dnn

Intel Core i7-1065G7 testing with a Dell 06CDVY (1.0.9 BIOS) and Intel Iris Plus ICL GT2 16GB on Ubuntu 22.04 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 2209299-NE-DNN17038446
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
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
September 28 2022
  44 Minutes
B
September 29 2022
  39 Minutes
C
September 29 2022
  40 Minutes
Invert Hiding All Results Option
  41 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):


dnnOpenBenchmarking.orgPhoronix Test SuiteIntel Core i7-1065G7 @ 3.90GHz (4 Cores / 8 Threads)Dell 06CDVY (1.0.9 BIOS)Intel Ice Lake-LP DRAM16GBToshiba KBG40ZPZ512G NVMe 512GBIntel Iris Plus ICL GT2 16GB (1100MHz)Realtek ALC289Intel Ice Lake-LP PCH CNVi WiFiUbuntu 22.045.18.8-051808-generic (x86_64)GNOME Shell 42.2X Server + Wayland4.6 Mesa 22.0.11.3.204GCC 11.2.0ext41920x1200ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionDnn 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-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/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: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xb2 - Thermald 2.4.9 - itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Not affected

aBCResult OverviewPhoronix Test Suite100%165%230%296%oneDNNoneDNNoneDNNAOM AV1oneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNAOM AV1oneDNNoneDNNAOM AV1oneDNNoneDNNoneDNNoneDNNoneDNNAOM AV1AOM AV1AOM AV1AOM AV1oneDNNoneDNNAOM AV1oneDNNAOM AV1AOM AV1AOM AV1oneDNNAOM AV1AOM AV1AOM AV1oneDNNoneDNNIP Shapes 1D - f32 - CPUM.M.B.S.T - f32 - CPUD.B.s - u8s8f32 - CPUSpeed 0 Two-Pass - Bosphorus 4KIP Shapes 1D - u8s8f32 - CPUD.B.s - f32 - CPUD.B.s - bf16bf16bf16 - CPUR.N.N.T - f32 - CPUIP Shapes 3D - u8s8f32 - CPUIP Shapes 3D - bf16bf16bf16 - CPUC.B.S.A - bf16bf16bf16 - CPUR.N.N.T - u8s8f32 - CPUSpeed 4 Two-Pass - Bosphorus 4KC.B.S.A - f32 - CPUM.M.B.S.T - bf16bf16bf16 - CPUSpeed 6 Realtime - Bosphorus 4KR.N.N.I - f32 - CPUM.M.B.S.T - u8s8f32 - CPUD.B.s - f32 - CPUR.N.N.I - bf16bf16bf16 - CPUIP Shapes 1D - bf16bf16bf16 - CPUSpeed 6 Two-Pass - Bosphorus 4KSpeed 8 Realtime - Bosphorus 1080pSpeed 0 Two-Pass - Bosphorus 1080pSpeed 4 Two-Pass - Bosphorus 1080pD.B.s - bf16bf16bf16 - CPUR.N.N.T - bf16bf16bf16 - CPUSpeed 6 Realtime - Bosphorus 1080pIP Shapes 3D - f32 - CPUSpeed 9 Realtime - Bosphorus 4KSpeed 8 Realtime - Bosphorus 4KSpeed 6 Two-Pass - Bosphorus 1080pD.B.s - u8s8f32 - CPUSpeed 10 Realtime - Bosphorus 4KSpeed 9 Realtime - Bosphorus 1080pSpeed 10 Realtime - Bosphorus 1080pR.N.N.I - u8s8f32 - CPUC.B.S.A - u8s8f32 - CPU

