oidn onednn

Intel Core i9-13900K testing with a ASUS PRIME Z790-P WIFI (0812 BIOS) and AMD Radeon RX 7900 XTX 24GB on Ubuntu 23.10 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 2310123-PTS-OIDNONED01
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
Intel oneAPI 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
October 12 2023
  48 Minutes
b
October 12 2023
  51 Minutes
c
October 12 2023
  53 Minutes
Invert Hiding All Results Option
  51 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):


oidn onednnOpenBenchmarking.orgPhoronix Test SuiteIntel Core i9-13900K @ 5.50GHz (24 Cores / 32 Threads)ASUS PRIME Z790-P WIFI (0812 BIOS)Intel Device 7a2732GBWestern Digital WD_BLACK SN850X 1000GBAMD Radeon RX 7900 XTX 24GB (2304/1249MHz)Realtek ALC897ASUS VP28UUbuntu 23.106.5.0-7-generic (x86_64)GNOME Shell 45.0X Server + Wayland4.6 Mesa 23.2.1-1ubuntu3 (LLVM 15.0.7 DRM 3.54)GCC 13.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionOidn Onednn 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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/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: 0x119 - Thermald 2.5.4 - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

abcResult OverviewPhoronix Test Suite100%102%105%107%110%oneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNIntel Open Image DenoiseIntel Open Image DenoiseIntel Open Image DenoiseIP Shapes 1D - f32 - CPUD.B.s - f32 - CPUIP Shapes 1D - u8s8f32 - CPUC.B.S.A - f32 - CPUR.N.N.I - bf16bf16bf16 - CPUR.N.N.T - u8s8f32 - CPUR.N.N.T - f32 - CPUD.B.s - u8s8f32 - CPUD.B.s - f32 - CPUC.B.S.A - u8s8f32 - CPUD.B.s - u8s8f32 - CPUR.N.N.T - bf16bf16bf16 - CPUIP Shapes 3D - f32 - CPUR.N.N.I - u8s8f32 - CPUIP Shapes 3D - u8s8f32 - CPUR.N.N.I - f32 - CPURT.hdr_alb_nrm.3840x2160 - CPU-OnlyRT.ldr_alb_nrm.3840x2160 - CPU-OnlyRTLightmap.hdr.4096x4096 - CPU-Only

oidn onednnoidn: RT.hdr_alb_nrm.3840x2160 - CPU-Onlyoidn: RT.ldr_alb_nrm.3840x2160 - CPU-Onlyoidn: RTLightmap.hdr.4096x4096 - CPU-Onlyonednn: 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: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUabc0.670.670.331.834944.126160.6937360.6957926.001046.758114.044365.924990.9929531.593802109.871091.632139.931092.272138.321107.240.670.670.332.013074.179640.7226800.7039045.956606.832823.976245.963970.9922691.580942123.001094.822117.341079.342125.441105.660.670.670.331.976254.141790.6876030.6985156.242317.120423.993145.867111.0072151.565562155.381083.282164.011088.582154.151079.33OpenBenchmarking.org

Intel Open Image Denoise

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Onlyabc0.15080.30160.45240.60320.754SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 30.670.670.67
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Onlyabc246810Min: 0.67 / Avg: 0.67 / Max: 0.68Min: 0.66 / Avg: 0.67 / Max: 0.68Min: 0.67 / Avg: 0.67 / Max: 0.68

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Onlyabc0.15080.30160.45240.60320.754SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.670.670.67
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Onlyabc246810Min: 0.66 / Avg: 0.67 / Max: 0.67Min: 0.67 / Avg: 0.67 / Max: 0.68Min: 0.67 / Avg: 0.67 / Max: 0.67

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RTLightmap.hdr.4096x4096 - Device: CPU-Onlyabc0.07430.14860.22290.29720.3715SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.330.330.33
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RTLightmap.hdr.4096x4096 - Device: CPU-Onlyabc12345Min: 0.33 / Avg: 0.33 / Max: 0.33Min: 0.33 / Avg: 0.33 / Max: 0.33Min: 0.33 / Avg: 0.33 / Max: 0.33

