epyc-75f3-new

2 x AMD EPYC 75F3 32-Core testing with a ASRockRack ROME2D16-2T (P3.30 BIOS) and ASPEED on Ubuntu 21.10 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2204097-NE-EPYC75F3N46
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

Creator Workloads 2 Tests
HPC - High Performance Computing 2 Tests
Machine Learning 2 Tests
Multi-Core 2 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
A
April 09 2022
  1 Hour, 46 Minutes
AA
April 09 2022
  39 Minutes
B
April 09 2022
  39 Minutes
C
April 09 2022
  39 Minutes
Invert Hiding All Results Option
  56 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

A

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001114
Python Notes: Python 3.9.7
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

AA

B

C

Processor: 2 x AMD EPYC 75F3 32-Core @ 2.95GHz (64 Cores / 128 Threads), Motherboard: ASRockRack ROME2D16-2T (P3.30 BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: ASPEED, Audio: AMD Starship/Matisse, Network: 2 x Intel 10G X550T

OS: Ubuntu 21.10, Kernel: 5.17.0-051700rc4daily20220219-generic (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server, Vulkan: 1.1.182, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1024x768

epyc-75f3-new OpenBenchmarking.orgPhoronix Test Suite2 x AMD EPYC 75F3 32-Core @ 2.95GHz (64 Cores / 128 Threads)ASRockRack ROME2D16-2T (P3.30 BIOS)AMD Starship/Matisse128GB1000GB Western Digital WD_BLACK SN850 1TBASPEEDAMD Starship/Matisse2 x Intel 10G X550TUbuntu 21.105.17.0-051700rc4daily20220219-generic (x86_64)GNOME Shell 40.5X Server1.1.182GCC 11.2.0ext41024x768ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen ResolutionEpyc-75f3-new BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001114 - Python 3.9.7- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

AAABCResult OverviewPhoronix Test Suite100%102%104%107%109%oneDNNperf-benchlibavif avifenc

epyc-75f3-new perf-bench: Epoll Waitperf-bench: Futex Hashperf-bench: Memcpy 1MBperf-bench: Memset 1MBperf-bench: Sched Pipeperf-bench: Futex Lock-Piperf-bench: Syscall Basicavifenc: 0avifenc: 2avifenc: 6avifenc: 6, Losslessavifenc: 10, Losslessonednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: yolov4 - CPU - Parallelonnx: yolov4 - CPU - Standardonnx: bertsquad-12 - CPU - Parallelonnx: bertsquad-12 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Standardonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - StandardAAABC2352297679242.86838962.455072345990771705162169.46038.7844.2787.2155.0102.941582.639124.055690.7470840.70538011.23612.127670.8972881.683910.8785533874.181693.033819.451624.24611.512142299297671242.82982963.415414351368771705220269.41138.7284.0937.3895.2293.77922.548114.258650.8156320.70881211.13952.104071.247011.075150.9046624530.241803.514416.222016.9417.55344276.71711.6122.906113081323443435559454012317012251194432046262572297913444.14791663.789341346133801694187970.32737.5663.9867.5145.1973.180912.566434.772920.7578260.68479911.21741.946320.9288931.8530.8034264336.251810.374623.031801.2912.49654464.121734.9227.343612251310643629159264312315812351244424277622062294549442.92648563.185354339461771692459470.64639.5734.2157.1854.9713.854442.544042.558610.743010.68958311.19421.996390.784431.237530.8292174224.871713.394390.231696.621.67183862.481721.1229.1013124290944363165925391241521229127942334488OpenBenchmarking.org

perf-bench

This test profile is used for running Linux perf-bench, the benchmark support within the Linux kernel's perf tool. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Epoll WaitAAABC6001200180024003000SE +/- 23.81, N = 1223522299257220621. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma
OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Epoll WaitAAABC400800120016002000Min: 2285 / Avg: 2351.67 / Max: 25901. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Futex HashAAABC600K1200K1800K2400K3000KSE +/- 6620.62, N = 329767922976712297913429454941. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma
OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Futex HashAAABC500K1000K1500K2000K2500KMin: 2963563 / Avg: 2976792.33 / Max: 29838931. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma

OpenBenchmarking.orgGB/sec, More Is Betterperf-benchBenchmark: Memcpy 1MBAAABC1020304050SE +/- 0.17, N = 342.8742.8344.1542.931. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma
OpenBenchmarking.orgGB/sec, More Is Betterperf-benchBenchmark: Memcpy 1MBAAABC918273645Min: 42.6 / Avg: 42.87 / Max: 43.171. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma

OpenBenchmarking.orgGB/sec, More Is Betterperf-benchBenchmark: Memset 1MBAAABC1428425670SE +/- 0.65, N = 562.4663.4263.7963.191. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma
OpenBenchmarking.orgGB/sec, More Is Betterperf-benchBenchmark: Memset 1MBAAABC1224364860Min: 60.03 / Avg: 62.46 / Max: 63.421. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Sched PipeAAABC80K160K240K320K400KSE +/- 3279.19, N = 33459903513683461333394611. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma
OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Sched PipeAAABC60K120K180K240K300KMin: 339445 / Avg: 345990.33 / Max: 3496211. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Futex Lock-PiAAABC20406080100SE +/- 0.58, N = 3777780771. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma
OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Futex Lock-PiAAABC1530456075Min: 76 / Avg: 77 / Max: 781. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Syscall BasicAAABC4M8M12M16M20MSE +/- 7517.61, N = 3170516211705220216941879169245941. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma
OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Syscall BasicAAABC3M6M9M12M15MMin: 17043146 / Avg: 17051621.33 / Max: 170666141. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 0AAABC1632486480SE +/- 0.35, N = 369.4669.4170.3370.651. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 0AAABC1428425670Min: 68.88 / Avg: 69.46 / Max: 70.081. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 2AAABC918273645SE +/- 0.11, N = 338.7838.7337.5739.571. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 2AAABC816243240Min: 38.61 / Avg: 38.78 / Max: 38.981. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6AAABC0.96261.92522.88783.85044.813SE +/- 0.011, N = 34.2784.0933.9864.2151. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6AAABC246810Min: 4.26 / Avg: 4.28 / Max: 4.31. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6, LosslessAAABC246810SE +/- 0.066, N = 77.2157.3897.5147.1851. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6, LosslessAAABC3691215Min: 7.03 / Avg: 7.21 / Max: 7.541. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 10, LosslessAAABC1.17652.3533.52954.7065.8825SE +/- 0.030, N = 35.0105.2295.1974.9711. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 10, LosslessAAABC246810Min: 4.97 / Avg: 5.01 / Max: 5.071. (CXX) g++ options: -O3 -fPIC -lm

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of Intel oneAPI. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUAAABC0.86721.73442.60163.46884.336SE +/- 0.19680, N = 152.941583.779203.180913.85444MIN: 1.53MIN: 2.55MIN: 2.24MIN: 2.651. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUAAABC246810Min: 1.87 / Avg: 2.94 / Max: 4.171. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUAAABC0.59381.18761.78142.37522.969SE +/- 0.01578, N = 32.639122.548112.566432.54404MIN: 2.08MIN: 2.06MIN: 2.05MIN: 2.051. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUAAABC246810Min: 2.61 / Avg: 2.64 / Max: 2.661. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUAAABC1.07392.14783.22174.29565.3695SE +/- 0.14420, N = 154.055694.258654.772922.55861MIN: 2.07MIN: 2.63MIN: 2.83MIN: 1.851. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUAAABC246810Min: 3.22 / Avg: 4.06 / Max: 5.071. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUAAABC0.18350.3670.55050.7340.9175SE +/- 0.011604, N = 150.7470840.8156320.7578260.743010MIN: 0.57MIN: 0.62MIN: 0.62MIN: 0.611. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUAAABC246810Min: 0.68 / Avg: 0.75 / Max: 0.81. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

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

A: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

AA: The test run did not produce a result.

B: The test run did not produce a result.

C: The test run did not produce a result.

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

A: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

AA: The test run did not produce a result.

B: The test run did not produce a result.

