EPYC 7F72

2 x AMD EPYC 7F72 24-Core testing with a Supermicro H11DSi-NT v2.00 (2.1 BIOS) and ASPEED on Ubuntu 20.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2012196-HA-EPYC7F72759&sro&grs.

EPYC 7F72ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionEPYC 7F72AMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72 2P7F72 2PAMD EPYC 7F72 24-Core @ 3.20GHz (24 Cores / 48 Threads)Supermicro H11DSi-NT v2.00 (2.1 BIOS)AMD Starship/Matisse64GB1000GB Western Digital WD_BLACK SN850 1TBllvmpipeVE2282 x Intel 10G X550TUbuntu 20.105.8.0-29-generic (x86_64)GNOME Shell 3.38.1X Server 1.20.9modesetting 1.20.94.5 Mesa 20.2.1 (LLVM 11.0.0 256 bits)GCC 10.2.0ext41920x10802 x AMD EPYC 7F72 24-Core @ 3.20GHz (48 Cores / 96 Threads)126GBASPEEDOpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,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-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/usr,hsa --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 Disk Details- NONE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Details- Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8301034Python Details- Python 3.8.6Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

EPYC 7F72onednn: IP Shapes 3D - f32 - CPUhpcc: Rand Ring Bandwidthonednn: Convolution Batch Shapes Auto - f32 - CPUleveldb: Rand Deleteleveldb: Seq Fillleveldb: Overwriteleveldb: Rand Fillonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUleveldb: Seek Randleveldb: Rand Readleveldb: Hot Readpgbench: 1 - 100 - Read Onlypgbench: 1 - 100 - Read Only - Average Latencyhpcg: namd: ATPase Simulation - 327,506 Atomslammps: Rhodopsin Proteinbrl-cad: VGR Performance Metricgromacs: Water Benchmarkstockfish: Total Timeasmfish: 1024 Hash Memory, 26 Depthhpcc: Rand Ring Latencyffte: N=256, 3D Complex FFT Routineyquake2: Software CPU - 1920 x 1080leveldb: Seq Fillleveldb: Overwriteonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUleveldb: Rand Fillonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUlammps: 20k Atomskvazaar: Bosphorus 1080p - Slowtensorflow-lite: Inception ResNet V2kvazaar: Bosphorus 1080p - Mediumbasis: UASTC Level 3tensorflow-lite: Inception V4kvazaar: Bosphorus 1080p - Very Fastbuild-linux-kernel: Time To Compileonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUtensorflow-lite: Mobilenet Floatkvazaar: Bosphorus 4K - Slowkvazaar: Bosphorus 4K - Mediumtensorflow-lite: Mobilenet Quantleveldb: Fill Synconednn: IP Shapes 1D - u8s8f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUhpcc: G-Rand Accesskeydb: kvazaar: Bosphorus 4K - Very Fastai-benchmark: Device Training Scoretensorflow-lite: NASNet Mobilebuild-llvm: Time To Compiletensorflow-lite: SqueezeNetonednn: IP Shapes 3D - u8s8f32 - CPUleveldb: Fill Synconednn: Recurrent Neural Network Training - f32 - CPUmlpack: scikit_qdapgbench: 100 - 100 - Read Only - Average Latencypgbench: 100 - 100 - Read Onlybasis: UASTC Level 2onednn: Deconvolution Batch shapes_3d - f32 - CPUhmmer: Pfam Database Searchai-benchmark: Device AI Scorekvazaar: Bosphorus 1080p - Ultra Fastinfluxdb: 4 - 10000 - 2,5000,1 - 10000kvazaar: Bosphorus 4K - Ultra Fastai-benchmark: Device Inference Scorex265: Bosphorus 4Khugin: Panorama Photo Assistant + Stitching Timehpcc: G-HPLpgbench: 100 - 50 - Read Only - Average Latencypgbench: 100 - 50 - Read Onlyonednn: IP Shapes 1D - f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUlibraw: Post-Processing Benchmarkx265: Bosphorus 1080pmlpack: scikit_linearridgeregressiononednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUtnn: CPU - MobileNet v2hpcc: EP-STREAM Triadx264: H.264 Video Encodinghpcc: EP-DGEMMpgbench: 100 - 50 - Read Write - Average Latencypgbench: 100 - 50 - Read Writepgbench: 1 - 50 - Read Write - Average Latencypgbench: 1 - 50 - Read Writeonednn: Deconvolution Batch shapes_1d - f32 - CPUpgbench: 100 - 100 - Read Write - Average Latencypgbench: 100 - 100 - Read Writepgbench: 1 - 100 - Read Writepgbench: 1 - 100 - Read Write - Average Latencypgbench: 1 - 50 - Read Onlypgbench: 1 - 50 - Read Only - Average Latencypgbench: 100 - 1 - Read Onlybasis: ETC1Spgbench: 100 - 1 - Read Only - Average Latencybuild-clash: Time To Compilemlpack: scikit_icarav1e: 10influxdb: 64 - 10000 - 2,5000,1 - 10000compress-lz4: 9 - Compression Speedcompress-lz4: 3 - Compression Speedbasis: UASTC Level 0pgbench: 1 - 1 - Read Only - Average Latencycompress-lz4: 3 - Decompression Speedbyte: Dhrystone 2pgbench: 1 - 1 - Read Onlycompress-lz4: 1 - Decompression Speedpgbench: 100 - 1 - Read Write - Average Latencymlpack: scikit_svmpgbench: 100 - 1 - Read Writewebp: Quality 100, Losslesscompress-lz4: 9 - Decompression Speedrav1e: 5rav1e: 6numpy: rav1e: 1phpbench: PHP Benchmark Suitecompress-lz4: 1 - Compression Speedpgbench: 1 - 1 - Read Write - Average Latencypgbench: 1 - 1 - Read Writebasis: UASTC Level 2 + RDO Post-Processingwebp: Quality 100webp: Quality 100, Lossless, Highest Compressioncrafty: Elapsed Timewebp: Defaulttnn: CPU - SqueezeNet v1.1webp: Quality 100, Highest Compressionhint: FLOATrnnoise: espeak: Text-To-Speech Synthesisindigobench: CPU - Supercarindigobench: CPU - Bedroomncnn: CPU - yolov4-tinyncnn: CPU - resnet50ncnn: CPU - alexnetncnn: CPU - resnet18ncnn: CPU - vgg16ncnn: CPU - googlenetncnn: CPU - blazefacencnn: CPU - efficientnet-b0ncnn: CPU - mnasnetncnn: CPU - shufflenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - mobilenetncnn: CPU - squeezenetredis: SETredis: GETredis: LPUSHredis: SADDredis: LPOPonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUhpcc: Max Ping Pong Bandwidthhpcc: G-Ptranshpcc: G-FfteEPYC 7F72AMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72 2P7F72 2P2.778152.710762.84936209.853220.327229.121228.0386.3772564.33739.86739.7726984520.14314.99950.8816912.1293379242.84752597544643498371.16869111181.7368531014.524.123.12.3096123.31.4023515.78936.21117566337.1427.182134287783.0638.8635.3032060165.310.7310.9561482.04.51.437821616.570.03144424090.9624.001513104517298.14589588.10.5928041168.5801611.2140.050.18952931816.9013.15047142.1153473142.441197999.841.99196023.5350.00687.254500.0915516231.73051934.68635.1160.611.610.578226295.1933.11627178.7936.141002.3292147920.66324212.359463.39529486214546.6838472310.0592433649.3600.041462.28351.743.0391339487.549.7050.787.5780.03410606.337455257.22941911308.90.55424.45180519.04210630.91.0371.385324.130.3495687969777.430.4952019694.8692.59639.28074063091.611275.5228.538321206770.0579421.13732.79510.3094.76931.0524.9510.3813.8236.4822.074.0912.299.5810.459.5210.0421.4421.261495615.592038392.691295998.651658090.042134890.15931.2751613.91925.9769566.4967.757399.872382.750042.725152.90342210.651220.804228.697228.6076.4139063.75140.38340.9906987780.14314.97310.8753211.7003323942.83053421517644487411.16276111004.6587361123.724.023.22.3063323.21.3865115.81636.09117991336.9727.287134740082.4639.0545.3595059959.610.7010.9161260.74.51.426451606.750.03051426284.5723.981523103641289.65489393.60.8390251163.4551613.7039.490.18953058116.9803.14499142.1313532141.931199592.442.13200923.5950.32587.310770.0905553201.73388930.71135.0160.331.590.575254292.9013.38220177.8636.765532.3242152120.57124312.341523.38929537214446.6948526120.0592434549.5110.041462.32351.823.0321339130.148.3350.547.7330.03410661.537547272.92939111271.40.55624.49180119.01810616.01.0361.386321.810.3495678979740.160.4932027693.8972.58539.17073829161.602275.7038.549321880722.6368921.12632.75910.3394.77531.3324.5310.5113.8636.5621.554.1312.619.5110.359.6110.0622.2621.101500640.311814383.801332610.561757206.721376509.23924.0241610.95930.71410110.2598.175538.431212.782142.730352.83648210.334220.867228.708228.3176.3288464.87140.03040.6236953440.14415.44510.8927711.7053418852.84652704023635647661.15717113220.1974780814.524.023.22.2967223.21.4034615.77936.15117859037.0827.210134489383.2938.9035.3633060331.610.7310.9261596.24.51.426691602.590.03037424640.3023.931520104362294.11389812.70.5917021162.7141611.7439.860.18952906616.9263.13878142.0803527142.031197198.042.17200723.6050.46186.882970.0915514841.72765928.11534.9660.251.620.576657294.6533.29923177.7136.438802.3282148120.63024242.357263.38829552214246.7428420220.0592444649.5790.041461.62451.843.0261297582.548.9849.317.6060.03410548.837624546.92946211314.60.55325.02180719.01510685.71.0371.385318.470.3465735679780.380.4982009694.9952.59139.34273592171.612275.3818.548322432634.1313221.16832.71110.3144.77030.7525.0310.5214.1037.4822.014.1612.549.5010.459.9410.0822.2021.871475849.681897703.881317592.971723521.291379285.46932.4891605.90929.88610456.2868.285559.418950.7846520.801670.860679690.963707.544736.377731.8762.02580191.741114.896112.49714132470.07130.35370.4465122.5656324955.287982324881153985502.02418186579.066906911514.41.4367114.50.88175224.92456.4675856657.5617.658871018126.2425.6965.4922040228.615.9016.1941754.26.62.072471109.290.04383296614.5434.381063117648209.24763691.30.7423231594.9371177.1254.560.14170823412.3912.31947187.8912725181.72951085.753.26166220.4356.785100.700330.0816192191.55767838.99031.4254.701.780.518269316.8233.41432194.1939.200302.1402337322.34322392.305643.61227730202049.5658167560.0612317151.9040.043483.40451.722.9721328030.948.2149.947.7460.03510360.538124375.52868111021.80.56124.61178419.01010448.21.0361.378318.080.3485729059657.040.4962016687.0842.57339.01374176211.611274.3278.514322779429.0787421.12032.79945.7846.8911.0721.2454.1942.9511.4040.1836.4531.5331.7333.1846.4668.431498592.431888968.341365777.401818648.351388985.48839.8521201.41823.74511661.77615.9182320.857700.8163060.826490.868864690.868710.333736.558734.8181.99172191.127112.076112.69514072710.07130.18600.4464222.3856386635.278975827531165249542.05512185994.0960317514.914.41.4684114.50.89033324.92056.2975490657.3717.601872809126.7925.7964.8752340591.015.9416.1341926.26.52.030421222.200.04396301799.8834.311078115976212.02463239.20.7522901630.9361166.5654.180.14071504512.4142.36572186.3962773180.39949471.853.22169520.2056.426100.371670.0806255121.52395827.22331.1454.631.750.529186299.4473.42379193.4039.029402.1642312121.91722822.262693.61427720200749.8767975660.0632329551.8540.043483.96453.022.9671345908.148.8349.677.8080.03410409.937519864.52925711114.30.55824.51179418.76810473.31.0301.369322.490.3465777969652.000.5002001689.4712.58039.27474190021.604274.1298.523322198292.3995521.08032.83950.9244.5510.8930.4855.5540.6510.8447.1533.4529.7332.1832.6347.4439.161580536.811996216.741368468.711814208.701380069.40822.7711182.17848.2499370.09816.4567320.629570.8917760.802610.928138670.018702.123737.227733.8192.10700189.297113.380112.40413884650.07228.11610.4547519.9626297065.251973765951161892322.04033163435.0163233215.114.41.5012014.50.95990424.54956.4382311257.3117.704963296126.8825.9503.6506245501.815.8316.0449006.26.42.090221407.980.04279308314.4533.841075148263211.78776438.60.7921531643.4901290.0751.460.13772909312.4212.30768188.2622729181.26944430.652.76165419.9958.65999.064700.0796336361.67289873.59031.9353.831.700.567497322.3023.21782194.9735.913872.1412336021.98122762.445383.63927520200250.0068254480.0612339652.0490.043482.27553.732.9271337280.448.0849.247.7890.03410402.738477706.32945211168.70.56624.55176619.19810602.41.0161.358320.650.3435728339632.390.4982007689.7992.58339.35273859931.611274.4508.556322561482.0050821.13932.82949.6256.4812.1424.8069.5657.4613.1643.8639.1232.4733.5034.7060.7843.061519952.931852789.071345722.501784823.371508834.92882.0551334.58907.0718695.06216.1235720.07943OpenBenchmarking.org

