lnxbuild-9-9900

Intel Core i9-9900 testing with a Gigabyte Z370 AORUS Ultra Gaming-CF (F16a BIOS) and Sapphire AMD Radeon RX 470/480/570/570X/580/580X/590 8GB on ManjaroLinux 20.2 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 2012162-HA-LNXBUILD968
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:

C/C++ Compiler Tests 2 Tests
CPU Massive 7 Tests
Creator Workloads 3 Tests
HPC - High Performance Computing 2 Tests
Machine Learning 2 Tests
Multi-Core 4 Tests
Python 2 Tests
Server CPU Tests 6 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
Perf-Per
Dollar
Date
Triggered
  Test
  Duration
lnxbuild-i9-9900-20201213
December 13 2020
  5 Minutes
numpy
December 13 2020
  10 Minutes
graphics-magick-2.02
December 13 2020
  22 Minutes
cython-i9-9900
December 13 2020
  1 Minute
x265
December 13 2020
  3 Minutes
ramspeed
December 14 2020
  31 Minutes
lz4
December 14 2020
  15 Minutes
onednn
December 14 2020
  9 Minutes
onednn-2nd
December 15 2020
  5 Minutes
onednn-100A
December 15 2020
  13 Minutes
onednn-110A
December 15 2020
  16 Minutes
numpy-110A
December 15 2020
  10 Minutes
build-linux-ker-110A
December 15 2020
 
build-linux-kernel-110A
December 15 2020
  6 Minutes
build-linux-kernel-110A-2nd
December 15 2020
  6 Minutes
onednn-50A
December 16 2020
 
onednn-75A
December 16 2020
 
onednn-85A
December 16 2020
  15 Minutes
onednn-95A
December 16 2020
 
onednn-95A-perf
December 16 2020
  13 Minutes
build-linux-ker-95A-perf
December 16 2020
  6 Minutes
numpy-95A
December 16 2020
  10 Minutes
Invert Hiding All Results Option
  9 Minutes
Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):


lnxbuild-9-9900OpenBenchmarking.orgPhoronix Test Suite 10.4.0m1Intel Core i9-9900 @ 5.00GHz (8 Cores / 16 Threads)Gigabyte Z370 AORUS Ultra Gaming-CF (F16a BIOS)Intel 8th/9th64GB960GB Corsair Force MP510 + 1000GB KINGSTON SA2000M81000G + 512GB Crucial CT512MX1 + 120GB INTEL SSDSC2CT12 + 3001GB TOSHIBA HDWA130 + 320GB Western Digital WD3200AAJS-0960GB Corsair Force MP510 + 1000GB KINGSTON SA2000M81000G + 512GB Crucial CT512MX1 + 120GB INTEL SSDSC2CT12 + 320GB Western Digital WD3200AAJS-0 + 3001GB TOSHIBA HDWA130Sapphire AMD Radeon RX 470/480/570/570X/580/580X/590 8GB (1340/2000MHz)Realtek ALC1220Q3279WG5BIntel I219-V + Realtek RTL8125 2.5GbEManjaroLinux 20.25.4.74-1-MANJARO (x86_64)Xfce 4.14X Server 1.20.94.6 Mesa 20.2.1 (LLVM 10.0.1)1.2.131GCC 10.2.0 + Clang 10.0.1 + LLVM 10.0.1ext42560x1440ProcessorMotherboardChipsetMemoryDisksGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionLnxbuild-9-9900 BenchmarksSystem Logs- lnxbuild-i9-9900-20201213, graphics-magick-2.02, x265, ramspeed, lz4, onednn, onednn-2nd, onednn-100A, onednn-110A, build-linux-ker-110A, build-linux-kernel-110A, build-linux-kernel-110A-2nd, onednn-50A, onednn-75A, onednn-85A, onednn-95A, onednn-95A-perf, build-linux-ker-95A-perf: --disable-libssp --disable-libstdcxx-pch --disable-libunwind-exceptions --disable-werror --enable-__cxa_atexit --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-install-libiberty --enable-languages=c,c++,ada,fortran,go,lto,objc,obj-c++,d --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-isl --with-linker-hash-style=gnu - lnxbuild-i9-9900-20201213: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- numpy: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- graphics-magick-2.02: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- cython-i9-9900: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- x265: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- ramspeed: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- lz4: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- onednn: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- onednn-2nd: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- onednn-100A: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- onednn-110A: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- numpy-110A: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- build-linux-ker-110A: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- build-linux-kernel-110A: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- build-linux-kernel-110A-2nd: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- onednn-50A: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- onednn-75A: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- onednn-85A: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- onednn-95A: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- onednn-95A-perf: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd6- build-linux-ker-95A-perf: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd6- numpy-95A: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd6- itlb_multihit: KVM: Mitigation of Split huge pages + 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: Mitigation of TSX disabled + tsx_async_abort: Mitigation of TSX disabled - numpy, numpy-110A, numpy-95A: sh: /home/axel/scripts/python: Is a directory + Python 3.8.6

lnxbuild-9-9900build-linux-kernel: Time To Compilenumpy: graphics-magick: Swirlgraphics-magick: Rotategraphics-magick: Sharpengraphics-magick: Enhancedgraphics-magick: Resizinggraphics-magick: Noise-Gaussiangraphics-magick: HWB Color Spacecython-bench: x265: Bosphorus 4Kx265: Bosphorus 1080pramspeed: Add - Integerramspeed: Copy - Integerramspeed: Scale - Integerramspeed: Triad - Integerramspeed: Average - Integerramspeed: Add - Floating Pointramspeed: Copy - Floating Pointramspeed: Scale - Floating Pointramspeed: Triad - Floating Pointramspeed: Average - Floating Pointcompress-lz4: 1 - Compression Speedcompress-lz4: 1 - Decompression Speedcompress-lz4: 3 - Compression Speedcompress-lz4: 3 - Decompression Speedcompress-lz4: 9 - Compression Speedcompress-lz4: 9 - Decompression Speedonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUlnxbuild-i9-9900-20201213numpygraphics-magick-2.02cython-i9-9900x265ramspeedlz4onednnonednn-2ndonednn-100Aonednn-110Anumpy-110Abuild-linux-ker-110Abuild-linux-kernel-110Abuild-linux-kernel-110A-2ndonednn-50Aonednn-75Aonednn-85Aonednn-95Aonednn-95A-perfbuild-linux-ker-95A-perfnumpy-95A92.993407.9538590312519891625099119.27013.7458.7129055.4527155.6327346.4529067.3128109.8629031.4027112.4826991.0528851.2527859.369023.6210993.355.3310670.554.2210681.83524.473603.603376.724138.194090.904072.842230.752213.442258.73415.80104.180104.5854712.014619.164611.114347.414268.154279.40111.861414.96OpenBenchmarking.org

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To Compilelnxbuild-i9-9900-20201213build-linux-kernel-110Abuild-linux-kernel-110A-2ndbuild-linux-ker-95A-perf306090120150SE +/- 0.44, N = 3SE +/- 0.75, N = 3SE +/- 0.94, N = 3SE +/- 0.80, N = 393.89104.18104.59111.86
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To Compilelnxbuild-i9-9900-20201213build-linux-kernel-110Abuild-linux-kernel-110A-2ndbuild-linux-ker-95A-perf20406080100Min: 93.28 / Avg: 93.89 / Max: 94.74Min: 103.31 / Avg: 104.18 / Max: 105.67Min: 103.54 / Avg: 104.58 / Max: 106.46Min: 110.87 / Avg: 111.86 / Max: 113.44

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy Benchmarknumpynumpy-110Anumpy-95A90180270360450SE +/- 2.49, N = 3SE +/- 0.46, N = 3SE +/- 2.64, N = 3407.95415.80414.96
OpenBenchmarking.orgScore, More Is BetterNumpy Benchmarknumpynumpy-110Anumpy-95A70140210280350Min: 403.27 / Avg: 407.95 / Max: 411.78Min: 415.13 / Avg: 415.8 / Max: 416.69Min: 411.42 / Avg: 414.96 / Max: 420.13

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Swirlgraphics-magick-2.0280160240320400SE +/- 2.96, N = 33851. (CC) gcc options: -fopenmp -O2 -pthread -lwebp -lwebpmux -llcms2 -ltiff -lfreetype -ljasper -ljpeg -lwmflite -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Rotategraphics-magick-2.022004006008001000SE +/- 17.09, N = 39031. (CC) gcc options: -fopenmp -O2 -pthread -lwebp -lwebpmux -llcms2 -ltiff -lfreetype -ljasper -ljpeg -lwmflite -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Sharpengraphics-magick-2.02306090120150SE +/- 0.88, N = 31251. (CC) gcc options: -fopenmp -O2 -pthread -lwebp -lwebpmux -llcms2 -ltiff -lfreetype -ljasper -ljpeg -lwmflite -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Enhancedgraphics-magick-2.024080120160200SE +/- 0.58, N = 31981. (CC) gcc options: -fopenmp -O2 -pthread -lwebp -lwebpmux -llcms2 -ltiff -lfreetype -ljasper -ljpeg -lwmflite -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Resizinggraphics-magick-2.022004006008001000SE +/- 1.45, N = 39161. (CC) gcc options: -fopenmp -O2 -pthread -lwebp -lwebpmux -llcms2 -ltiff -lfreetype -ljasper -ljpeg -lwmflite -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Noise-Gaussiangraphics-magick-2.0250100150200250SE +/- 0.88, N = 32501. (CC) gcc options: -fopenmp -O2 -pthread -lwebp -lwebpmux -llcms2 -ltiff -lfreetype -ljasper -ljpeg -lwmflite -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: HWB Color Spacegraphics-magick-2.022004006008001000SE +/- 4.16, N = 39911. (CC) gcc options: -fopenmp -O2 -pthread -lwebp -lwebpmux -llcms2 -ltiff -lfreetype -ljasper -ljpeg -lwmflite -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

Cython benchmark

Stress benchmark tests to measure time consumed by cython code Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCython benchmark 0.27cython-i9-9900510152025SE +/- 0.09, N = 319.27

x265

This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4Kx26548121620SE +/- 0.19, N = 313.741. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080px2651326395265SE +/- 0.33, N = 358.711. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: Integerramspeed6K12K18K24K30KSE +/- 48.95, N = 329055.451. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Integerramspeed6K12K18K24K30KSE +/- 71.40, N = 327155.631. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: Integerramspeed6K12K18K24K30KSE +/- 42.10, N = 327346.451. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: Integerramspeed6K12K18K24K30KSE +/- 51.19, N = 329067.311. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Integerramspeed6K12K18K24K30KSE +/- 12.51, N = 328109.861. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: Floating Pointramspeed6K12K18K24K30KSE +/- 33.84, N = 329031.401. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Floating Pointramspeed6K12K18K24K30KSE +/- 118.85, N = 327112.481. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: Floating Pointramspeed6K12K18K24K30KSE +/- 93.32, N = 326991.051. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: Floating Pointramspeed6K12K18K24K30KSE +/- 81.41, N = 328851.251. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Floating Pointramspeed6K12K18K24K30KSE +/- 172.31, N = 327859.361. (CC) gcc options: -O3 -march=native

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (an Ubuntu ISO) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 1 - Compression Speedlz42K4K6K8K10KSE +/- 33.80, N = 39023.621. (CC) gcc options: -O3

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 1 - Decompression Speedlz42K4K6K8K10KSE +/- 16.15, N = 310993.31. (CC) gcc options: -O3

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Compression Speedlz41224364860SE +/- 0.74, N = 355.331. (CC) gcc options: -O3

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Decompression Speedlz42K4K6K8K10KSE +/- 29.16, N = 310670.51. (CC) gcc options: -O3

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Compression Speedlz41224364860SE +/- 0.65, N = 354.221. (CC) gcc options: -O3

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Decompression Speedlz42K4K6K8K10KSE +/- 19.59, N = 310681.81. (CC) gcc options: -O3

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUonednnonednn-2ndonednn-100Aonednn-85Aonednn-95A-perf10002000300040005000SE +/- 3.52, N = 3SE +/- 3.87, N = 3SE +/- 47.28, N = 3SE +/- 75.66, N = 4SE +/- 35.82, N = 33524.473376.724138.194712.014347.41MIN: 3399.85MIN: 3279.05MIN: 3969.52MIN: 4509.55MIN: 4183.071. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUonednnonednn-2ndonednn-100Aonednn-85Aonednn-95A-perf8001600240032004000Min: 3517.99 / Avg: 3524.47 / Max: 3530.1Min: 3369.17 / Avg: 3376.72 / Max: 3381.95Min: 4077.52 / Avg: 4138.19 / Max: 4231.33Min: 4628.05 / Avg: 4712.01 / Max: 4938.82Min: 4287.06 / Avg: 4347.41 / Max: 4411.011. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUonednnonednn-100Aonednn-85Aonednn-95A-perf10002000300040005000SE +/- 64.64, N = 3SE +/- 12.66, N = 3SE +/- 11.04, N = 3SE +/- 1.11, N = 33603.604090.904619.164268.15MIN: 3422.52MIN: 3976.87MIN: 4506.42MIN: 4186.61. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUonednnonednn-100Aonednn-85Aonednn-95A-perf8001600240032004000Min: 3520.46 / Avg: 3603.6 / Max: 3730.9Min: 4066.48 / Avg: 4090.9 / Max: 4108.92Min: 4599.07 / Avg: 4619.16 / Max: 4637.12Min: 4266.46 / Avg: 4268.15 / Max: 4270.241. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUonednn-100Aonednn-85Aonednn-95A-perf10002000300040005000SE +/- 4.63, N = 3SE +/- 13.05, N = 3SE +/- 4.23, N = 34072.844611.114279.40MIN: 3971.73MIN: 4509.24MIN: 4184.411. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUonednn-100Aonednn-85Aonednn-95A-perf8001600240032004000Min: 4063.72 / Avg: 4072.84 / Max: 4078.77Min: 4585.27 / Avg: 4611.11 / Max: 4627.17Min: 4271.98 / Avg: 4279.4 / Max: 4286.631. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUonednn-110A5001000150020002500SE +/- 30.45, N = 62230.75MIN: 1639.681. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUonednn-110A5001000150020002500SE +/- 5.34, N = 32213.44MIN: 2125.381. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUonednn-110A5001000150020002500SE +/- 39.39, N = 32258.73MIN: 2123.731. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread