewer Is Better SMHasher 2022-08-22 Hash: t1ha2_atonce EPYC 9654 2P EPYC 9654 2P Repeat EPYC 9654 2P - Perf M EPYC 9654 EPYC 9654 Repeat EPYC 9654 Power 9654 Power EPYC 9554 8380 2p 9554 TwoP 6 12 18 24 30 20.10 20.10 20.10 20.10 20.10 20.10 20.10 25.76 25.90 26.81 1. (CXX) g++ options: -march=native -O3 -flto=auto -fno-fat-lto-objects
SMHasher Hash: t1ha0_aes_avx2 x86_64 OpenBenchmarking.org cycles/hash, Fewer Is Better SMHasher 2022-08-22 Hash: t1ha0_aes_avx2 x86_64 EPYC 9654 2P EPYC 9654 2P Repeat EPYC 9654 2P - Perf M EPYC 9654 EPYC 9654 Repeat 9654 Power EPYC 9654 Power 8380 2p 9554 TwoP EPYC 9554 6 12 18 24 30 20.47 20.47 20.47 20.47 20.47 20.47 20.48 25.69 26.26 26.26 1. (CXX) g++ options: -march=native -O3 -flto=auto -fno-fat-lto-objects
SMHasher Hash: t1ha0_aes_avx2 x86_64 OpenBenchmarking.org MiB/sec, More Is Better SMHasher 2022-08-22 Hash: t1ha0_aes_avx2 x86_64 EPYC 9654 2P EPYC 9654 Power EPYC 9654 2P - Perf M 9654 Power EPYC 9654 EPYC 9654 Repeat EPYC 9654 2P Repeat 9554 TwoP EPYC 9554 8380 2p 20K 40K 60K 80K 100K 102425.27 102400.95 102396.46 102394.00 102376.03 102315.37 101829.90 80341.36 80231.04 64712.67 1. (CXX) g++ options: -march=native -O3 -flto=auto -fno-fat-lto-objects
Apache HBase Rows: 10000 - Test: Increment - Clients: 1 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.5.0 Rows: 10000 - Test: Increment - Clients: 1 EPYC 9654 2P AMD EPYC 75F3 32-Core 75F32 60 120 180 240 300 181 237 267
Apache HBase Rows: 10000 - Test: Increment - Clients: 1 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.5.0 Rows: 10000 - Test: Increment - Clients: 1 EPYC 9654 2P AMD EPYC 75F3 32-Core 75F32 1100 2200 3300 4400 5500 5319 4097 3631
libavif avifenc Encoder Speed: 6, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 6, Lossless EPYC 9654 Power EPYC 9654 EPYC 9654 2P Repeat EPYC 9654 Repeat 9654 Power EPYC 9654 2P - Perf M EPYC 9554 9554 TwoP EPYC 9654 2P AMD EPYC 75F3 32-Core 75F32 8380 2p 2 4 6 8 10 5.083 5.161 5.210 5.226 5.227 5.241 5.247 5.316 5.323 6.536 6.651 7.447 1. (CXX) g++ options: -O3 -fPIC -lm
Apache HBase Rows: 10000 - Test: Random Read - Clients: 1 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.5.0 Rows: 10000 - Test: Random Read - Clients: 1 EPYC 9654 2P AMD EPYC 75F3 32-Core 75F32 40 80 120 160 200 142 186 189
Apache HBase Rows: 10000 - Test: Random Read - Clients: 1 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.5.0 Rows: 10000 - Test: Random Read - Clients: 1 EPYC 9654 2P AMD EPYC 75F3 32-Core 75F32 1400 2800 4200 5600 7000 6698 5189 5071
SMHasher Hash: wyhash OpenBenchmarking.org MiB/sec, More Is Better SMHasher 2022-08-22 Hash: wyhash EPYC 9654 2P - Perf M EPYC 9654 2P Repeat 9654 Power EPYC 9654 2P EPYC 9654 Repeat EPYC 9654 EPYC 9654 Power 8380 2p EPYC 9554 9554 TwoP 7K 14K 21K 28K 35K 31248.91 31247.36 31245.47 31218.05 31201.20 31198.52 31197.92 27859.54 24509.44 24475.93 1. (CXX) g++ options: -march=native -O3 -flto=auto -fno-fat-lto-objects
SMHasher Hash: wyhash OpenBenchmarking.org cycles/hash, Fewer Is Better SMHasher 2022-08-22 Hash: wyhash EPYC 9654 2P Repeat EPYC 9654 EPYC 9654 Repeat EPYC 9654 Power 9654 Power EPYC 9654 2P EPYC 9654 2P - Perf M EPYC 9554 9554 TwoP 8380 2p 5 10 15 20 25 13.97 13.97 13.97 13.97 13.98 13.99 14.22 18.09 18.19 19.63 1. (CXX) g++ options: -march=native -O3 -flto=auto -fno-fat-lto-objects
libavif avifenc Encoder Speed: 10, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 10, Lossless EPYC 9654 Power 9654 Power EPYC 9554 EPYC 9654 EPYC 9654 2P - Perf M 9554 TwoP EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 Repeat AMD EPYC 75F3 32-Core 75F32 8380 2p 1.3064 2.6128 3.9192 5.2256 6.532 4.078 4.099 4.106 4.124 4.244 4.250 4.288 4.322 4.427 4.725 4.945 5.806 1. (CXX) g++ options: -O3 -fPIC -lm
Apache HBase Rows: 10000 - Test: Random Write - Clients: 1 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.5.0 Rows: 10000 - Test: Random Write - Clients: 1 AMD EPYC 75F3 32-Core 75F32 EPYC 9654 2P 8 16 24 32 40 34 34 36
Apache HBase Rows: 10000 - Test: Random Write - Clients: 1 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.5.0 Rows: 10000 - Test: Random Write - Clients: 1 75F32 AMD EPYC 75F3 32-Core EPYC 9654 2P 6K 12K 18K 24K 30K 27027 26954 25907
x264 Video Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better x264 2022-02-22 Video Input: Bosphorus 1080p EPYC 9654 2P Repeat EPYC 9654 Repeat 9554 TwoP EPYC 9654 Power 75F32 EPYC 9654 AMD EPYC 75F3 32-Core EPYC 9654 2P - Perf M 8380 2p 60 120 180 240 300 265.96 265.77 262.79 221.25 217.75 211.70 205.05 200.65 193.65 1. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -flto
libavif avifenc Encoder Speed: 6 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 6 EPYC 9654 9654 Power EPYC 9654 Power EPYC 9654 Repeat EPYC 9554 9554 TwoP EPYC 9654 2P Repeat EPYC 9654 2P EPYC 9654 2P - Perf M AMD EPYC 75F3 32-Core 75F32 8380 2p 0.7571 1.5142 2.2713 3.0284 3.7855 2.290 2.297 2.311 2.321 2.342 2.404 2.415 2.422 2.422 3.265 3.304 3.365 1. (CXX) g++ options: -O3 -fPIC -lm
Phoronix Test Suite v10.8.4