dnnaom-av1: Speed 0 Two-Pass - Bosphorus 4Kaom-av1: Speed 4 Two-Pass - Bosphorus 4Kaom-av1: Speed 6 Realtime - Bosphorus 4Kaom-av1: Speed 6 Two-Pass - Bosphorus 4Kaom-av1: Speed 8 Realtime - Bosphorus 4Kaom-av1: Speed 9 Realtime - Bosphorus 4Kaom-av1: Speed 10 Realtime - Bosphorus 4Kaom-av1: Speed 0 Two-Pass - Bosphorus 1080paom-av1: Speed 4 Two-Pass - Bosphorus 1080paom-av1: Speed 6 Realtime - Bosphorus 1080paom-av1: Speed 6 Two-Pass - Bosphorus 1080paom-av1: Speed 8 Realtime - Bosphorus 1080paom-av1: Speed 9 Realtime - Bosphorus 1080paom-av1: Speed 10 Realtime - Bosphorus 1080ponednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: IP Shapes 1D - bf16bf16bf16 - CPUonednn: IP Shapes 3D - bf16bf16bf16 - 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: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - 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 - CPUonednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPUy-cruncher: 1BaBC0.051.639.643.118.9931.8233.710.154.5123.7510.476.81121.8128.5735.00346.411782.046812.5352123.09757.1819312.80416.430113.026311.20552.55863.098298712.075531.1910530.146.292867.237247.5945842.13.098311316.15690.091.7859713.4512138.9280.071.8510.723.3619.5132.9834.620.164.7924.7410.7182.7124130.079.702066.526292.64052.5685124.05667.2643813.271818.777212.83611.24282.709123.0091711575.65891.1511553.546.344388.525747.43155885.494.6993411562.25933.911.9462814.73890.061.72103.1518.8732.1434.110.154.5523.6110.5482.41123.75130.4711.23126.66172.821933.2552125.37938.8049514.507322.547711.824811.32143.907593.04817116466146.3212419.555.928591.034845.04875924.854.8628211871.26265.971.9695115.0843OpenBenchmarking.org

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4KCBa0.01580.03160.04740.06320.0790.060.070.051. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4KCBa0.41630.83261.24891.66522.08151.721.851.631. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4KCBa369121510.0010.729.641. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4KCBa0.7561.5122.2683.0243.783.153.363.101. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4KCBa51015202518.8719.5118.991. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4KCBa81624324032.1432.9831.821. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4KCBa81624324034.1134.6233.711. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080pCBa0.0360.0720.1080.1440.180.150.160.151. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080pCBa1.07782.15563.23344.31125.3894.554.794.511. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080pCBa61218243023.6124.7423.751. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080pCBa369121510.5410.7110.401. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080pCBa2040608010082.4182.7076.811. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080pCBa306090120150123.75124.00121.801. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080pCBa306090120150130.47130.07128.571. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUCBa81624324011.231209.7020635.00340MIN: 8.47MIN: 8.68MIN: 8.351. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUCBa2468106.661706.526296.41178MIN: 6.16MIN: 6.07MIN: 5.991. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUCBa0.63491.26981.90472.53963.17452.821932.640502.04681MIN: 1.92MIN: 2.03MIN: 1.821. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUCBa0.73241.46482.19722.92963.6623.255212.568512.53521MIN: 2.39MIN: 2.41MIN: 2.411. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPUCBa61218243025.3824.0623.10MIN: 22.08MIN: 23.01MIN: 22.421. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPUCBa2468108.804957.264387.18193MIN: 5.86MIN: 5.92MIN: 5.941. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUCBa4812162014.5113.2712.80MIN: 11.86MIN: 11.9MIN: 12.391. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUCBa51015202522.5518.7816.43MIN: 19.3MIN: 17.1MIN: 14.431. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUCBa369121511.8212.8413.03MIN: 11.2MIN: 12.46MIN: 12.71. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUCBa369121511.3211.2411.21MIN: 11MIN: 10.97MIN: 10.941. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUCBa0.87921.75842.63763.51684.3963.907592.709122.55860MIN: 3.46MIN: 2.47MIN: 2.441. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUCBa0.69711.39422.09132.78843.48553.048173.009173.09829MIN: 2.61MIN: 2.93MIN: 2.941. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUCBa2K4K6K8K10K11646.0011575.608712.07MIN: 11481.1MIN: 11484.4MIN: 8593.521. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUCBa130026003900520065006146.325891.155531.19MIN: 6015.19MIN: 5819.44MIN: 5047.071. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUCBa3K6K9K12K15K12419.511553.510530.1MIN: 12136.1MIN: 11456.1MIN: 10283.81. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUCBa132639526555.9346.3446.29MIN: 43.27MIN: 45.85MIN: 45.91. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUCBa2040608010091.0388.5367.24MIN: 84.63MIN: 81.12MIN: 60.941. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPUCBa112233445545.0547.4347.59MIN: 44.45MIN: 47.03MIN: 47.051. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUCBa130026003900520065005924.855885.495842.10MIN: 5824.25MIN: 5795.49MIN: 5759.921. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUCBa1.09412.18823.28234.37645.47054.862824.699343.09830MIN: 3.88MIN: 3.41MIN: 2.941. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUCBa3K6K9K12K15K11871.211562.211316.1MIN: 11485.9MIN: 11467.7MIN: 11021.61. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUCBa130026003900520065006265.975933.915690.09MIN: 6014.76MIN: 5831.79MIN: 5283.511. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUCBa0.44310.88621.32931.77242.21551.969511.946281.78597MIN: 1.63MIN: 1.63MIN: 1.561. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPUCBa4812162015.0814.7413.45MIN: 14.17MIN: 11.7MIN: 11.711. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Y-Cruncher

Y-Cruncher is a multi-threaded Pi benchmark capable of computing Pi to trillions of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.7.10.9513Pi Digits To Calculate: 1Ba306090120150138.93

39 Results Shown

AOM AV1:
  Speed 0 Two-Pass - Bosphorus 4K
  Speed 4 Two-Pass - Bosphorus 4K
  Speed 6 Realtime - Bosphorus 4K
  Speed 6 Two-Pass - Bosphorus 4K
  Speed 8 Realtime - Bosphorus 4K
  Speed 9 Realtime - Bosphorus 4K
  Speed 10 Realtime - Bosphorus 4K
  Speed 0 Two-Pass - Bosphorus 1080p
  Speed 4 Two-Pass - Bosphorus 1080p
  Speed 6 Realtime - Bosphorus 1080p
  Speed 6 Two-Pass - Bosphorus 1080p
  Speed 8 Realtime - Bosphorus 1080p
  Speed 9 Realtime - Bosphorus 1080p
  Speed 10 Realtime - Bosphorus 1080p
oneDNN:
  IP Shapes 1D - f32 - CPU
  IP Shapes 3D - f32 - CPU
  IP Shapes 1D - u8s8f32 - CPU
  IP Shapes 3D - u8s8f32 - CPU
  IP Shapes 1D - bf16bf16bf16 - CPU
  IP Shapes 3D - bf16bf16bf16 - CPU
  Convolution Batch Shapes Auto - f32 - CPU
  Deconvolution Batch shapes_1d - f32 - CPU
  Deconvolution Batch shapes_3d - f32 - CPU
  Convolution Batch Shapes Auto - u8s8f32 - CPU
  Deconvolution Batch shapes_1d - u8s8f32 - CPU
  Deconvolution Batch shapes_3d - u8s8f32 - CPU
  Recurrent Neural Network Training - f32 - CPU
  Recurrent Neural Network Inference - f32 - CPU
  Recurrent Neural Network Training - u8s8f32 - CPU
  Convolution Batch Shapes Auto - bf16bf16bf16 - CPU
  Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU
  Deconvolution Batch shapes_3d - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - u8s8f32 - CPU
  Matrix Multiply Batch Shapes Transformer - f32 - CPU
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
  Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU
  Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPU
Y-Cruncher