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUabc0.45290.90581.35871.81162.2645SE +/- 0.00124, N = 3SE +/- 0.01347, N = 3SE +/- 0.00479, N = 31.834942.013071.97625MIN: 1.58MIN: 1.58MIN: 1.581. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUabc246810Min: 1.83 / Avg: 1.83 / Max: 1.84Min: 2 / Avg: 2.01 / Max: 2.04Min: 1.97 / Avg: 1.98 / Max: 1.981. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUabc0.94041.88082.82123.76164.702SE +/- 0.01877, N = 3SE +/- 0.01855, N = 3SE +/- 0.01054, N = 34.126164.179644.14179MIN: 3.85MIN: 3.89MIN: 3.91. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUabc246810Min: 4.11 / Avg: 4.13 / Max: 4.16Min: 4.14 / Avg: 4.18 / Max: 4.21Min: 4.13 / Avg: 4.14 / Max: 4.161. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUabc0.16260.32520.48780.65040.813SE +/- 0.003785, N = 3SE +/- 0.004468, N = 3SE +/- 0.000543, N = 30.6937360.7226800.687603MIN: 0.62MIN: 0.62MIN: 0.621. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUabc246810Min: 0.69 / Avg: 0.69 / Max: 0.7Min: 0.71 / Avg: 0.72 / Max: 0.73Min: 0.69 / Avg: 0.69 / Max: 0.691. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUabc0.15840.31680.47520.63360.792SE +/- 0.003205, N = 3SE +/- 0.003187, N = 3SE +/- 0.003928, N = 30.6957920.7039040.698515MIN: 0.58MIN: 0.6MIN: 0.591. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUabc246810Min: 0.69 / Avg: 0.7 / Max: 0.7Min: 0.7 / Avg: 0.7 / Max: 0.71Min: 0.69 / Avg: 0.7 / Max: 0.711. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUabc246810SE +/- 0.07544, N = 3SE +/- 0.03828, N = 3SE +/- 0.02742, N = 36.001045.956606.24231MIN: 5.53MIN: 5.67MIN: 5.461. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUabc246810Min: 5.89 / Avg: 6 / Max: 6.14Min: 5.89 / Avg: 5.96 / Max: 6.02Min: 6.19 / Avg: 6.24 / Max: 6.281. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUabc246810SE +/- 0.08251, N = 4SE +/- 0.08585, N = 15SE +/- 0.13608, N = 156.758116.832827.12042MIN: 2.64MIN: 2.59MIN: 2.611. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUabc3691215Min: 6.55 / Avg: 6.76 / Max: 6.92Min: 6.51 / Avg: 6.83 / Max: 7.72Min: 6.38 / Avg: 7.12 / Max: 7.861. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUabc0.911.822.733.644.55SE +/- 0.11784, N = 15SE +/- 0.08784, N = 15SE +/- 0.11227, N = 154.044363.976243.99314MIN: 3.39MIN: 3.37MIN: 3.381. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUabc246810Min: 3.58 / Avg: 4.04 / Max: 5.09Min: 3.51 / Avg: 3.98 / Max: 4.67Min: 3.51 / Avg: 3.99 / Max: 4.951. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUabc1.34192.68384.02575.36766.7095SE +/- 0.02525, N = 3SE +/- 0.02944, N = 3SE +/- 0.03630, N = 35.924995.963975.86711MIN: 4.78MIN: 4.87MIN: 4.861. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUabc246810Min: 5.89 / Avg: 5.92 / Max: 5.97Min: 5.91 / Avg: 5.96 / Max: 6Min: 5.82 / Avg: 5.87 / Max: 5.941. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUabc0.22660.45320.67980.90641.133SE +/- 0.007985, N = 15SE +/- 0.009400, N = 15SE +/- 0.006142, N = 30.9929530.9922691.007215MIN: 0.86MIN: 0.86MIN: 0.861. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUabc246810Min: 0.95 / Avg: 0.99 / Max: 1.08Min: 0.94 / Avg: 0.99 / Max: 1.1Min: 1 / Avg: 1.01 / Max: 1.021. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUabc0.35860.71721.07581.43441.793SE +/- 0.03076, N = 15SE +/- 0.02186, N = 15SE +/- 0.01738, N = 151.593801.580941.56556MIN: 1.42MIN: 1.42MIN: 1.421. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUabc246810Min: 1.45 / Avg: 1.59 / Max: 1.84Min: 1.46 / Avg: 1.58 / Max: 1.78Min: 1.45 / Avg: 1.57 / Max: 1.691. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUabc5001000150020002500SE +/- 25.97, N = 3SE +/- 24.29, N = 3SE +/- 10.68, N = 32109.872123.002155.38MIN: 1942.02MIN: 1953.79MIN: 1933.951. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUabc400800120016002000Min: 2058.13 / Avg: 2109.87 / Max: 2139.62Min: 2089.15 / Avg: 2123 / Max: 2170.1Min: 2134.49 / Avg: 2155.38 / Max: 2169.71. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUabc2004006008001000SE +/- 10.88, N = 3SE +/- 13.48, N = 4SE +/- 8.50, N = 101091.631094.821083.28MIN: 981.79MIN: 981.46MIN: 977.311. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUabc2004006008001000Min: 1070.39 / Avg: 1091.63 / Max: 1106.33Min: 1055.86 / Avg: 1094.82 / Max: 1116.06Min: 1032.93 / Avg: 1083.28 / Max: 1111.491. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUabc5001000150020002500SE +/- 16.32, N = 3SE +/- 19.76, N = 3SE +/- 4.65, N = 32139.932117.342164.01MIN: 1934.49MIN: 1947.46MIN: 1943.271. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUabc400800120016002000Min: 2113.34 / Avg: 2139.93 / Max: 2169.63Min: 2087.04 / Avg: 2117.34 / Max: 2154.45Min: 2155 / Avg: 2164.01 / Max: 2170.51. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUabc2004006008001000SE +/- 11.13, N = 6SE +/- 12.74, N = 4SE +/- 13.94, N = 31092.271079.341088.58MIN: 980.94MIN: 979.13MIN: 982.991. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUabc2004006008001000Min: 1047.21 / Avg: 1092.27 / Max: 1119.45Min: 1056.69 / Avg: 1079.34 / Max: 1111.09Min: 1061.39 / Avg: 1088.58 / Max: 1107.561. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUabc5001000150020002500SE +/- 21.78, N = 3SE +/- 20.94, N = 3SE +/- 7.75, N = 32138.322125.442154.15MIN: 1963.87MIN: 1948.17MIN: 1942.21. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUabc400800120016002000Min: 2095.8 / Avg: 2138.32 / Max: 2167.77Min: 2089.09 / Avg: 2125.44 / Max: 2161.64Min: 2138.73 / Avg: 2154.15 / Max: 2163.271. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUabc2004006008001000SE +/- 5.86, N = 3SE +/- 2.39, N = 3SE +/- 14.03, N = 31107.241105.661079.33MIN: 982.65MIN: 984.41MIN: 9811. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUabc2004006008001000Min: 1097.65 / Avg: 1107.24 / Max: 1117.87Min: 1101.01 / Avg: 1105.66 / Max: 1108.92Min: 1061.85 / Avg: 1079.33 / Max: 1107.071. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl