xeon gold april

2 x Intel Xeon Gold 5220R testing with a TYAN S7106 (V2.01.B40 BIOS) and ASPEED on Ubuntu 20.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2204205-NE-XEONGOLDA77&grs.

xeon gold aprilProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionABCD2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads)TYAN S7106 (V2.01.B40 BIOS)Intel Sky Lake-E DMI3 Registers94GB500GB Samsung SSD 860ASPEEDVE2282 x Intel I210 + 2 x QLogic cLOM8214 1/10GbEUbuntu 20.045.9.0-050900rc6-generic (x86_64) 20200920GNOME Shell 3.36.4X Server 1.20.13GCC 9.4.0ext41920x1080OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler 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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-yTrUTS/gcc-9-9.4.0/debian/tmp-nvptx/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 Processor Details- Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x5003102 Java Details- OpenJDK Runtime Environment (build 11.0.14+9-Ubuntu-0ubuntu2.20.04)Security Details- itlb_multihit: KVM: Mitigation of VMX disabled + 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled

xeon gold aprilonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUonednn: IP Shapes 1D - f32 - CPUethr: TCP - Connections/s - 16ethr: TCP - Connections/s - 32ethr: TCP - Latency - 4ethr: TCP - Latency - 64ethr: TCP - Bandwidth - 1ethr: TCP - Latency - 2ethr: TCP - Bandwidth - 2ethr: UDP - Bandwidth - 4perf-bench: Epoll Waitethr: TCP - Latency - 16onednn: IP Shapes 3D - bf16bf16bf16 - CPUethr: TCP - Bandwidth - 32perf-bench: Memset 1MBethr: TCP - Latency - 1onednn: Recurrent Neural Network Inference - u8s8f32 - CPUethr: UDP - Bandwidth - 16ethr: UDP - Bandwidth - 16onednn: Recurrent Neural Network Inference - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUethr: UDP - Bandwidth - 8ethr: UDP - Bandwidth - 8perf-bench: Memcpy 1MBonednn: Recurrent Neural Network Training - u8s8f32 - CPUethr: UDP - Bandwidth - 2ethr: UDP - Bandwidth - 2ethr: UDP - Bandwidth - 1avifenc: 6avifenc: 6, Losslessethr: TCP - Bandwidth - 16onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUperf-bench: Futex Lock-Piethr: UDP - Bandwidth - 32ethr: UDP - Bandwidth - 4onednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPUethr: UDP - Bandwidth - 64onednn: IP Shapes 3D - u8s8f32 - CPUethr: TCP - Bandwidth - 64ethr: UDP - Bandwidth - 64ethr: TCP - Latency - 32ethr: TCP - Bandwidth - 8ethr: TCP - Latency - 8avifenc: 0avifenc: 10, Losslessavifenc: 2influxdb: 64 - 10000 - 2,5000,1 - 10000ethr: TCP - Bandwidth - 4ethr: UDP - Bandwidth - 32onednn: IP Shapes 3D - f32 - CPUperf-bench: Sched Pipeonednn: Recurrent Neural Network Training - f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUinfluxdb: 1024 - 10000 - 2,5000,1 - 10000onednn: IP Shapes 1D - bf16bf16bf16 - CPUinfluxdb: 4 - 10000 - 2,5000,1 - 10000perf-bench: Syscall Basiconednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUjava-jmh: Throughputethr: TCP - Connections/s - 8ethr: TCP - Connections/s - 64onednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUethr: TCP - Connections/s - 4onednn: Deconvolution Batch shapes_1d - f32 - CPUperf-bench: Futex Hashethr: TCP - Connections/s - 2ethr: TCP - Connections/s - 1ABCD0.2398591.770241011208332.21643.02923.3841.76523.511291.93770841.3474.0517615.2456.89458237.54779.526217200032.86865.5191.2713940.16139840016.8049521377.5137814132.7519.756.48910.89921.581391.2511120.718126672.6034129964001.228188.4911.9141.49525.3440.252113.4237.48858.8971040989.925.8727628003.72951801541396.337.539741079356.25.71974783450.1167176382.781366.955260.4714798.74834785.4390.555970.69116453387527398.055101210169.556236.36114101011.08332825232101010100.2399111.766891013101242.04840.85817.7241.80324.941601.86635041.7023.4071413.0359.80317339.873890.068226720033.88781.3271.3635540.97142560018.2925521367.0336871931.8618.886.76610.91420.731378.8810721.188412252.5348929400001.232698.6711.7142.38924.9341.127112.787.39759.1481028876.425.6327556003.766781814161404.647.464011071590.15.67367786195.2167752642.79746.95150.4722388.73941781.4170.5567110.69117553514068363.933101110149.538416.3588101011.07842824913101010107.478444.158031010165641.87741.89223.141.36120.671426.07755642.9143.8194415.0952.0748941.075788.892203560030.73779.1381.4102837.47130840016.7947361473.7738706733.2719.86.52411.34820.931434.5510721.478203982.5202729508001.196418.6511.7341.20224.7341.091110.9167.34360102195525.8428024003.704281831851382.237.4707110820505.68132780902.8168286872.793496.917110.4697798.78465781.50.5585460.69376953315949803.277101010149.543486.36553101011.08152824285101010102080101243.08732.25823.1432.23625.741377.4631435.97114.5553.01996343.111200320030.2540.6142800017.04766136678431.6619.6821.4621.0882026329076008.7411.5742.01825.1641.20326.092773600182091101010151011282478310101010OpenBenchmarking.org

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUABC2468100.2398590.2399117.478440MIN: 0.251. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUABC0.93561.87122.80683.74244.6781.770241.766894.15803MIN: 1.69MIN: 1.68MIN: 1.691. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

Ethr

Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 16

OpenBenchmarking.orgConnections/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 16ABCD4008001200160020001011101310102080MIN: 1010MIN: 1010 / MAX: 1020MIN: 1010

Ethr

Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 32

OpenBenchmarking.orgConnections/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 32ABCD4008001200160020002083101216561012MIN: 1010MIN: 1010 / MAX: 1020MIN: 1010MIN: 1010 / MAX: 1020

Ethr

Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 4

OpenBenchmarking.orgus, Fewer Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 4ABCD102030405032.2242.0541.8843.09MIN: 28.6 / MAX: 33.81MIN: 35.62 / MAX: 50.47MIN: 37.48 / MAX: 49.72MIN: 38.43 / MAX: 49.14

Ethr

Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 64

OpenBenchmarking.orgus, Fewer Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 64ABCD102030405043.0340.8641.8932.26MIN: 33.02 / MAX: 50.73MIN: 32.67 / MAX: 45.14MIN: 31.68 / MAX: 45.62MIN: 28.92 / MAX: 47.21

Ethr

Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 1

OpenBenchmarking.orgGbits/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 1ABCD61218243023.3817.7223.1023.14MIN: 21.34 / MAX: 25.05MIN: 14.68 / MAX: 22.62MIN: 21.11 / MAX: 24.02MIN: 22.13 / MAX: 24.35

Ethr

Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 2

OpenBenchmarking.orgus, Fewer Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 2ABCD102030405041.7741.8041.3632.24MIN: 34.05 / MAX: 52.7MIN: 37.72 / MAX: 49.34MIN: 37.14 / MAX: 46.94MIN: 29.44 / MAX: 40.51

Ethr

Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 2

OpenBenchmarking.orgGbits/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 2ABCD61218243023.5124.9420.6725.74MIN: 14.62 / MAX: 43.04MIN: 16.75 / MAX: 43.96MIN: 13.75 / MAX: 37.78MIN: 16.46 / MAX: 43.62

Ethr

Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 4

OpenBenchmarking.orgGbits/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 4ABCD300600900120015001291.931601.861426.071377.40MIN: 23.68MIN: 24.41MIN: 24.04MIN: 24.11

perf-bench

Benchmark: Epoll Wait

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Epoll WaitABCD1700340051006800850077086350755663141. (CC) gcc options: -pthread -shared -lunwind-x86_64 -lunwind -llzma -Xlinker -export-dynamic -O6 -ggdb3 -funwind-tables -std=gnu99 -fPIC -lnuma

Ethr

Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 16

OpenBenchmarking.orgus, Fewer Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 16ABCD102030405041.3541.7042.9135.97MIN: 36.81 / MAX: 44.28MIN: 32.41 / MAX: 45.69MIN: 30.22 / MAX: 51.22MIN: 29.59 / MAX: 45.4

oneDNN

Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPUABC0.91161.82322.73483.64644.5584.051763.407143.81944MIN: 2.94MIN: 2.86MIN: 2.931. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

Ethr

Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 32

OpenBenchmarking.orgGbits/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 32ABCD4812162015.2413.0315.0914.55MIN: 5.94 / MAX: 261.6MIN: 5.14 / MAX: 243.16MIN: 4.73 / MAX: 269.41MIN: 4.94 / MAX: 249.01

perf-bench

Benchmark: Memset 1MB

OpenBenchmarking.orgGB/sec, More Is Betterperf-benchBenchmark: Memset 1MBABCD132639526556.8959.8052.0753.021. (CC) gcc options: -pthread -shared -lunwind-x86_64 -lunwind -llzma -Xlinker -export-dynamic -O6 -ggdb3 -funwind-tables -std=gnu99 -fPIC -lnuma

Ethr

Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 1

OpenBenchmarking.orgus, Fewer Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 1ABCD102030405037.5439.8741.0843.11MIN: 29.88 / MAX: 48.56MIN: 31.88 / MAX: 47.22MIN: 32.43 / MAX: 50.94MIN: 38.3 / MAX: 49.42

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUABC2004006008001000779.53890.07788.89MIN: 769.69MIN: 769.73MIN: 765.691. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

Ethr

Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 16

OpenBenchmarking.orgPackets/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 16ABCD500K1000K1500K2000K2500K2172000226720020356002003200MIN: 1940000 / MAX: 2280000MIN: 2220000 / MAX: 2310000MIN: 1790000 / MAX: 2270000MIN: 1930000 / MAX: 2090000

Ethr

Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 16

OpenBenchmarking.orgGbits/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 16ABCD81624324032.8633.8830.7330.25MIN: 11.43 / MAX: 291.97MIN: 12.22 / MAX: 295.21MIN: 12.32 / MAX: 290.81MIN: 12.07 / MAX: 268.09

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUABC2004006008001000865.52781.33779.14MIN: 766.63MIN: 775.04MIN: 771.231. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUABC0.31730.63460.95191.26921.58651.271391.363551.41028MIN: 1.18MIN: 1.27MIN: 1.321. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

Ethr

Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 8

OpenBenchmarking.orgGbits/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 8ABCD91827364540.1640.9737.4740.60MIN: 18.92 / MAX: 191.69MIN: 18.81 / MAX: 192.13MIN: 18.98 / MAX: 175.77MIN: 18.23 / MAX: 199.35

Ethr

Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 8

OpenBenchmarking.orgPackets/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 8ABCD300K600K900K1200K1500K1398400142560013084001428000MIN: 1230000 / MAX: 1500000MIN: 1220000 / MAX: 1500000MIN: 1210000 / MAX: 1370000MIN: 1260000 / MAX: 1560000

perf-bench

Benchmark: Memcpy 1MB

OpenBenchmarking.orgGB/sec, More Is Betterperf-benchBenchmark: Memcpy 1MBABCD51015202516.8018.2916.7917.051. (CC) gcc options: -pthread -shared -lunwind-x86_64 -lunwind -llzma -Xlinker -export-dynamic -O6 -ggdb3 -funwind-tables -std=gnu99 -fPIC -lnuma

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUABC300600900120015001377.511367.031473.77MIN: 1371.47MIN: 1359.37MIN: 1371.191. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

Ethr

Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 2

OpenBenchmarking.orgPackets/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 2ABCD80K160K240K320K400K378141368719387067366784MIN: 349770 / MAX: 426690MIN: 335020 / MAX: 393720MIN: 338890 / MAX: 426850MIN: 337700 / MAX: 385930

Ethr

Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 2

OpenBenchmarking.orgGbits/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 2ABCD81624324032.7531.8633.2731.66MIN: 22.31 / MAX: 54.62MIN: 21.41 / MAX: 52.55MIN: 21.65 / MAX: 54.64MIN: 21.42 / MAX: 51.04

Ethr

Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 1

OpenBenchmarking.orgGbits/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 1ABCD51015202519.7518.8819.8019.68MIN: 18.01 / MAX: 25.67MIN: 17.69 / MAX: 21.31MIN: 17.79 / MAX: 25.36MIN: 17.78 / MAX: 24.79

libavif avifenc

Encoder Speed: 6

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6ABC2468106.4896.7666.5241. (CXX) g++ options: -O3 -fPIC -lm

libavif avifenc

Encoder Speed: 6, Lossless

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6, LosslessABC369121510.9010.9111.351. (CXX) g++ options: -O3 -fPIC -lm

Ethr

Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 16

OpenBenchmarking.orgGbits/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 16ABCD51015202521.5820.7320.9321.46MIN: 8.82 / MAX: 183.6MIN: 8.03 / MAX: 182.13MIN: 8.39 / MAX: 185.03MIN: 8.37 / MAX: 184.83

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUABC300600900120015001391.251378.881434.55MIN: 1375.6MIN: 1370.45MIN: 1353.511. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

perf-bench

Benchmark: Futex Lock-Pi

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Futex Lock-PiABC204060801001111071071. (CC) gcc options: -pthread -shared -lunwind-x86_64 -lunwind -llzma -Xlinker -export-dynamic -O6 -ggdb3 -funwind-tables -std=gnu99 -fPIC -lnuma

Ethr

Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 32

OpenBenchmarking.orgGbits/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 32ABCD51015202520.7121.1821.4721.08MIN: 5.71 / MAX: 358.92MIN: 6.11 / MAX: 361.13MIN: 5.68 / MAX: 364.15MIN: 5.84 / MAX: 360.82

Ethr

Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 4

OpenBenchmarking.orgPackets/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 4ABCD200K400K600K800K1000K812667841225820398820263MIN: 778180 / MAX: 866540MIN: 798610 / MAX: 902140MIN: 778870 / MAX: 857010MIN: 777610 / MAX: 866340

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPUABC0.58581.17161.75742.34322.9292.603412.534892.52027MIN: 2.36MIN: 2.3MIN: 2.251. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

Ethr

Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 64

OpenBenchmarking.orgPackets/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 64ABCD600K1200K1800K2400K3000K2996400294000029508002907600MIN: 2780000 / MAX: 3170000MIN: 2910000 / MAX: 2990000MIN: 2900000 / MAX: 2980000MIN: 2890000 / MAX: 2940000

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUABC0.27740.55480.83221.10961.3871.228181.232691.19641MIN: 1.14MIN: 1.15MIN: 1.121. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

Ethr

Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 64

OpenBenchmarking.orgGbits/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 64ABCD2468108.498.678.658.74MIN: 1.22 / MAX: 296.78MIN: 2.19 / MAX: 291.04MIN: 1.55 / MAX: 291.46MIN: 2.35 / MAX: 299.41

Ethr

Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 64

OpenBenchmarking.orgGbits/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 64ABCD369121511.9111.7111.7311.57MIN: 4.84 / MAX: 405.65MIN: 4.19 / MAX: 382.52MIN: 4.43 / MAX: 381.48MIN: 4.84 / MAX: 376.44

Ethr

Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 32

OpenBenchmarking.orgus, Fewer Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 32ABCD102030405041.5042.3941.2042.02MIN: 37.34 / MAX: 50.59MIN: 35.95 / MAX: 46.82MIN: 38.11 / MAX: 45.61MIN: 30.7 / MAX: 52.35

Ethr

Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 8

OpenBenchmarking.orgGbits/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 8ABCD61218243025.3424.9324.7325.16MIN: 12.61 / MAX: 127.4MIN: 12.3 / MAX: 117.07MIN: 11.99 / MAX: 115.22MIN: 12.8 / MAX: 126.04

Ethr

Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 8

OpenBenchmarking.orgus, Fewer Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 8ABCD91827364540.2541.1341.0941.20MIN: 31.18 / MAX: 45.88MIN: 31.32 / MAX: 48.35MIN: 32.56 / MAX: 47.82MIN: 31.05 / MAX: 46.46

libavif avifenc

Encoder Speed: 0

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 0ABC306090120150113.42112.78110.921. (CXX) g++ options: -O3 -fPIC -lm

libavif avifenc

Encoder Speed: 10, Lossless

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 10, LosslessABC2468107.4887.3977.3431. (CXX) g++ options: -O3 -fPIC -lm

libavif avifenc

Encoder Speed: 2

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 2ABC132639526558.9059.1560.001. (CXX) g++ options: -O3 -fPIC -lm

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: 10000ABC200K400K600K800K1000K1040989.91028876.41021955.0

Ethr

Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 4

OpenBenchmarking.orgGbits/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 4ABCD61218243025.8725.6325.8426.09MIN: 14.13 / MAX: 78.06MIN: 13.97 / MAX: 77.66MIN: 14.08 / MAX: 75.21MIN: 13.23 / MAX: 79.39