C: The test run did not produce a result.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUAAABC0.15950.3190.47850.6380.7975SE +/- 0.006925, N = 30.7053800.7088120.6847990.689583MIN: 0.64MIN: 0.67MIN: 0.64MIN: 0.641. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUAAABC246810Min: 0.7 / Avg: 0.71 / Max: 0.721. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUAAABC3691215SE +/- 0.09, N = 311.2411.1411.2211.19MIN: 8.6MIN: 9MIN: 9MIN: 8.841. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUAAABC3691215Min: 11.07 / Avg: 11.24 / Max: 11.361. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUAAABC0.47870.95741.43611.91482.3935SE +/- 0.02508, N = 32.127672.104071.946321.99639MIN: 1.72MIN: 1.79MIN: 1.74MIN: 1.731. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUAAABC246810Min: 2.08 / Avg: 2.13 / Max: 2.161. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUAAABC0.28060.56120.84181.12241.403SE +/- 0.048482, N = 150.8972881.2470100.9288930.784430MIN: 0.51MIN: 0.56MIN: 0.54MIN: 0.541. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUAAABC246810Min: 0.61 / Avg: 0.9 / Max: 1.241. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUAAABC0.41690.83381.25071.66762.0845SE +/- 0.09292, N = 151.683911.075151.853001.23753MIN: 0.87MIN: 0.92MIN: 1.67MIN: 1.091. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUAAABC246810Min: 1.02 / Avg: 1.68 / Max: 2.281. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUAAABC0.20350.4070.61050.8141.0175SE +/- 0.011448, N = 120.8785530.9046620.8034260.829217MIN: 0.65MIN: 0.68MIN: 0.57MIN: 0.61. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUAAABC246810Min: 0.81 / Avg: 0.88 / Max: 0.931. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUAAABC10002000300040005000SE +/- 239.78, N = 143874.184530.244336.254224.87MIN: 1544.77MIN: 3953.07MIN: 3938.66MIN: 3842.951. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUAAABC8001600240032004000Min: 1938.1 / Avg: 3874.18 / Max: 4513.421. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUAAABC400800120016002000SE +/- 64.86, N = 121693.031803.511810.371713.39MIN: 1036.24MIN: 1650.67MIN: 1535.85MIN: 1504.131. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUAAABC30060090012001500Min: 1153.4 / Avg: 1693.03 / Max: 2021.021. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUAAABC10002000300040005000SE +/- 242.60, N = 123819.454416.224623.034390.23MIN: 1342.54MIN: 4047.45MIN: 4242.04MIN: 3742.531. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUAAABC8001600240032004000Min: 1582.95 / Avg: 3819.45 / Max: 4519.051. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

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

A: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

AA: The test run did not produce a result.

B: The test run did not produce a result.

C: The test run did not produce a result.

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

A: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

AA: The test run did not produce a result.

B: The test run did not produce a result.

C: The test run did not produce a result.

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

A: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

AA: The test run did not produce a result.

B: The test run did not produce a result.

C: The test run did not produce a result.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUAAABC400800120016002000SE +/- 88.05, N = 121624.252016.941801.291696.60MIN: 827.28MIN: 1858.23MIN: 1534.31MIN: 1543.981. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUAAABC400800120016002000Min: 974.64 / Avg: 1624.25 / Max: 1964.091. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUAAABC510152025SE +/- 1.25, N = 1511.5117.5512.5021.67MIN: 5.15MIN: 12.56MIN: 8.99MIN: 15.661. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUAAABC510152025Min: 6.07 / Avg: 11.51 / Max: 21.221. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUAABC100020003000400050004276.704464.123862.48MIN: 3959.8MIN: 4162.92MIN: 3242.511. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUAABC4008001200160020001711.611734.921721.12MIN: 1495.43MIN: 1463.54MIN: 1603.971. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUAABC71421283522.9127.3429.10MIN: 16.94MIN: 19.51MIN: 20.221. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

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

AA: The test run did not produce a result.

B: The test run did not produce a result.

C: The test run did not produce a result.

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: ParallelAABC300600900120015001308122512421. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: StandardAABC3K6K9K12K15K132341310690941. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: yolov4 - Device: CPU - Executor: ParallelAABC901802703604504344364361. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: yolov4 - Device: CPU - Executor: StandardAABC801602403204003552913161. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: ParallelAABC1302603905206505945925921. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: StandardAABC1402804205607005406435391. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelAABC3060901201501231231241. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: StandardAABC40801201602001701581521. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelAABC300600900120015001225123512291. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardAABC300600900120015001194124412791. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: ParallelAABC90018002700360045004320424242331. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: StandardAABC170034005100680085004626776244881. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

A

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001114
Python Notes: Python 3.9.7
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 9 April 2022 15:27 by user phoronix.

AA

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001114
Python Notes: Python 3.9.7
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 9 April 2022 17:52 by user phoronix.

B

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001114
Python Notes: Python 3.9.7
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 9 April 2022 18:39 by user phoronix.

C

Processor: 2 x AMD EPYC 75F3 32-Core @ 2.95GHz (64 Cores / 128 Threads), Motherboard: ASRockRack ROME2D16-2T (P3.30 BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: ASPEED, Audio: AMD Starship/Matisse, Network: 2 x Intel 10G X550T

OS: Ubuntu 21.10, Kernel: 5.17.0-051700rc4daily20220219-generic (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server, Vulkan: 1.1.182, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1024x768

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001114
Python Notes: Python 3.9.7
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 9 April 2022 19:31 by user phoronix.