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.6261.2521.8782.5043.13SE +/- 0.008788, N = 3SE +/- 0.017798, N = 3SE +/- 0.013730, N = 3SE +/- 0.007882, N = 6SE +/- 0.011681, N = 3SE +/- 0.009922, N = 30.8917762.7500402.7821400.7846522.7781500.816306MIN: 0.72MIN: 2.48MIN: 2.48MIN: 0.67MIN: 2.48MIN: 0.691. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

HPC Challenge

Test / Class: Random Ring Bandwidth

OpenBenchmarking.orgGB/s, More Is BetterHPC Challenge 1.5.0Test / Class: Random Ring Bandwidth7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.61431.22861.84292.45723.0715SE +/- 0.00700, N = 3SE +/- 0.06549, N = 3SE +/- 0.03283, N = 3SE +/- 0.00576, N = 3SE +/- 0.01911, N = 3SE +/- 0.02292, N = 30.802612.725152.730350.801672.710760.826491. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 4.0.3

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.65331.30661.95992.61323.2665SE +/- 0.005045, N = 3SE +/- 0.008767, N = 3SE +/- 0.018414, N = 3SE +/- 0.011932, N = 3SE +/- 0.008471, N = 3SE +/- 0.002168, N = 30.9281382.9034202.8364800.8606792.8493600.868864MIN: 0.79MIN: 2.52MIN: 2.45MIN: 0.79MIN: 2.46MIN: 0.791. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

LevelDB

Benchmark: Random Delete

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random Delete7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P150300450600750SE +/- 3.35, N = 3SE +/- 0.41, N = 3SE +/- 0.20, N = 3SE +/- 1.87, N = 3SE +/- 0.57, N = 3SE +/- 7.14, N = 3670.02210.65210.33690.96209.85690.871. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Sequential Fill

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Sequential Fill7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P150300450600750SE +/- 2.29, N = 3SE +/- 0.58, N = 3SE +/- 0.16, N = 3SE +/- 0.53, N = 3SE +/- 0.18, N = 3SE +/- 2.35, N = 3702.12220.80220.87707.54220.33710.331. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Overwrite

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Overwrite7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P160320480640800SE +/- 0.43, N = 3SE +/- 0.71, N = 3SE +/- 0.57, N = 3SE +/- 1.17, N = 3SE +/- 0.36, N = 3SE +/- 0.59, N = 3737.23228.70228.71736.38229.12736.561. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Random Fill

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random Fill7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P160320480640800SE +/- 3.93, N = 3SE +/- 0.18, N = 3SE +/- 0.12, N = 3SE +/- 1.35, N = 3SE +/- 0.24, N = 3SE +/- 2.04, N = 3733.82228.61228.32731.88228.04734.821. (CXX) g++ options: -O3 -lsnappy -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P246810SE +/- 0.01009, N = 3SE +/- 0.01141, N = 3SE +/- 0.03710, N = 3SE +/- 0.01946, N = 3SE +/- 0.00849, N = 3SE +/- 0.01945, N = 32.107006.413906.328842.025806.377251.99172MIN: 1.86MIN: 5.78MIN: 5.76MIN: 1.87MIN: 5.79MIN: 1.861. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

LevelDB

Benchmark: Seek Random

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Seek Random7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P4080120160200SE +/- 0.57, N = 3SE +/- 0.14, N = 3SE +/- 0.52, N = 3SE +/- 1.65, N = 3SE +/- 0.66, N = 3SE +/- 0.59, N = 3189.3063.7564.87191.7464.34191.131. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Random Read

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random Read7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P306090120150SE +/- 1.08, N = 15SE +/- 0.44, N = 4SE +/- 0.21, N = 3SE +/- 1.04, N = 15SE +/- 0.18, N = 3SE +/- 0.91, N = 3113.3840.3840.03114.9039.87112.081. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Hot Read

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot Read7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P306090120150SE +/- 1.40, N = 3SE +/- 0.50, N = 4SE +/- 0.14, N = 3SE +/- 1.04, N = 15SE +/- 0.13, N = 3SE +/- 1.54, N = 3112.4040.9940.62112.5039.77112.701. (CXX) g++ options: -O3 -lsnappy -lpthread

PostgreSQL pgbench

Scaling Factor: 1 - Clients: 100 - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 100 - Mode: Read Only7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P300K600K900K1200K1500KSE +/- 12723.13, N = 3SE +/- 755.05, N = 3SE +/- 1176.24, N = 3SE +/- 18458.00, N = 3SE +/- 1961.28, N = 3SE +/- 10614.63, N = 121388465698778695344141324769845214072711. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL pgbench

Scaling Factor: 1 - Clients: 100 - Mode: Read Only - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 100 - Mode: Read Only - Average Latency7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.03240.06480.09720.12960.162SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 120.0720.1430.1440.0710.1430.0711. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

High Performance Conjugate Gradient

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.17F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P714212835SE +/- 0.41, N = 12SE +/- 0.32, N = 12SE +/- 0.17, N = 3SE +/- 0.30, N = 3SE +/- 0.25, N = 12SE +/- 0.02, N = 328.1214.9715.4530.3515.0030.191. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 Atoms7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.20090.40180.60270.80361.0045SE +/- 0.00250, N = 3SE +/- 0.00402, N = 3SE +/- 0.01077, N = 3SE +/- 0.00014, N = 3SE +/- 0.00562, N = 3SE +/- 0.00027, N = 30.454750.875320.892770.446510.881690.44642

LAMMPS Molecular Dynamics Simulator

Model: Rhodopsin Protein

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: Rhodopsin Protein7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P510152025SE +/- 0.22, N = 5SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.43, N = 15SE +/- 0.08, N = 3SE +/- 0.25, N = 319.9611.7011.7122.5712.1322.391. (CXX) g++ options: -O3 -pthread -lm

BRL-CAD

VGR Performance Metric

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.30.8VGR Performance Metric7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P140K280K420K560K700K6297063323943418856324953379246386631. (CXX) g++ options: -std=c++11 -pipe -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -rdynamic -lSM -lICE -lXi -lGLU -lGL -lGLdispatch -lX11 -lXext -lXrender -lpthread -ldl -luuid -lm

GROMACS

Water Benchmark

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.3Water Benchmark7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1.18962.37923.56884.75845.948SE +/- 0.007, N = 3SE +/- 0.009, N = 3SE +/- 0.003, N = 3SE +/- 0.004, N = 3SE +/- 0.004, N = 3SE +/- 0.007, N = 35.2512.8302.8465.2872.8475.2781. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm

Stockfish

Total Time

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 12Total Time7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P20M40M60M80M100MSE +/- 639295.30, N = 3SE +/- 678703.71, N = 3SE +/- 356097.54, N = 15SE +/- 946054.05, N = 3SE +/- 458927.44, N = 15SE +/- 724949.76, N = 39737659553421517527040239823248852597544975827531. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++17 -pedantic -O3 -msse -msse3 -mpopcnt -msse4.1 -mssse3 -msse2 -flto -flto=jobserver

asmFish

1024 Hash Memory, 26 Depth

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 Depth7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P20M40M60M80M100MSE +/- 1665400.53, N = 3SE +/- 380311.53, N = 3SE +/- 644607.06, N = 3SE +/- 412071.14, N = 3SE +/- 282969.84, N = 3SE +/- 422109.99, N = 3116189232644487416356476611539855064349837116524954

HPC Challenge

Test / Class: Random Ring Latency

OpenBenchmarking.orgusecs, Fewer Is BetterHPC Challenge 1.5.0Test / Class: Random Ring Latency7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.46240.92481.38721.84962.312SE +/- 0.01822, N = 3SE +/- 0.01886, N = 3SE +/- 0.01464, N = 3SE +/- 0.01426, N = 3SE +/- 0.00865, N = 3SE +/- 0.03528, N = 32.040331.162761.157172.024181.168692.055121. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 4.0.3

FFTE

N=256, 3D Complex FFT Routine

OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 7.0N=256, 3D Complex FFT Routine7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P40K80K120K160K200KSE +/- 2147.54, N = 15SE +/- 1197.97, N = 4SE +/- 1183.24, N = 3SE +/- 2264.92, N = 4SE +/- 1183.09, N = 3SE +/- 2641.44, N = 3163435.02111004.66113220.20186579.07111181.74185994.101. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp

yquake2

Renderer: Software CPU - Resolution: 1920 x 1080

OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 7.45Renderer: Software CPU - Resolution: 1920 x 1080AMD 7F72AMD EPYC 7F72EPYC 7F72612182430SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 323.714.514.51. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC

LevelDB

Benchmark: Sequential Fill

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Sequential Fill7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P612182430SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.07, N = 315.124.024.015.024.114.91. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Overwrite

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Overwrite7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P612182430SE +/- 0.00, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 314.423.223.214.423.114.41. (CXX) g++ options: -O3 -lsnappy -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.51971.03941.55912.07882.5985SE +/- 0.01121, N = 15SE +/- 0.00978, N = 3SE +/- 0.00103, N = 3SE +/- 0.00707, N = 3SE +/- 0.00115, N = 3SE +/- 0.01842, N = 151.501202.306332.296721.436712.309611.46841MIN: 1.27MIN: 2.18MIN: 2.18MIN: 1.28MIN: 2.18MIN: 1.271. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

LevelDB

Benchmark: Random Fill

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Random Fill7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P612182430SE +/- 0.07, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 314.523.223.214.523.314.51. (CXX) g++ options: -O3 -lsnappy -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.31580.63160.94741.26321.579SE +/- 0.007240, N = 3SE +/- 0.005378, N = 3SE +/- 0.005195, N = 3SE +/- 0.004844, N = 3SE +/- 0.009113, N = 3SE +/- 0.001013, N = 30.9599041.3865101.4034600.8817521.4023500.890333MIN: 0.84MIN: 1.29MIN: 1.29MIN: 0.83MIN: 1.29MIN: 0.841. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

LAMMPS Molecular Dynamics Simulator

Model: 20k Atoms

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: 20k Atoms7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P612182430SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 324.5515.8215.7824.9215.7924.921. (CXX) g++ options: -O3 -pthread -lm

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Slow

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Slow7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1326395265SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 356.4336.0936.1556.4636.2156.291. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

TensorFlow Lite

Model: Inception ResNet V2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V27F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P300K600K900K1200K1500KSE +/- 7122.24, N = 3SE +/- 2105.81, N = 3SE +/- 3330.08, N = 3SE +/- 2776.56, N = 3SE +/- 2727.68, N = 3SE +/- 2200.08, N = 3823112117991311785907585661175663754906

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Medium

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Medium7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1326395265SE +/- 0.18, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.18, N = 357.3136.9737.0857.5637.1457.371. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Basis Universal

Settings: UASTC Level 3

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 37F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P612182430SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 317.7027.2927.2117.6627.1817.601. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

TensorFlow Lite

Model: Inception V4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V47F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P300K600K900K1200K1500KSE +/- 8354.40, N = 15SE +/- 2838.53, N = 3SE +/- 3249.51, N = 3SE +/- 2614.29, N = 3SE +/- 3318.77, N = 3SE +/- 3825.03, N = 3963296134740013448938710181342877872809

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Very Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Very Fast7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P306090120150SE +/- 0.61, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.48, N = 3SE +/- 0.22, N = 3SE +/- 0.83, N = 3126.8882.4683.29126.2483.06126.791. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To Compile7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P918273645SE +/- 0.16, N = 13SE +/- 0.41, N = 5SE +/- 0.37, N = 6SE +/- 0.16, N = 13SE +/- 0.47, N = 3SE +/- 0.16, N = 1325.9539.0538.9025.7038.8625.80

