3950X svt

AMD Ryzen 9 3950X 16-Core testing with a ASUS ROG CROSSHAIR VII HERO (WI-FI) (3103 BIOS) and Sapphire AMD Radeon RX 470/480/570/570X/580/580X/590 4GB on Ubuntu 20.04 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 2103153-HA-3950XSVT011
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:

CPU Massive 4 Tests
Creator Workloads 3 Tests
Encoding 2 Tests
Multi-Core 4 Tests
Server CPU Tests 4 Tests
Video Encoding 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
1
March 15 2021
  47 Minutes
2
March 15 2021
  40 Minutes
3
March 15 2021
  53 Minutes
Invert Hiding All Results Option
  47 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

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,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 (Boost: Enabled) - CPU Microcode: 0x8701021
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: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

2

3

Processor: AMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VII HERO (WI-FI) (3103 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: Samsung SSD 970 EVO 250GB, Graphics: Sapphire AMD Radeon RX 470/480/570/570X/580/580X/590 4GB (1260/1750MHz), Audio: AMD Ellesmere HDMI Audio, Monitor: VA2431, Network: Intel I211 + Realtek RTL8822BE 802.11a/b/g/n/ac

OS: Ubuntu 20.04, Kernel: 5.9.0-050900rc6daily20200922-generic (x86_64) 20200921, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.9, OpenGL: 4.6 Mesa 20.0.8 (LLVM 10.0.0), Vulkan: 1.2.128, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080

3950X svtProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen Resolution123AMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR VII HERO (WI-FI) (3103 BIOS)AMD Starship/Matisse16GBSamsung SSD 970 EVO 250GBSapphire AMD Radeon RX 470/480/570/570X/580/580X/590 4GB (1260/1750MHz)AMD Ellesmere HDMI AudioVA2431Intel I211 + Realtek RTL8822BE 802.11a/b/g/n/acUbuntu 20.045.9.0-050900rc6daily20200922-generic (x86_64) 20200921GNOME Shell 3.36.4X Server 1.20.94.6 Mesa 20.0.8 (LLVM 10.0.0)1.2.128GCC 9.3.0ext41920x1080OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,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 (Boost: Enabled) - CPU Microcode: 0x8701021Security 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: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

123Result OverviewPhoronix Test Suite100%100%101%101%oneDNNSVT-HEVCSVT-VP9Sysbench

3950X svtsvt-hevc: 1 - Bosphorus 1080psvt-hevc: 7 - Bosphorus 1080psvt-hevc: 10 - Bosphorus 1080psvt-vp9: VMAF Optimized - Bosphorus 1080psvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080psvt-vp9: Visual Quality Optimized - Bosphorus 1080ponednn: 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 - CPUsysbench: RAM / Memorysysbench: CPU12314.83185.78313.54213.01217.00198.944.593478.202561.349930.63269120.18436.843254.3634121.88221.854312.565384564.792169.854546.422166.900.7122234601.112207.391.574008802.7235178.0314.83184.77313.10212.78216.41198.844.672918.473071.354420.66673820.29696.862414.3764122.08441.837522.552564609.002202.794603.702156.840.7178154619.772172.401.572558816.8235172.4214.87185.40313.32212.46216.88199.404.673738.579861.351230.68941220.34846.861424.3602522.14411.841772.551694642.112173.764696.752171.520.7202224610.742196.621.570428822.4735182.76OpenBenchmarking.org

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080p32148121620SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 314.8714.8314.831. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080p32148121620Min: 14.83 / Avg: 14.87 / Max: 14.92Min: 14.76 / Avg: 14.83 / Max: 14.93Min: 14.75 / Avg: 14.83 / Max: 14.951. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080p3214080120160200SE +/- 0.49, N = 3SE +/- 0.59, N = 3SE +/- 0.15, N = 3185.40184.77185.781. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080p321306090120150Min: 184.45 / Avg: 185.4 / Max: 186.05Min: 184.05 / Avg: 184.77 / Max: 185.93Min: 185.53 / Avg: 185.78 / Max: 186.051. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080p32170140210280350SE +/- 0.59, N = 3SE +/- 0.11, N = 3SE +/- 0.88, N = 3313.32313.10313.541. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080p32160120180240300Min: 312.5 / Avg: 313.32 / Max: 314.47Min: 312.99 / Avg: 313.1 / Max: 313.32Min: 311.85 / Avg: 313.54 / Max: 314.81. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080p32150100150200250SE +/- 0.15, N = 3SE +/- 0.35, N = 3SE +/- 0.25, N = 3212.46212.78213.011. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080p3214080120160200Min: 212.31 / Avg: 212.46 / Max: 212.75Min: 212.1 / Avg: 212.78 / Max: 213.22Min: 212.5 / Avg: 213.01 / Max: 213.281. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p32150100150200250SE +/- 0.54, N = 3SE +/- 0.27, N = 3SE +/- 0.59, N = 3216.88216.41217.001. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p3214080120160200Min: 215.84 / Avg: 216.88 / Max: 217.63Min: 215.93 / Avg: 216.41 / Max: 216.87Min: 215.83 / Avg: 217 / Max: 217.691. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080p3214080120160200SE +/- 0.11, N = 3SE +/- 0.14, N = 3SE +/- 0.10, N = 3199.40198.84198.941. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080p3214080120160200Min: 199.26 / Avg: 199.4 / Max: 199.61Min: 198.64 / Avg: 198.84 / Max: 199.12Min: 198.74 / Avg: 198.94 / Max: 199.051. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -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 the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU3211.05162.10323.15484.20645.258SE +/- 0.00892, N = 3SE +/- 0.00547, N = 3SE +/- 0.00553, N = 34.673734.672914.59347MIN: 4.46MIN: 4.46MIN: 4.331. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU321246810Min: 4.66 / Avg: 4.67 / Max: 4.69Min: 4.66 / Avg: 4.67 / Max: 4.68Min: 4.58 / Avg: 4.59 / Max: 4.61. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU321246810SE +/- 0.01948, N = 3SE +/- 0.00869, N = 3SE +/- 0.03344, N = 38.579868.473078.20256MIN: 8.21MIN: 8.11MIN: 7.771. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU3213691215Min: 8.54 / Avg: 8.58 / Max: 8.61Min: 8.46 / Avg: 8.47 / Max: 8.49Min: 8.14 / Avg: 8.2 / Max: 8.261. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU3210.30470.60940.91411.21881.5235SE +/- 0.00222, N = 3SE +/- 0.00659, N = 3SE +/- 0.00281, N = 31.351231.354421.34993MIN: 1.32MIN: 1.32MIN: 1.321. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU321246810Min: 1.35 / Avg: 1.35 / Max: 1.35Min: 1.34 / Avg: 1.35 / Max: 1.37Min: 1.35 / Avg: 1.35 / Max: 1.351. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU3210.15510.31020.46530.62040.7755SE +/- 0.008883, N = 3SE +/- 0.003939, N = 3SE +/- 0.007730, N = 30.6894120.6667380.632691MIN: 0.64MIN: 0.61MIN: 0.571. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU321246810Min: 0.68 / Avg: 0.69 / Max: 0.71Min: 0.66 / Avg: 0.67 / Max: 0.67Min: 0.62 / Avg: 0.63 / Max: 0.651. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU321510152025SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 320.3520.3020.18MIN: 19.91MIN: 19.84MIN: 19.81. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU321510152025Min: 20.31 / Avg: 20.35 / Max: 20.41Min: 20.29 / Avg: 20.3 / Max: 20.31Min: 20.17 / Avg: 20.18 / Max: 20.21. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU321246810SE +/- 0.00853, N = 3SE +/- 0.00168, N = 3SE +/- 0.00880, N = 36.861426.862416.84325MIN: 3.53MIN: 3.85MIN: 3.541. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU3213691215Min: 6.84 / Avg: 6.86 / Max: 6.87Min: 6.86 / Avg: 6.86 / Max: 6.87Min: 6.83 / Avg: 6.84 / Max: 6.861. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU3210.98471.96942.95413.93884.9235SE +/- 0.01339, N = 3SE +/- 0.00857, N = 3SE +/- 0.01253, N = 34.360254.376414.36341MIN: 4.24MIN: 4.28MIN: 4.251. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU321246810Min: 4.33 / Avg: 4.36 / Max: 4.38Min: 4.36 / Avg: 4.38 / Max: 4.39Min: 4.34 / Avg: 4.36 / Max: 4.381. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU321510152025SE +/- 0.13, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 322.1422.0821.88MIN: 21.88MIN: 21.83MIN: 21.681. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU321510152025Min: 22.01 / Avg: 22.14 / Max: 22.4Min: 21.98 / Avg: 22.08 / Max: 22.14Min: 21.87 / Avg: 21.88 / Max: 21.911. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU3210.41720.83441.25161.66882.086SE +/- 0.00383, N = 3SE +/- 0.00518, N = 3SE +/- 0.01267, N = 31.841771.837521.85431MIN: 1.79MIN: 1.79MIN: 1.791. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU321246810Min: 1.83 / Avg: 1.84 / Max: 1.85Min: 1.83 / Avg: 1.84 / Max: 1.85Min: 1.83 / Avg: 1.85 / Max: 1.881. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU3210.57721.15441.73162.30882.886SE +/- 0.00214, N = 3SE +/- 0.00351, N = 3SE +/- 0.00851, N = 32.551692.552562.56538MIN: 2.44MIN: 2.45MIN: 2.461. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU321246810Min: 2.55 / Avg: 2.55 / Max: 2.56Min: 2.55 / Avg: 2.55 / Max: 2.56Min: 2.55 / Avg: 2.57 / Max: 2.581. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU32110002000300040005000SE +/- 16.33, N = 3SE +/- 13.05, N = 3SE +/- 22.44, N = 34642.114609.004564.79MIN: 4601.29MIN: 4555.25MIN: 45051. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU3218001600240032004000Min: 4623.77 / Avg: 4642.11 / Max: 4674.68Min: 4584.17 / Avg: 4609 / Max: 4628.4Min: 4522.47 / Avg: 4564.79 / Max: 4598.871. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU3215001000150020002500SE +/- 8.37, N = 3SE +/- 18.47, N = 3SE +/- 8.25, N = 32173.762202.792169.85MIN: 2144.26MIN: 2154.97MIN: 2147.841. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU321400800120016002000Min: 2159.48 / Avg: 2173.76 / Max: 2188.48Min: 2166.43 / Avg: 2202.79 / Max: 2226.64Min: 2159.32 / Avg: 2169.85 / Max: 2186.121. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU32110002000300040005000SE +/- 6.15, N = 3SE +/- 38.20, N = 3SE +/- 19.10, N = 34696.754603.704546.42MIN: 4659.16MIN: 4517.77MIN: 4491.771. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU3218001600240032004000Min: 4686.64 / Avg: 4696.75 / Max: 4707.88Min: 4556.1 / Avg: 4603.7 / Max: 4679.25Min: 4515.06 / Avg: 4546.42 / Max: 4580.991. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU3215001000150020002500SE +/- 10.21, N = 3SE +/- 2.21, N = 3SE +/- 8.14, N = 32171.522156.842166.90MIN: 2143.49MIN: 2144.96MIN: 2143.781. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU321400800120016002000Min: 2152.48 / Avg: 2171.52 / Max: 2187.42Min: 2154.03 / Avg: 2156.84 / Max: 2161.21Min: 2157.2 / Avg: 2166.9 / Max: 2183.071. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU3210.1620.3240.4860.6480.81SE +/- 0.002170, N = 3SE +/- 0.001394, N = 3SE +/- 0.001931, N = 30.7202220.7178150.712223MIN: 0.7MIN: 0.69MIN: 0.691. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU321246810Min: 0.72 / Avg: 0.72 / Max: 0.72Min: 0.72 / Avg: 0.72 / Max: 0.72Min: 0.71 / Avg: 0.71 / Max: 0.711. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU32110002000300040005000SE +/- 41.24, N = 3SE +/- 24.40, N = 3SE +/- 27.16, N = 34610.744619.774601.11MIN: 4494.78MIN: 4564.55MIN: 4523.451. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU3218001600240032004000Min: 4528.67 / Avg: 4610.74 / Max: 4658.81Min: 4592.28 / Avg: 4619.77 / Max: 4668.43Min: 4550.89 / Avg: 4601.11 / Max: 4644.151. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU3215001000150020002500SE +/- 18.66, N = 13SE +/- 13.75, N = 3SE +/- 22.26, N = 82196.622172.402207.39MIN: 2144.76MIN: 2144.29MIN: 2144.071. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU321400800120016002000Min: 2157.28 / Avg: 2196.62 / Max: 2412.71Min: 2153.9 / Avg: 2172.4 / Max: 2199.27Min: 2161.31 / Avg: 2207.39 / Max: 2354.481. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU3210.35420.70841.06261.41681.771SE +/- 0.00081, N = 3SE +/- 0.00439, N = 3SE +/- 0.00339, N = 31.570421.572551.57400MIN: 1.52MIN: 1.52MIN: 1.521. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU321246810Min: 1.57 / Avg: 1.57 / Max: 1.57Min: 1.56 / Avg: 1.57 / Max: 1.58Min: 1.57 / Avg: 1.57 / Max: 1.581. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Sysbench

This is a benchmark of Sysbench with the built-in CPU and memory sub-tests. Sysbench is a scriptable multi-threaded benchmark tool based on LuaJIT. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/sec, More Is BetterSysbench 1.0.20Test: RAM / Memory3212K4K6K8K10KSE +/- 15.46, N = 3SE +/- 9.00, N = 3SE +/- 15.29, N = 38822.478816.828802.721. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm
OpenBenchmarking.orgMiB/sec, More Is BetterSysbench 1.0.20Test: RAM / Memory32115003000450060007500Min: 8805.17 / Avg: 8822.47 / Max: 8853.32Min: 8800.77 / Avg: 8816.82 / Max: 8831.91Min: 8782.33 / Avg: 8802.72 / Max: 8832.661. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 1.0.20Test: CPU3218K16K24K32K40KSE +/- 2.97, N = 3SE +/- 8.57, N = 3SE +/- 2.48, N = 335182.7635172.4235178.031. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm
OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 1.0.20Test: CPU3216K12K18K24K30KMin: 35176.87 / Avg: 35182.76 / Max: 35186.43Min: 35155.87 / Avg: 35172.42 / Max: 35184.55Min: 35173.59 / Avg: 35178.03 / Max: 35182.161. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm

1

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,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 (Boost: Enabled) - CPU Microcode: 0x8701021
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: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 15 March 2021 10:20 by user phoronix.

2

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,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 (Boost: Enabled) - CPU Microcode: 0x8701021
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: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 15 March 2021 11:32 by user phoronix.

3

Processor: AMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VII HERO (WI-FI) (3103 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: Samsung SSD 970 EVO 250GB, Graphics: Sapphire AMD Radeon RX 470/480/570/570X/580/580X/590 4GB (1260/1750MHz), Audio: AMD Ellesmere HDMI Audio, Monitor: VA2431, Network: Intel I211 + Realtek RTL8822BE 802.11a/b/g/n/ac

OS: Ubuntu 20.04, Kernel: 5.9.0-050900rc6daily20200922-generic (x86_64) 20200921, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.9, OpenGL: 4.6 Mesa 20.0.8 (LLVM 10.0.0), Vulkan: 1.2.128, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,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 (Boost: Enabled) - CPU Microcode: 0x8701021
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: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 15 March 2021 12:26 by user phoronix.