Ryzen 7 2700 oneDNN 2.0

AMD Ryzen 7 2700 Eight-Core testing with a Gigabyte AB350N-Gaming WIFI-CF (F20 BIOS) and HIS AMD Radeon HD 6450/7450/8450 / R5 230 OEM 1GB on Ubuntu 19.10 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 2012101-HA-RYZEN727034
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

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
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
1
December 10 2020
  40 Minutes
2
December 10 2020
  43 Minutes
3
December 10 2020
  36 Minutes
Invert Hiding All Results Option
  40 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):

1

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x800820b
Security Notes: itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

2

3

Processor: AMD Ryzen 7 2700 Eight-Core @ 3.20GHz (8 Cores / 16 Threads), Motherboard: Gigabyte AB350N-Gaming WIFI-CF (F20 BIOS), Chipset: AMD 17h, Memory: 16GB, Disk: 120GB ADATA SU700, Graphics: HIS AMD Radeon HD 6450/7450/8450 / R5 230 OEM 1GB, Audio: AMD Caicos HDMI Audio, Monitor: DELL S2409W, Network: Realtek RTL8111/8168/8411 + Intel 3165

OS: Ubuntu 19.10, Kernel: 5.9.0-050900rc7daily20201004-generic (x86_64) 20201003, Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 3.3 Mesa 19.2.8 (LLVM 9.0.0), Compiler: GCC 9.2.1 20191008, File-System: ext4, Screen Resolution: 1920x1080

Ryzen 7 2700 oneDNN 2.0ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen Resolution123AMD Ryzen 7 2700 Eight-Core @ 3.20GHz (8 Cores / 16 Threads)Gigabyte AB350N-Gaming WIFI-CF (F20 BIOS)AMD 17h16GB120GB ADATA SU700HIS AMD Radeon HD 6450/7450/8450 / R5 230 OEM 1GBAMD Caicos HDMI AudioDELL S2409WRealtek RTL8111/8168/8411 + Intel 3165Ubuntu 19.105.9.0-050900rc7daily20201004-generic (x86_64) 20201003GNOME Shell 3.34.1X Server 1.20.5modesetting 1.20.53.3 Mesa 19.2.8 (LLVM 9.0.0)GCC 9.2.1 20191008ext41920x1080OpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x800820bSecurity Details- itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

123Result OverviewPhoronix Test Suite100%104%107%111%115%oneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNND.B.s - u8s8f32 - CPUD.B.s - f32 - CPUIP Shapes 3D - u8s8f32 - CPUIP Shapes 1D - f32 - CPUIP Shapes 1D - u8s8f32 - CPUM.M.B.S.T - f32 - CPUR.N.N.T - f32 - CPUM.M.B.S.T - u8s8f32 - CPUR.N.N.T - bf16bf16bf16 - CPUIP Shapes 3D - f32 - CPUR.N.N.I - f32 - CPUR.N.N.T - u8s8f32 - CPUD.B.s - u8s8f32 - CPUR.N.N.I - u8s8f32 - CPUC.B.S.A - u8s8f32 - CPUD.B.s - f32 - CPUC.B.S.A - f32 - CPUR.N.N.I - bf16bf16bf16 - CPU

Ryzen 7 2700 oneDNN 2.0onednn: 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 - CPU1238.3021612.05366.411402.6160323.747310.258614.395924.243312.828512.62178137.114324.228213.834329.685.161288201.124336.816.044408.3840711.99056.471352.5676823.757410.525514.404724.190214.085512.66138199.884339.608222.434340.575.124238212.314335.516.043238.3194512.01976.446522.5670523.733410.323014.378924.186812.258412.62108159.584321.118188.934336.595.121438165.854338.296.08775OpenBenchmarking.org

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU321246810SE +/- 0.02622, N = 3SE +/- 0.00291, N = 3SE +/- 0.01659, N = 38.319458.384078.30216MIN: 8.14MIN: 8.22MIN: 8.091. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU3213691215Min: 8.28 / Avg: 8.32 / Max: 8.37Min: 8.38 / Avg: 8.38 / Max: 8.39Min: 8.28 / Avg: 8.3 / Max: 8.331. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU3213691215SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 312.0211.9912.05MIN: 11.56MIN: 11.59MIN: 11.71. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU32148121620Min: 11.97 / Avg: 12.02 / Max: 12.05Min: 11.98 / Avg: 11.99 / Max: 12.02Min: 12.02 / Avg: 12.05 / Max: 12.111. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU321246810SE +/- 0.01020, N = 3SE +/- 0.00778, N = 3SE +/- 0.00691, N = 36.446526.471356.41140MIN: 6.26MIN: 6.34MIN: 6.241. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU3213691215Min: 6.43 / Avg: 6.45 / Max: 6.46Min: 6.46 / Avg: 6.47 / Max: 6.49Min: 6.4 / Avg: 6.41 / Max: 6.421. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU3210.58861.17721.76582.35442.943SE +/- 0.00426, N = 3SE +/- 0.00219, N = 3SE +/- 0.00622, N = 32.567052.567682.61603MIN: 2.38MIN: 2.38MIN: 2.431. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU321246810Min: 2.56 / Avg: 2.57 / Max: 2.58Min: 2.56 / Avg: 2.57 / Max: 2.57Min: 2.61 / Avg: 2.62 / Max: 2.631. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU321612182430SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 323.7323.7623.75MIN: 23.31MIN: 23.17MIN: 23.071. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU321612182430Min: 23.71 / Avg: 23.73 / Max: 23.75Min: 23.69 / Avg: 23.76 / Max: 23.87Min: 23.73 / Avg: 23.75 / Max: 23.761. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU3213691215SE +/- 0.03, N = 3SE +/- 0.18, N = 13SE +/- 0.03, N = 310.3210.5310.26MIN: 10.12MIN: 10MIN: 10.091. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU3213691215Min: 10.26 / Avg: 10.32 / Max: 10.36Min: 10.28 / Avg: 10.53 / Max: 12.74Min: 10.21 / Avg: 10.26 / Max: 10.311. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU32148121620SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 314.3814.4014.40MIN: 14MIN: 13.99MIN: 13.971. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU32148121620Min: 14.37 / Avg: 14.38 / Max: 14.39Min: 14.37 / Avg: 14.4 / Max: 14.46Min: 14.33 / Avg: 14.4 / Max: 14.461. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU321612182430SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 324.1924.1924.24MIN: 23.43MIN: 23.15MIN: 23.551. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU321612182430Min: 24.17 / Avg: 24.19 / Max: 24.21Min: 24.16 / Avg: 24.19 / Max: 24.24Min: 24.19 / Avg: 24.24 / Max: 24.291. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU32148121620SE +/- 0.03, N = 3SE +/- 0.34, N = 15SE +/- 0.24, N = 1512.2614.0912.83MIN: 12.03MIN: 12MIN: 11.991. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU32148121620Min: 12.21 / Avg: 12.26 / Max: 12.3Min: 12.19 / Avg: 14.09 / Max: 15.22Min: 12.19 / Avg: 12.83 / Max: 15.021. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU3213691215SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 312.6212.6612.62MIN: 12.46MIN: 12.45MIN: 12.381. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU32148121620Min: 12.59 / Avg: 12.62 / Max: 12.65Min: 12.64 / Avg: 12.66 / Max: 12.71Min: 12.61 / Avg: 12.62 / Max: 12.641. (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: CPU3212K4K6K8K10KSE +/- 28.96, N = 3SE +/- 27.53, N = 3SE +/- 13.50, N = 38159.588199.888137.11MIN: 8099.23MIN: 8153.31MIN: 8105.81. (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: CPU32114002800420056007000Min: 8104.02 / Avg: 8159.58 / Max: 8201.55Min: 8159.36 / Avg: 8199.88 / Max: 8252.42Min: 8117.68 / Avg: 8137.11 / Max: 8163.071. (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: CPU3219001800270036004500SE +/- 17.01, N = 3SE +/- 6.18, N = 3SE +/- 5.49, N = 34321.114339.604324.22MIN: 4291.26MIN: 4322.49MIN: 4308.631. (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: CPU3218001600240032004000Min: 4299.06 / Avg: 4321.11 / Max: 4354.56Min: 4327.34 / Avg: 4339.6 / Max: 4347Min: 4316.57 / Avg: 4324.22 / Max: 4334.881. (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: CPU3212K4K6K8K10KSE +/- 33.99, N = 3SE +/- 19.08, N = 3SE +/- 16.68, N = 38188.938222.438213.83MIN: 8126.7MIN: 8176.89MIN: 8172.421. (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: CPU32114002800420056007000Min: 8135.8 / Avg: 8188.93 / Max: 8252.23Min: 8184.97 / Avg: 8222.43 / Max: 8247.43Min: 8180.71 / Avg: 8213.83 / Max: 8233.921. (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: CPU3219001800270036004500SE +/- 18.03, N = 3SE +/- 9.76, N = 3SE +/- 15.08, N = 34336.594340.574329.68MIN: 4309.62MIN: 4313.07MIN: 4300.391. (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: CPU3218001600240032004000Min: 4317.89 / Avg: 4336.59 / Max: 4372.65Min: 4326.95 / Avg: 4340.57 / Max: 4359.5Min: 4308.58 / Avg: 4329.68 / Max: 4358.891. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU3211.16132.32263.48394.64525.8065SE +/- 0.00382, N = 3SE +/- 0.00240, N = 3SE +/- 0.00286, N = 35.121435.124235.16128MIN: 4.9MIN: 5.01MIN: 5.061. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU321246810Min: 5.11 / Avg: 5.12 / Max: 5.13Min: 5.12 / Avg: 5.12 / Max: 5.13Min: 5.16 / Avg: 5.16 / Max: 5.171. (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: CPU3212K4K6K8K10KSE +/- 15.62, N = 3SE +/- 24.03, N = 3SE +/- 15.02, N = 38165.858212.318201.12MIN: 8128.51MIN: 8161.35MIN: 8176.441. (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: CPU32114002800420056007000Min: 8139.05 / Avg: 8165.85 / Max: 8193.16Min: 8170.63 / Avg: 8212.31 / Max: 8253.87Min: 8185.62 / Avg: 8201.12 / Max: 8231.151. (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: CPU3219001800270036004500SE +/- 9.76, N = 3SE +/- 15.49, N = 3SE +/- 11.38, N = 34338.294335.514336.81MIN: 4311.48MIN: 4295.9MIN: 4303.781. (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: CPU3218001600240032004000Min: 4318.85 / Avg: 4338.29 / Max: 4349.52Min: 4304.68 / Avg: 4335.51 / Max: 4353.64Min: 4314.17 / Avg: 4336.81 / Max: 4350.191. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU321246810SE +/- 0.02684, N = 3SE +/- 0.01029, N = 3SE +/- 0.01033, N = 36.087756.043236.04440MIN: 5.77MIN: 5.79MIN: 5.771. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU321246810Min: 6.05 / Avg: 6.09 / Max: 6.14Min: 6.02 / Avg: 6.04 / Max: 6.06Min: 6.03 / Avg: 6.04 / Max: 6.061. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

1

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x800820b
Security Notes: itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 10 December 2020 08:36 by user phoronix.

2

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x800820b
Security Notes: itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 10 December 2020 09:24 by user phoronix.

3

Processor: AMD Ryzen 7 2700 Eight-Core @ 3.20GHz (8 Cores / 16 Threads), Motherboard: Gigabyte AB350N-Gaming WIFI-CF (F20 BIOS), Chipset: AMD 17h, Memory: 16GB, Disk: 120GB ADATA SU700, Graphics: HIS AMD Radeon HD 6450/7450/8450 / R5 230 OEM 1GB, Audio: AMD Caicos HDMI Audio, Monitor: DELL S2409W, Network: Realtek RTL8111/8168/8411 + Intel 3165

OS: Ubuntu 19.10, Kernel: 5.9.0-050900rc7daily20201004-generic (x86_64) 20201003, Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 3.3 Mesa 19.2.8 (LLVM 9.0.0), Compiler: GCC 9.2.1 20191008, File-System: ext4, Screen Resolution: 1920x1080

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x800820b
Security Notes: itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 10 December 2020 10:24 by user phoronix.