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1.23572.47143.70714.94286.1785SE +/- 0.04554, N = 3SE +/- 0.02370, N = 3SE +/- 0.03533, N = 3SE +/- 0.51653, N = 14SE +/- 0.01527, N = 3SE +/- 0.48144, N = 123.650625.359505.363305.492205.303204.87523MIN: 2.99MIN: 4.96MIN: 4.96MIN: 2.85MIN: 4.97MIN: 2.891. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

TensorFlow Lite

Model: Mobilenet Float

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Float7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P13K26K39K52K65KSE +/- 394.42, N = 3SE +/- 39.74, N = 3SE +/- 126.43, N = 3SE +/- 154.16, N = 3SE +/- 43.27, N = 3SE +/- 383.17, N = 345501.859959.660331.640228.660165.340591.0

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Slow

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Slow7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P48121620SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 315.8310.7010.7315.9010.7315.941. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Medium

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Medium7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P48121620SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 316.0410.9110.9216.1910.9516.131. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

TensorFlow Lite

Model: Mobilenet Quant

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Quant7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P13K26K39K52K65KSE +/- 959.33, N = 15SE +/- 111.88, N = 3SE +/- 119.05, N = 3SE +/- 394.63, N = 3SE +/- 90.15, N = 3SE +/- 228.51, N = 349006.261260.761596.241754.261482.041926.2

LevelDB

Benchmark: Fill Sync

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Fill Sync7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P246810SE +/- 0.09, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.07, N = 15SE +/- 0.00, N = 3SE +/- 0.06, N = 86.44.54.56.64.56.51. (CXX) g++ options: -O3 -lsnappy -lpthread

oneDNN

Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.47030.94061.41091.88122.3515SE +/- 0.01869, N = 7SE +/- 0.00516, N = 3SE +/- 0.00056, N = 3SE +/- 0.02566, N = 4SE +/- 0.00957, N = 3SE +/- 0.01974, N = 62.090221.426451.426692.072471.437822.03042MIN: 1.74MIN: 1.33MIN: 1.32MIN: 1.66MIN: 1.33MIN: 1.661. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P30060090012001500SE +/- 42.19, N = 15SE +/- 2.70, N = 3SE +/- 2.00, N = 3SE +/- 0.72, N = 3SE +/- 3.74, N = 3SE +/- 43.23, N = 121407.981606.751602.591109.291616.571222.20MIN: 1169.39MIN: 1564.52MIN: 1564.17MIN: 1072.44MIN: 1572.33MIN: 1075.031. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

HPC Challenge

Test / Class: G-Random Access

OpenBenchmarking.orgGUP/s, More Is BetterHPC Challenge 1.5.0Test / Class: G-Random Access7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.00990.01980.02970.03960.0495SE +/- 0.00060, N = 3SE +/- 0.00105, N = 3SE +/- 0.00070, N = 3SE +/- 0.00017, N = 3SE +/- 0.00015, N = 3SE +/- 0.00002, N = 30.042790.030510.030370.043830.031440.043961. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 4.0.3

KeyDB

OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 6.0.167F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P90K180K270K360K450KSE +/- 3846.80, N = 3SE +/- 4696.92, N = 3SE +/- 2330.52, N = 3SE +/- 2893.10, N = 15SE +/- 1068.73, N = 3SE +/- 3213.58, N = 5308314.45426284.57424640.30296614.54424090.96301799.881. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Very Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Very Fast7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P816243240SE +/- 0.11, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.11, N = 333.8423.9823.9334.3824.0034.311. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

AI Benchmark Alpha

Device Training Score

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Training Score7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P30060090012001500107515231520106315131078

TensorFlow Lite

Model: NASNet Mobile

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet Mobile7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P30K60K90K120K150KSE +/- 6473.79, N = 15SE +/- 239.98, N = 3SE +/- 60.45, N = 3SE +/- 1327.95, N = 15SE +/- 165.43, N = 3SE +/- 1433.11, N = 15148263103641104362117648104517115976

Timed LLVM Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 10.0Time To Compile7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P60120180240300SE +/- 2.37, N = 3SE +/- 2.80, N = 3SE +/- 4.06, N = 3SE +/- 1.26, N = 3SE +/- 1.69, N = 3SE +/- 0.63, N = 3211.79289.65294.11209.25298.15212.02

TensorFlow Lite

Model: SqueezeNet

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNet7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P20K40K60K80K100KSE +/- 1496.92, N = 15SE +/- 45.73, N = 3SE +/- 87.10, N = 3SE +/- 717.51, N = 4SE +/- 44.82, N = 3SE +/- 386.78, N = 376438.689393.689812.763691.389588.163239.2

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.18880.37760.56640.75520.944SE +/- 0.001315, N = 3SE +/- 0.017578, N = 12SE +/- 0.000920, N = 3SE +/- 0.002965, N = 3SE +/- 0.002974, N = 3SE +/- 0.009511, N = 30.7921530.8390250.5917020.7423230.5928040.752290MIN: 0.66MIN: 0.64MIN: 0.5MIN: 0.67MIN: 0.51MIN: 0.671. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

LevelDB

Benchmark: Fill Sync

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Fill Sync7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P400800120016002000SE +/- 19.99, N = 3SE +/- 4.35, N = 3SE +/- 8.92, N = 3SE +/- 17.18, N = 15SE +/- 2.23, N = 3SE +/- 15.97, N = 81643.491163.461162.711594.941168.581630.941. (CXX) g++ options: -O3 -lsnappy -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P30060090012001500SE +/- 11.72, N = 3SE +/- 10.75, N = 3SE +/- 3.90, N = 3SE +/- 20.62, N = 14SE +/- 2.75, N = 3SE +/- 20.53, N = 151290.071613.701611.741177.121611.211166.56MIN: 1195.72MIN: 1565.85MIN: 1572.94MIN: 1074.6MIN: 1572.74MIN: 1069.011. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Mlpack Benchmark

Benchmark: scikit_qda

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qda7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1224364860SE +/- 0.53, N = 15SE +/- 0.18, N = 3SE +/- 0.31, N = 10SE +/- 0.64, N = 15SE +/- 0.08, N = 3SE +/- 0.47, N = 1551.4639.4939.8654.5640.0554.18

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.04250.0850.12750.170.2125SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.002, N = 50.1370.1890.1890.1410.1890.1401. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 100 - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 100 - Mode: Read Only7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P160K320K480K640K800KSE +/- 4479.87, N = 3SE +/- 493.86, N = 3SE +/- 613.62, N = 3SE +/- 2733.07, N = 3SE +/- 602.59, N = 3SE +/- 7684.00, N = 57290935305815290667082345293187150451. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Basis Universal

Settings: UASTC Level 2

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 27F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P48121620SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 312.4216.9816.9312.3916.9012.411. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.70891.41782.12672.83563.5445SE +/- 0.03863, N = 15SE +/- 0.01746, N = 3SE +/- 0.01523, N = 3SE +/- 0.05452, N = 12SE +/- 0.01172, N = 3SE +/- 0.02839, N = 32.307683.144993.138782.319473.150472.36572MIN: 1.95MIN: 2.97MIN: 2.98MIN: 1.96MIN: 2.98MIN: 2.011. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Timed HMMer Search

Pfam Database Search

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.1Pfam Database Search7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P4080120160200SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.14, N = 3SE +/- 0.64, N = 3SE +/- 0.11, N = 3SE +/- 0.78, N = 3188.26142.13142.08187.89142.12186.401. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm

AI Benchmark Alpha

Device AI Score

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device AI Score7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P8001600240032004000272935323527272534732773

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Ultra Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Ultra Fast7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P4080120160200SE +/- 0.82, N = 3SE +/- 0.44, N = 3SE +/- 0.12, N = 3SE +/- 1.83, N = 6SE +/- 0.27, N = 3SE +/- 1.97, N = 3181.26141.93142.03181.72142.44180.391. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

InfluxDB

Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 100007F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P300K600K900K1200K1500KSE +/- 2635.14, N = 3SE +/- 3879.14, N = 3SE +/- 2015.92, N = 3SE +/- 941.41, N = 3SE +/- 2428.05, N = 3SE +/- 288.02, N = 3944430.61199592.41197198.0951085.71197999.8949471.8

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Ultra Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Ultra Fast7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1224364860SE +/- 0.37, N = 3SE +/- 0.07, N = 3SE +/- 0.16, N = 3SE +/- 0.22, N = 3SE +/- 0.07, N = 3SE +/- 0.48, N = 352.7642.1342.1753.2641.9953.221. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