Ethr

Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 32

OpenBenchmarking.orgPackets/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 32ABCD600K1200K1800K2400K3000K2762800275560028024002773600MIN: 2690000 / MAX: 2800000MIN: 2630000 / MAX: 2820000MIN: 2740000 / MAX: 2840000MIN: 2670000 / MAX: 2820000

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUABC0.84751.6952.54253.394.23753.729503.766783.70428MIN: 3.68MIN: 3.72MIN: 3.651. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

perf-bench

Benchmark: Sched Pipe

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Sched PipeABCD40K80K120K160K200K1801541814161831851820911. (CC) gcc options: -pthread -shared -lunwind-x86_64 -lunwind -llzma -Xlinker -export-dynamic -O6 -ggdb3 -funwind-tables -std=gnu99 -fPIC -lnuma

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUABC300600900120015001396.331404.641382.23MIN: 1377.62MIN: 1353.93MIN: 1361.511. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUABC2468107.539747.464017.47071MIN: 7.45MIN: 7.38MIN: 7.381. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

InfluxDB

Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000ABC200K400K600K800K1000K1079356.21071590.11082050.0

oneDNN

Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPUABC1.28692.57383.86075.14766.43455.719745.673675.68132MIN: 5.55MIN: 5.54MIN: 5.541. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

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: 10000ABC200K400K600K800K1000K783450.1786195.2780902.8

perf-bench

Benchmark: Syscall Basic

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Syscall BasicABC4M8M12M16M20M1671763816775264168286871. (CC) gcc options: -pthread -shared -lunwind-x86_64 -lunwind -llzma -Xlinker -export-dynamic -O6 -ggdb3 -funwind-tables -std=gnu99 -fPIC -lnuma

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUABC0.62941.25881.88822.51763.1472.781362.797402.79349MIN: 2.75MIN: 2.75MIN: 2.741. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUABC2468106.955266.951506.91711MIN: 6.88MIN: 6.84MIN: 6.851. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUABC0.10630.21260.31890.42520.53150.4714790.4722380.469779MIN: 0.45MIN: 0.45MIN: 0.451. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUABC2468108.748348.739418.78465MIN: 8.64MIN: 8.63MIN: 8.651. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUABC2004006008001000785.44781.42781.50MIN: 773.81MIN: 775.98MIN: 772.151. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUABC0.12570.25140.37710.50280.62850.5559700.5567110.558546MIN: 0.53MIN: 0.54MIN: 0.541. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUABC0.15610.31220.46830.62440.78050.6911640.6911750.693769MIN: 0.68MIN: 0.68MIN: 0.681. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

Java JMH

Throughput

OpenBenchmarking.orgOps/s, More Is BetterJava JMHThroughputABC11000M22000M33000M44000M55000M53387527398.0653514068363.9353315949803.28

Ethr

Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 8

OpenBenchmarking.orgConnections/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 8ABCD20040060080010001012101110101010MIN: 1010 / MAX: 1020MIN: 1010 / MAX: 1020

Ethr

Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 64

OpenBenchmarking.orgConnections/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 64ABCD20040060080010001016101410141015MIN: 1010 / MAX: 1020MIN: 1010 / MAX: 1020MIN: 1010 / MAX: 1020MIN: 1010 / MAX: 1020

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPUABC36912159.556239.538419.54348MIN: 9.46MIN: 9.46MIN: 9.451. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUABC2468106.361146.358806.36553MIN: 6.32MIN: 6.32MIN: 6.321. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

Ethr

Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 4

OpenBenchmarking.orgConnections/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 4ABCD20040060080010001010101010101011MIN: 1010

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUABC369121511.0811.0811.08MIN: 8.7MIN: 7.46MIN: 9.511. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

perf-bench

Benchmark: Futex Hash

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Futex HashABCD600K1200K1800K2400K3000K28252322824913282428528247831. (CC) gcc options: -pthread -shared -lunwind-x86_64 -lunwind -llzma -Xlinker -export-dynamic -O6 -ggdb3 -funwind-tables -std=gnu99 -fPIC -lnuma

Ethr

Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 2

OpenBenchmarking.orgConnections/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 2ABCD20040060080010001010101010101010

Ethr

Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 1

OpenBenchmarking.orgConnections/sec, More Is BetterEthr 1.0Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 1ABCD20040060080010001010101010101010

Phoronix Test Suite v10.8.5