AI Benchmark Alpha

Device Inference Score

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Inference Score7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P400800120016002000165420092007166219601695

x265

Video Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4K7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P612182430SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 319.9923.5923.6020.4323.5320.201. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Hugin

Panorama Photo Assistant + Stitching Time

OpenBenchmarking.orgSeconds, Fewer Is BetterHuginPanorama Photo Assistant + Stitching Time7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1326395265SE +/- 0.73, N = 3SE +/- 0.39, N = 3SE +/- 0.24, N = 3SE +/- 0.45, N = 3SE +/- 0.51, N = 3SE +/- 0.22, N = 358.6650.3350.4656.7950.0156.43

HPC Challenge

Test / Class: G-HPL

OpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.5.0Test / Class: G-HPL7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P20406080100SE +/- 0.20, N = 3SE +/- 0.30, N = 3SE +/- 0.42, N = 3SE +/- 0.04, N = 3SE +/- 0.39, N = 3SE +/- 0.10, N = 399.0687.3186.88100.7087.25100.371. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 4.0.3

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.02050.0410.06150.0820.1025SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 4SE +/- 0.001, N = 3SE +/- 0.001, N = 30.0790.0900.0910.0810.0910.0801. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 50 - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 50 - Mode: Read Only7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P140K280K420K560K700KSE +/- 6741.00, N = 3SE +/- 2634.03, N = 3SE +/- 1352.44, N = 3SE +/- 6778.87, N = 4SE +/- 5773.06, N = 3SE +/- 7480.51, N = 36336365553205514846192195516236255121. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.39010.78021.17031.56041.9505SE +/- 0.01869, N = 5SE +/- 0.01016, N = 3SE +/- 0.00210, N = 3SE +/- 0.01626, N = 5SE +/- 0.00365, N = 3SE +/- 0.01312, N = 31.672891.733881.727651.557671.730511.52395MIN: 1.31MIN: 1.57MIN: 1.58MIN: 1.3MIN: 1.58MIN: 1.31. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P2004006008001000SE +/- 12.96, N = 15SE +/- 2.82, N = 3SE +/- 3.30, N = 3SE +/- 25.26, N = 12SE +/- 2.42, N = 3SE +/- 20.75, N = 12873.59930.71928.12838.99934.69827.22MIN: 754.76MIN: 900MIN: 898.12MIN: 702.98MIN: 900.24MIN: 702.571. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

LibRaw

Post-Processing Benchmark

OpenBenchmarking.orgMpix/sec, More Is BetterLibRaw 0.20Post-Processing Benchmark7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P816243240SE +/- 0.18, N = 3SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.13, N = 3SE +/- 0.11, N = 3SE +/- 0.32, N = 331.9335.0134.9631.4235.1131.141. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm

x265

Video Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080p7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1428425670SE +/- 0.45, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.41, N = 11SE +/- 0.19, N = 3SE +/- 0.21, N = 353.8360.3360.2554.7060.6154.631. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Mlpack Benchmark

Benchmark: scikit_linearridgeregression

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregression7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.40050.8011.20151.6022.0025SE +/- 0.03, N = 15SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 14SE +/- 0.01, N = 3SE +/- 0.02, N = 151.701.591.621.781.611.75

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.13010.26020.39030.52040.6505SE +/- 0.004259, N = 15SE +/- 0.002676, N = 3SE +/- 0.001616, N = 3SE +/- 0.005740, N = 3SE +/- 0.001786, N = 3SE +/- 0.005785, N = 50.5674970.5752540.5766570.5182690.5782260.529186MIN: 0.43MIN: 0.52MIN: 0.52MIN: 0.43MIN: 0.52MIN: 0.431. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

TNN

Target: CPU - Model: MobileNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v27F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P70140210280350SE +/- 2.69, N = 15SE +/- 0.39, N = 3SE +/- 0.88, N = 3SE +/- 2.64, N = 3SE +/- 0.66, N = 3SE +/- 0.89, N = 3322.30292.90294.65316.82295.19299.45MIN: 284.29 / MAX: 478.05MIN: 281.47 / MAX: 324.04MIN: 281.79 / MAX: 332.39MIN: 284.59 / MAX: 461.35MIN: 281.63 / MAX: 334.08MIN: 284.3 / MAX: 463.881. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

HPC Challenge

Test / Class: EP-STREAM Triad

OpenBenchmarking.orgGB/s, More Is BetterHPC Challenge 1.5.0Test / Class: EP-STREAM Triad7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.77041.54082.31123.08163.852SE +/- 0.13098, N = 3SE +/- 0.00767, N = 3SE +/- 0.06266, N = 3SE +/- 0.01458, N = 3SE +/- 0.13922, N = 3SE +/- 0.00319, N = 33.217823.382203.299233.414323.116273.423791. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 4.0.3

x264

H.264 Video Encoding

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2019-12-17H.264 Video Encoding7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P4080120160200SE +/- 1.79, N = 6SE +/- 1.47, N = 3SE +/- 1.51, N = 3SE +/- 1.79, N = 12SE +/- 1.85, N = 3SE +/- 2.07, N = 5194.97177.86177.71194.19178.79193.401. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

HPC Challenge

Test / Class: EP-DGEMM

OpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.5.0Test / Class: EP-DGEMM7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P918273645SE +/- 0.19, N = 3SE +/- 0.85, N = 3SE +/- 0.48, N = 3SE +/- 0.14, N = 3SE +/- 0.60, N = 3SE +/- 0.36, N = 335.9136.7736.4439.2036.1439.031. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 4.0.3

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.5241.0481.5722.0962.62SE +/- 0.006, N = 3SE +/- 0.001, N = 3SE +/- 0.003, N = 3SE +/- 0.004, N = 3SE +/- 0.003, N = 3SE +/- 0.007, N = 32.1412.3242.3282.1402.3292.1641. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 50 - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 50 - Mode: Read Write7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P5K10K15K20K25KSE +/- 62.07, N = 3SE +/- 9.19, N = 3SE +/- 31.97, N = 3SE +/- 40.02, N = 3SE +/- 24.14, N = 3SE +/- 68.23, N = 32336021521214812337321479231211. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL pgbench

Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average Latency7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P510152025SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.11, N = 321.9820.5720.6322.3420.6621.921. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL pgbench

Scaling Factor: 1 - Clients: 50 - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read Write7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P5001000150020002500SE +/- 6.74, N = 3SE +/- 1.25, N = 3SE +/- 5.02, N = 3SE +/- 7.88, N = 3SE +/- 2.57, N = 3SE +/- 10.95, N = 32276243124242239242122821. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.55021.10041.65062.20082.751SE +/- 0.03614, N = 15SE +/- 0.02163, N = 3SE +/- 0.01986, N = 3SE +/- 0.03458, N = 12SE +/- 0.00293, N = 3SE +/- 0.02846, N = 152.445382.341522.357262.305642.359462.26269MIN: 1.83MIN: 2.1MIN: 2.1MIN: 1.86MIN: 2.12MIN: 1.861. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.81881.63762.45643.27524.094SE +/- 0.011, N = 3SE +/- 0.013, N = 3SE +/- 0.003, N = 3SE +/- 0.029, N = 3SE +/- 0.006, N = 3SE +/- 0.010, N = 33.6393.3893.3883.6123.3953.6141. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 100 - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 100 - Mode: Read Write7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P6K12K18K24K30KSE +/- 83.97, N = 3SE +/- 108.48, N = 3SE +/- 34.89, N = 3SE +/- 222.16, N = 3SE +/- 54.62, N = 3SE +/- 74.83, N = 32752029537295522773029486277201. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL pgbench

Scaling Factor: 1 - Clients: 100 - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 100 - Mode: Read Write7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P5001000150020002500SE +/- 2.35, N = 3SE +/- 6.61, N = 3SE +/- 3.93, N = 3SE +/- 4.42, N = 3SE +/- 4.79, N = 3SE +/- 2.08, N = 32002214421422020214520071. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL pgbench

Scaling Factor: 1 - Clients: 100 - Mode: Read Write - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 100 - Mode: Read Write - Average Latency7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1122334455SE +/- 0.06, N = 3SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.11, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 350.0146.6946.7449.5746.6849.881. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL pgbench

Scaling Factor: 1 - Clients: 50 - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read Only7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P200K400K600K800K1000KSE +/- 7882.33, N = 6SE +/- 4242.40, N = 3SE +/- 9353.87, N = 3SE +/- 1336.65, N = 3SE +/- 11183.06, N = 3SE +/- 7738.13, N = 38254488526128420228167568472317975661. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL pgbench

Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average Latency7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.01420.02840.04260.05680.071SE +/- 0.001, N = 6SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 30.0610.0590.0590.0610.0590.0631. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 1 - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 1 - Mode: Read Only7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P5K10K15K20K25KSE +/- 275.23, N = 15SE +/- 144.26, N = 3SE +/- 325.52, N = 3SE +/- 277.60, N = 3SE +/- 171.06, N = 3SE +/- 206.81, N = 152339624345244462317124336232951. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Basis Universal

Settings: ETC1S

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: ETC1S7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1224364860SE +/- 0.21, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.13, N = 3SE +/- 0.01, N = 3SE +/- 0.33, N = 352.0549.5149.5851.9049.3651.851. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 1 - Mode: Read Only - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 1 - Mode: Read Only - Average Latency7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.00970.01940.02910.03880.0485SE +/- 0.001, N = 15SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 150.0430.0410.0410.0430.0410.0431. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Timed Clash Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Clash CompilationTime To Compile7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P100200300400500SE +/- 4.35, N = 3SE +/- 1.06, N = 3SE +/- 0.52, N = 3SE +/- 1.18, N = 3SE +/- 0.12, N = 3SE +/- 1.97, N = 3482.28462.32461.62483.40462.28483.96

Mlpack Benchmark

Benchmark: scikit_ica

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_ica7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1224364860SE +/- 0.57, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.73, N = 3SE +/- 0.11, N = 3SE +/- 0.49, N = 353.7351.8251.8451.7251.7453.02

rav1e

Speed: 10

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4 AlphaSpeed: 107F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.68381.36762.05142.73523.419SE +/- 0.021, N = 3SE +/- 0.008, N = 3SE +/- 0.002, N = 3SE +/- 0.010, N = 3SE +/- 0.003, N = 3SE +/- 0.035, N = 32.9273.0323.0262.9723.0392.967

InfluxDB

Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 100007F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P300K600K900K1200K1500KSE +/- 1149.51, N = 3SE +/- 811.21, N = 3SE +/- 1608.37, N = 3SE +/- 961.62, N = 3SE +/- 1881.74, N = 3SE +/- 11350.62, N = 31337280.41339130.11297582.51328030.91339487.51345908.1

LZ4 Compression

Compression Level: 9 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Compression Speed7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1122334455SE +/- 0.31, N = 3SE +/- 0.54, N = 5SE +/- 0.42, N = 3SE +/- 0.41, N = 3SE +/- 0.51, N = 5SE +/- 0.62, N = 348.0848.3348.9848.2149.7048.831. (CC) gcc options: -O3

LZ4 Compression

Compression Level: 3 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Compression Speed7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1122334455SE +/- 0.56, N = 15SE +/- 0.36, N = 3SE +/- 0.05, N = 3SE +/- 0.49, N = 6SE +/- 0.55, N = 4SE +/- 0.61, N = 449.2450.5449.3149.9450.7849.671. (CC) gcc options: -O3

Basis Universal

Settings: UASTC Level 0

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 07F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P246810SE +/- 0.018, N = 3SE +/- 0.015, N = 3SE +/- 0.021, N = 3SE +/- 0.033, N = 3SE +/- 0.004, N = 3SE +/- 0.043, N = 37.7897.7337.6067.7467.5787.8081. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

PostgreSQL pgbench

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read Only - Average Latency7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.00790.01580.02370.03160.0395SE +/- 0.000, N = 10SE +/- 0.000, N = 3SE +/- 0.000, N = 4SE +/- 0.000, N = 4SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0340.0340.0340.0350.0340.0341. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

LZ4 Compression

Compression Level: 3 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Decompression Speed7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P2K4K6K8K10KSE +/- 35.55, N = 15SE +/- 1.64, N = 3SE +/- 18.01, N = 3SE +/- 35.35, N = 6SE +/- 37.48, N = 4SE +/- 72.96, N = 410402.710661.510548.810360.510606.310409.91. (CC) gcc options: -O3

BYTE Unix Benchmark

Computational Test: Dhrystone 2

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Dhrystone 27F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P8M16M24M32M40MSE +/- 523722.43, N = 3SE +/- 231062.98, N = 3SE +/- 93255.90, N = 3SE +/- 218663.85, N = 3SE +/- 295946.74, N = 12SE +/- 455276.37, N = 338477706.337547272.937624546.938124375.537455257.237519864.5

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read Only7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P6K12K18K24K30KSE +/- 222.86, N = 10SE +/- 325.35, N = 3SE +/- 335.87, N = 4SE +/- 320.79, N = 4SE +/- 161.30, N = 3SE +/- 230.23, N = 32945229391294622868129419292571. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

LZ4 Compression

Compression Level: 1 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 1 - Decompression Speed7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P2K4K6K8K10KSE +/- 80.64, N = 3SE +/- 3.46, N = 3SE +/- 28.90, N = 3SE +/- 47.03, N = 3SE +/- 35.72, N = 3SE +/- 54.20, N = 311168.711271.411314.611021.811308.911114.31. (CC) gcc options: -O3

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 1 - Mode: Read Write - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 1 - Mode: Read Write - Average Latency7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.12740.25480.38220.50960.637SE +/- 0.001, N = 3SE +/- 0.004, N = 3SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.002, N = 30.5660.5560.5530.5610.5540.5581. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Mlpack Benchmark

Benchmark: scikit_svm

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svm7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P612182430SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.15, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 324.5524.4925.0224.6124.4524.51

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 1 - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 1 - Mode: Read Write7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P400800120016002000SE +/- 2.71, N = 3SE +/- 10.89, N = 3SE +/- 5.85, N = 3SE +/- 2.88, N = 3SE +/- 1.53, N = 3SE +/- 7.22, N = 31766180118071784180517941. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

WebP Image Encode

Encode Settings: Quality 100, Lossless

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P510152025SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.12, N = 319.2019.0219.0219.0119.0418.771. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

LZ4 Compression

Compression Level: 9 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Decompression Speed7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P2K4K6K8K10KSE +/- 45.57, N = 3SE +/- 22.43, N = 5SE +/- 8.87, N = 3SE +/- 50.17, N = 3SE +/- 28.09, N = 5SE +/- 99.24, N = 310602.410616.010685.710448.210630.910473.31. (CC) gcc options: -O3

rav1e

Speed: 5

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4 AlphaSpeed: 57F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.23330.46660.69990.93321.1665SE +/- 0.005, N = 3SE +/- 0.001, N = 3SE +/- 0.002, N = 3SE +/- 0.003, N = 3SE +/- 0.003, N = 3SE +/- 0.002, N = 31.0161.0361.0371.0361.0371.030

rav1e

Speed: 6

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4 AlphaSpeed: 67F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.31190.62380.93571.24761.5595SE +/- 0.005, N = 3SE +/- 0.002, N = 3SE +/- 0.003, N = 3SE +/- 0.002, N = 3SE +/- 0.004, N = 3SE +/- 0.007, N = 31.3581.3861.3851.3781.3851.369

Numpy Benchmark

OpenBenchmarking.orgScore, More Is BetterNumpy Benchmark7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P70140210280350SE +/- 1.06, N = 3SE +/- 2.42, N = 3SE +/- 0.87, N = 3SE +/- 2.70, N = 3SE +/- 0.44, N = 3SE +/- 0.52, N = 3320.65321.81318.47318.08324.13322.49

rav1e

Speed: 1

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4 AlphaSpeed: 17F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.07850.1570.23550.3140.3925SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 30.3430.3490.3460.3480.3490.346

PHPBench

PHP Benchmark Suite

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark Suite7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P120K240K360K480K600KSE +/- 5940.23, N = 3SE +/- 4364.31, N = 3SE +/- 3310.62, N = 3SE +/- 4510.18, N = 3SE +/- 5796.24, N = 3SE +/- 5131.05, N = 3572833567897573567572905568796577796

LZ4 Compression

Compression Level: 1 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 1 - Compression Speed7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P2K4K6K8K10KSE +/- 45.18, N = 3SE +/- 22.56, N = 3SE +/- 17.93, N = 3SE +/- 55.92, N = 3SE +/- 29.36, N = 3SE +/- 79.54, N = 39632.399740.169780.389657.049777.439652.001. (CC) gcc options: -O3

PostgreSQL pgbench

Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average Latency7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.11250.2250.33750.450.5625SE +/- 0.001, N = 3SE +/- 0.004, N = 3SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 30.4980.4930.4980.4960.4950.5001. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL pgbench

Scaling Factor: 1 - Clients: 1 - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read Write7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P400800120016002000SE +/- 6.30, N = 3SE +/- 15.86, N = 3SE +/- 7.88, N = 3SE +/- 5.35, N = 3SE +/- 0.78, N = 3SE +/- 6.32, N = 32007202720092016201920011. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Basis Universal

Settings: UASTC Level 2 + RDO Post-Processing

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 2 + RDO Post-Processing7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P150300450600750SE +/- 1.44, N = 3SE +/- 0.27, N = 3SE +/- 1.41, N = 3SE +/- 0.66, N = 3SE +/- 2.14, N = 3SE +/- 1.53, N = 3689.80693.90695.00687.08694.87689.471. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

WebP Image Encode

Encode Settings: Quality 100

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 1007F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.58411.16821.75232.33642.9205SE +/- 0.003, N = 3SE +/- 0.003, N = 3SE +/- 0.003, N = 3SE +/- 0.000, N = 3SE +/- 0.005, N = 3SE +/- 0.001, N = 32.5832.5852.5912.5732.5962.5801. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

WebP Image Encode

Encode Settings: Quality 100, Lossless, Highest Compression

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest Compression7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P918273645SE +/- 0.13, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 339.3539.1739.3439.0139.2839.271. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

Crafty

Elapsed Time

OpenBenchmarking.orgNodes Per Second, More Is BetterCrafty 25.2Elapsed Time7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1.6M3.2M4.8M6.4M8MSE +/- 15876.84, N = 3SE +/- 15235.97, N = 3SE +/- 62574.81, N = 3SE +/- 1368.48, N = 3SE +/- 14432.27, N = 3SE +/- 4184.78, N = 37385993738291673592177417621740630974190021. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm

WebP Image Encode

Encode Settings: Default

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Default7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P0.36270.72541.08811.45081.8135SE +/- 0.001, N = 3SE +/- 0.004, N = 3SE +/- 0.004, N = 3SE +/- 0.002, N = 3SE +/- 0.003, N = 3SE +/- 0.001, N = 31.6111.6021.6121.6111.6111.6041. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

TNN

Target: CPU - Model: SqueezeNet v1.1

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.17F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P60120180240300SE +/- 0.12, N = 3SE +/- 0.24, N = 3SE +/- 0.38, N = 3SE +/- 0.02, N = 3SE +/- 0.13, N = 3SE +/- 0.13, N = 3274.45275.70275.38274.33275.52274.13MIN: 273.58 / MAX: 288.27MIN: 274.17 / MAX: 289.54MIN: 273.95 / MAX: 287.65MIN: 273.5 / MAX: 275.08MIN: 274.32 / MAX: 281.55MIN: 273.18 / MAX: 274.921. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

WebP Image Encode

Encode Settings: Quality 100, Highest Compression

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest Compression7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P246810SE +/- 0.027, N = 3SE +/- 0.021, N = 3SE +/- 0.001, N = 3SE +/- 0.006, N = 3SE +/- 0.004, N = 3SE +/- 0.009, N = 38.5568.5498.5488.5148.5388.5231. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

Hierarchical INTegration

Test: FLOAT

OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: FLOAT7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P70M140M210M280M350MSE +/- 41543.71, N = 3SE +/- 81095.29, N = 3SE +/- 256408.73, N = 3SE +/- 139034.34, N = 3SE +/- 739610.19, N = 3SE +/- 767979.21, N = 3322561482.01321880722.64322432634.13322779429.08321206770.06322198292.401. (CC) gcc options: -O3 -march=native -lm

RNNoise

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-287F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P510152025SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 321.1421.1321.1721.1221.1421.081. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

eSpeak-NG Speech Engine

Text-To-Speech Synthesis

OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak-NG Speech Engine 20200907Text-To-Speech Synthesis7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P816243240SE +/- 0.15, N = 4SE +/- 0.11, N = 4SE +/- 0.09, N = 4SE +/- 0.08, N = 4SE +/- 0.11, N = 4SE +/- 0.06, N = 432.8332.7632.7132.8032.8032.841. (CC) gcc options: -O2 -std=c99

IndigoBench

Acceleration: CPU - Scene: Supercar

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: SupercarAMD 7F72AMD EPYC 7F72EPYC 7F723691215SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 310.3410.3110.31

IndigoBench

Acceleration: CPU - Scene: Bedroom

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: BedroomAMD 7F72AMD EPYC 7F72EPYC 7F721.07442.14883.22324.29765.372SE +/- 0.013, N = 3SE +/- 0.006, N = 3SE +/- 0.029, N = 34.7754.7704.769

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: yolov4-tiny7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1122334455SE +/- 1.13, N = 12SE +/- 0.43, N = 3SE +/- 0.29, N = 3SE +/- 2.49, N = 9SE +/- 0.18, N = 3SE +/- 3.26, N = 949.6231.3330.7545.7831.0550.92MIN: 38.65 / MAX: 235.85MIN: 28.52 / MAX: 71.5MIN: 28.27 / MAX: 134MIN: 35.06 / MAX: 1595.62MIN: 28.99 / MAX: 116.2MIN: 35.74 / MAX: 1673.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet507F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1326395265SE +/- 5.95, N = 12SE +/- 0.54, N = 3SE +/- 0.20, N = 3SE +/- 4.19, N = 9SE +/- 0.13, N = 3SE +/- 1.38, N = 956.4824.5325.0346.8924.9544.55MIN: 36.09 / MAX: 4251.1MIN: 22.55 / MAX: 91.3MIN: 23.18 / MAX: 107.4MIN: 33.82 / MAX: 2829.75MIN: 22.93 / MAX: 118.48MIN: 32.73 / MAX: 132.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: alexnet7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P3691215SE +/- 0.41, N = 12SE +/- 0.08, N = 3SE +/- 0.18, N = 3SE +/- 0.44, N = 9SE +/- 0.09, N = 3SE +/- 0.38, N = 912.1410.5110.5211.0710.3810.89MIN: 8.73 / MAX: 262.91MIN: 9.04 / MAX: 16.98MIN: 9.15 / MAX: 90.44MIN: 8.87 / MAX: 549.19MIN: 9.08 / MAX: 21.34MIN: 8.79 / MAX: 91.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet187F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P714212835SE +/- 1.57, N = 12SE +/- 0.27, N = 3SE +/- 0.35, N = 3SE +/- 0.97, N = 9SE +/- 0.08, N = 3SE +/- 8.38, N = 924.8013.8614.1021.2413.8230.48MIN: 17.45 / MAX: 211.2MIN: 11.95 / MAX: 34.76MIN: 12.23 / MAX: 36.59MIN: 17.2 / MAX: 114.52MIN: 12.13 / MAX: 30.86MIN: 16.86 / MAX: 1521.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: vgg167F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1530456075SE +/- 2.81, N = 12SE +/- 0.88, N = 3SE +/- 0.64, N = 3SE +/- 2.16, N = 9SE +/- 0.23, N = 3SE +/- 3.59, N = 969.5636.5637.4854.1936.4855.55MIN: 45.69 / MAX: 825.7MIN: 33.32 / MAX: 133.5MIN: 33.78 / MAX: 126.41MIN: 43.69 / MAX: 183.9MIN: 33.2 / MAX: 130.64MIN: 44.48 / MAX: 1203.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: googlenet7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1326395265SE +/- 4.22, N = 12SE +/- 0.20, N = 3SE +/- 0.41, N = 3SE +/- 3.10, N = 9SE +/- 0.24, N = 3SE +/- 2.94, N = 957.4621.5522.0142.9522.0740.65MIN: 30.69 / MAX: 401.15MIN: 20.16 / MAX: 115.96MIN: 20.09 / MAX: 121.23MIN: 29.59 / MAX: 214.92MIN: 20.38 / MAX: 109.3MIN: 29.01 / MAX: 203.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: blazeface7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P3691215SE +/- 0.66, N = 12SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.47, N = 9SE +/- 0.04, N = 3SE +/- 0.39, N = 913.164.134.1611.404.0910.84MIN: 7.98 / MAX: 86.77MIN: 3.53 / MAX: 17.37MIN: 3.55 / MAX: 15.23MIN: 8.9 / MAX: 30.45MIN: 3.49 / MAX: 10.46MIN: 7.35 / MAX: 56.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: efficientnet-b07F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1122334455SE +/- 3.27, N = 12SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 2.94, N = 9SE +/- 0.25, N = 3SE +/- 8.35, N = 943.8612.6112.5440.1812.2947.15MIN: 23.72 / MAX: 2862.86MIN: 10.98 / MAX: 64.21MIN: 11.02 / MAX: 93.95MIN: 23.32 / MAX: 3005.7MIN: 10.71 / MAX: 71.52MIN: 24.1 / MAX: 4132.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mnasnet7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P918273645SE +/- 4.23, N = 12SE +/- 0.24, N = 3SE +/- 0.18, N = 3SE +/- 6.48, N = 9SE +/- 0.33, N = 3SE +/- 2.05, N = 939.129.519.5036.459.5833.45MIN: 17.58 / MAX: 1785.75MIN: 8.23 / MAX: 82.21MIN: 8.28 / MAX: 26.52MIN: 17.61 / MAX: 3072.99MIN: 8.12 / MAX: 77.12MIN: 16.65 / MAX: 742.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: shufflenet-v27F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P816243240SE +/- 1.47, N = 12SE +/- 0.14, N = 3SE +/- 0.16, N = 3SE +/- 4.58, N = 9SE +/- 0.49, N = 3SE +/- 1.30, N = 932.4710.3510.4531.5310.4529.73MIN: 19.24 / MAX: 158.48MIN: 8.97 / MAX: 20.34MIN: 9.13 / MAX: 68.26MIN: 19.78 / MAX: 3234.51MIN: 9 / MAX: 67.14MIN: 18.72 / MAX: 99.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v3-v3 - Model: mobilenet-v37F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P816243240SE +/- 1.57, N = 11SE +/- 0.11, N = 3SE +/- 0.09, N = 3SE +/- 2.41, N = 9SE +/- 0.20, N = 3SE +/- 0.87, N = 933.509.619.9431.739.5232.18MIN: 18.64 / MAX: 1819.26MIN: 8.63 / MAX: 62.41MIN: 8.64 / MAX: 101.46MIN: 18.95 / MAX: 2531.7MIN: 8.4 / MAX: 19.2MIN: 19.35 / MAX: 124.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v2-v2 - Model: mobilenet-v27F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P816243240SE +/- 2.24, N = 12SE +/- 0.17, N = 3SE +/- 0.04, N = 3SE +/- 1.77, N = 9SE +/- 0.17, N = 3SE +/- 2.05, N = 934.7010.0610.0833.1810.0432.63MIN: 16.28 / MAX: 2990.34MIN: 8.8 / MAX: 95.72MIN: 8.99 / MAX: 20.35MIN: 16.98 / MAX: 1915.06MIN: 8.78 / MAX: 67.63MIN: 16.77 / MAX: 105.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mobilenet7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1428425670SE +/- 4.13, N = 12SE +/- 0.49, N = 3SE +/- 0.56, N = 3SE +/- 3.70, N = 9SE +/- 0.66, N = 3SE +/- 1.97, N = 960.7822.2622.2046.4621.4447.44MIN: 33.09 / MAX: 237.32MIN: 18.47 / MAX: 54.35MIN: 18.67 / MAX: 87.73MIN: 32.81 / MAX: 130.57MIN: 18.65 / MAX: 82.99MIN: 31.66 / MAX: 146.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: squeezenet7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P1530456075SE +/- 1.31, N = 12SE +/- 0.17, N = 3SE +/- 0.29, N = 3SE +/- 32.56, N = 9SE +/- 0.28, N = 3SE +/- 3.29, N = 943.0621.1021.8768.4321.2639.16MIN: 31.76 / MAX: 540.59MIN: 18.23 / MAX: 105.85MIN: 18.11 / MAX: 113.58MIN: 29.51 / MAX: 3576.55MIN: 18.08 / MAX: 111.42MIN: 29.86 / MAX: 3350.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Redis

Test: SET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SET7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P300K600K900K1200K1500KSE +/- 22454.24, N = 15SE +/- 35684.24, N = 15SE +/- 27970.44, N = 15SE +/- 40018.52, N = 15SE +/- 37419.69, N = 12SE +/- 38603.79, N = 151519952.931500640.311475849.681498592.431495615.591580536.811. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: GET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: GET7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P400K800K1200K1600K2000KSE +/- 37005.83, N = 15SE +/- 29329.60, N = 15SE +/- 51919.80, N = 15SE +/- 53123.87, N = 12SE +/- 51555.46, N = 15SE +/- 39950.00, N = 151852789.071814383.801897703.881888968.342038392.691996216.741. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: LPUSH

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: LPUSH7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P300K600K900K1200K1500KSE +/- 25705.74, N = 15SE +/- 24808.96, N = 12SE +/- 23963.24, N = 15SE +/- 26859.21, N = 15SE +/- 23366.84, N = 15SE +/- 28243.04, N = 121345722.501332610.561317592.971365777.401295998.651368468.711. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: SADD

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SADD7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P400K800K1200K1600K2000KSE +/- 46378.46, N = 15SE +/- 39190.67, N = 15SE +/- 39087.64, N = 15SE +/- 40431.61, N = 15SE +/- 37861.09, N = 12SE +/- 39991.80, N = 151784823.371757206.721723521.291818648.351658090.041814208.701. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: LPOP

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: LPOP7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P500K1000K1500K2000K2500KSE +/- 95529.13, N = 15SE +/- 22561.14, N = 15SE +/- 61951.41, N = 13SE +/- 28427.12, N = 15SE +/- 44675.79, N = 15SE +/- 38584.49, N = 151508834.921376509.231379285.461388985.482134890.151380069.401. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P2004006008001000SE +/- 14.28, N = 15SE +/- 3.80, N = 3SE +/- 4.03, N = 3SE +/- 20.53, N = 15SE +/- 6.19, N = 3SE +/- 18.50, N = 15882.06924.02932.49839.85931.28822.77MIN: 758.65MIN: 894.61MIN: 897.7MIN: 694.65MIN: 898.52MIN: 694.281. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P30060090012001500SE +/- 20.83, N = 15SE +/- 6.46, N = 3SE +/- 6.62, N = 3SE +/- 28.74, N = 13SE +/- 7.42, N = 3SE +/- 29.40, N = 151334.581610.951605.901201.411613.911182.17MIN: 1172.82MIN: 1556.69MIN: 1559.69MIN: 1072.26MIN: 1557.21MIN: 1076.031. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P2004006008001000SE +/- 15.65, N = 15SE +/- 0.29, N = 3SE +/- 7.20, N = 3SE +/- 14.28, N = 15SE +/- 1.31, N = 3SE +/- 16.69, N = 15907.07930.71929.89823.75925.98848.25MIN: 758.94MIN: 898.24MIN: 896.55MIN: 700.39MIN: 896.94MIN: 699.461. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

HPC Challenge

Test / Class: Max Ping Pong Bandwidth

OpenBenchmarking.orgMB/s, More Is BetterHPC Challenge 1.5.0Test / Class: Max Ping Pong Bandwidth7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P2K4K6K8K10KSE +/- 296.59, N = 3SE +/- 760.03, N = 3SE +/- 1135.29, N = 3SE +/- 491.47, N = 3SE +/- 564.95, N = 3SE +/- 437.93, N = 38695.0610110.2610456.2911661.789566.509370.101. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 4.0.3

HPC Challenge

Test / Class: G-Ptrans

OpenBenchmarking.orgGB/s, More Is BetterHPC Challenge 1.5.0Test / Class: G-Ptrans7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P48121620SE +/- 0.83051, N = 3SE +/- 0.42362, N = 3SE +/- 0.32995, N = 3SE +/- 0.20382, N = 3SE +/- 0.43146, N = 3SE +/- 0.32220, N = 316.123578.175538.2855515.918237.7573916.456731. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 4.0.3

HPC Challenge

Test / Class: G-Ffte

OpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.5.0Test / Class: G-Ffte7F72 2PAMD 7F72AMD EPYC 7F72AMD EPYC 7F72 2PEPYC 7F72EPYC 7F72 2P510152025SE +/- 0.86449, N = 3SE +/- 0.56601, N = 3SE +/- 0.73072, N = 3SE +/- 0.18996, N = 3SE +/- 1.15527, N = 3SE +/- 0.25898, N = 320.079438.431219.4189520.857709.8723820.629571. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 4.0.3

Phoronix Test Suite v10.8.4