3800XT Sat AMD Ryzen 7 3800XT 8-Core testing with a MSI X370 XPOWER GAMING TITANIUM (MS-7A31) v1.0 (1.MS BIOS) and Sapphire AMD Radeon HD 4650 on Debian 10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2012128-HA-3800XTSAT00&grs&rdt&rro .
3800XT Sat Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Display Server Display Driver Compiler File-System Screen Resolution 1 2 3 AMD Ryzen 7 3800XT 8-Core @ 3.90GHz (8 Cores / 16 Threads) MSI X370 XPOWER GAMING TITANIUM (MS-7A31) v1.0 (1.MS BIOS) AMD Starship/Matisse 16GB 128GB INTEL SSDPEKKW128G7 Sapphire AMD Radeon HD 4650 AMD RV710/730 Intel I211 Debian 10 4.19.0-13-amd64 (x86_64) X Server 1.20.4 modesetting 1.20.4 GCC 8.3.0 ext4 1024x768 OpenBenchmarking.org Compiler 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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v Disk Details - NONE / errors=remount-ro,relatime,rw / Block Size: 4096 Processor Details - Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8701021 Python Details - Python 2.7.16 + Python 3.7.3 Security 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
3800XT Sat sqlite-speedtest: Timed Time - Size 1,000 compilebench: Read Compiled Tree onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU compilebench: Compile onednn: Recurrent Neural Network Inference - f32 - CPU onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU build-ffmpeg: Time To Compile onednn: Recurrent Neural Network Inference - u8s8f32 - CPU onednn: IP Shapes 3D - f32 - CPU onednn: Recurrent Neural Network Training - f32 - CPU mafft: Multiple Sequence Alignment - LSU RNA brl-cad: VGR Performance Metric onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU onednn: Recurrent Neural Network Training - u8s8f32 - CPU onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU graphics-magick: Rotate onednn: Deconvolution Batch shapes_1d - f32 - CPU onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU graphics-magick: Enhanced onednn: IP Shapes 1D - u8s8f32 - CPU graphics-magick: Noise-Gaussian graphics-magick: Swirl onednn: IP Shapes 1D - f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU hmmer: Pfam Database Search onednn: Deconvolution Batch shapes_3d - f32 - CPU onednn: IP Shapes 3D - u8s8f32 - CPU graphics-magick: Resizing onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU coremark: CoreMark Size 666 - Iterations Per Second onednn: Convolution Batch Shapes Auto - f32 - CPU graphics-magick: HWB Color Space graphics-magick: Sharpen compilebench: Initial Create 1 2 3 54.909 4171.63 5.07364 844.54 2568.38 2534.48 47.869 2576.03 8.53716 3769.89 11.629 128159 2.79548 3771.02 6.15886 849 4.90950 3770.04 213 2.52954 267 575 4.48965 4.86878 98.329 6.46414 2.21579 1163 20.0259 383032.552244 22.2703 1366 140 669.49 56.328 4088.29 5.12100 853.74 2579.11 2569.94 47.241 2545.55 8.53066 3739.63 11.539 127169 2.78793 3764.83 6.12533 846 4.93803 3768.24 213 2.52521 267 573 4.49317 4.88063 98.413 6.47656 2.21160 1165 20.0112 383539.030274 22.2539 1366 140 702.73 4131.97 5.02533 860.27 2541.56 2566.17 2571.76 8.62494 3753.45 11.536 2.77572 3747.44 6.12171 851 4.91964 3752.15 214 2.53552 268 573 4.50496 4.86841 98.563 6.47200 2.21205 1164 20.0379 22.2635 1366 140 738.06 OpenBenchmarking.org
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 2 1 13 26 39 52 65 SE +/- 0.63, N = 7 SE +/- 0.26, N = 3 56.33 54.91 1. (CC) gcc options: -O2 -ldl -lz -lpthread
Compile Bench Test: Read Compiled Tree OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Read Compiled Tree 3 2 1 900 1800 2700 3600 4500 SE +/- 21.72, N = 3 SE +/- 16.29, N = 3 SE +/- 1.89, N = 3 4131.97 4088.29 4171.63
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU 3 2 1 1.1522 2.3044 3.4566 4.6088 5.761 SE +/- 0.00124, N = 3 SE +/- 0.06972, N = 3 SE +/- 0.02389, N = 3 5.02533 5.12100 5.07364 MIN: 4.88 MIN: 4.87 MIN: 4.89 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Compile Bench Test: Compile OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Compile 3 2 1 200 400 600 800 1000 SE +/- 2.82, N = 3 SE +/- 3.60, N = 3 SE +/- 13.31, N = 9 860.27 853.74 844.54
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU 3 2 1 600 1200 1800 2400 3000 SE +/- 10.80, N = 3 SE +/- 10.92, N = 3 SE +/- 35.65, N = 3 2541.56 2579.11 2568.38 MIN: 2508.49 MIN: 2557.19 MIN: 2521.85 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU 3 2 1 600 1200 1800 2400 3000 SE +/- 20.57, N = 3 SE +/- 16.22, N = 3 SE +/- 3.40, N = 3 2566.17 2569.94 2534.48 MIN: 2529.35 MIN: 2528.06 MIN: 2508.43 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Timed FFmpeg Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed FFmpeg Compilation 4.2.2 Time To Compile 2 1 11 22 33 44 55 SE +/- 0.03, N = 3 SE +/- 0.75, N = 3 47.24 47.87
oneDNN Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU 3 2 1 600 1200 1800 2400 3000 SE +/- 3.99, N = 3 SE +/- 5.82, N = 3 SE +/- 14.58, N = 3 2571.76 2545.55 2576.03 MIN: 2531.02 MIN: 2511.67 MIN: 2532.36 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU 3 2 1 2 4 6 8 10 SE +/- 0.09450, N = 3 SE +/- 0.01733, N = 3 SE +/- 0.01048, N = 3 8.62494 8.53066 8.53716 MIN: 8.21 MIN: 8.26 MIN: 8.22 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU 3 2 1 800 1600 2400 3200 4000 SE +/- 24.47, N = 3 SE +/- 10.99, N = 3 SE +/- 29.93, N = 3 3753.45 3739.63 3769.89 MIN: 3695.8 MIN: 3685.61 MIN: 3713.41 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Timed MAFFT Alignment Multiple Sequence Alignment - LSU RNA OpenBenchmarking.org Seconds, Fewer Is Better Timed MAFFT Alignment 7.471 Multiple Sequence Alignment - LSU RNA 3 2 1 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 11.54 11.54 11.63 1. (CC) gcc options: -std=c99 -O3 -lm -lpthread
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.30.8 VGR Performance Metric 2 1 30K 60K 90K 120K 150K 127169 128159 1. (CXX) g++ options: -std=c++11 -pipe -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -rdynamic -lSM -lICE -lXi -lGLU -lGL -lGLdispatch -lX11 -lXext -lXrender -lpthread -ldl -luuid -lm
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU 3 2 1 0.629 1.258 1.887 2.516 3.145 SE +/- 0.00253, N = 3 SE +/- 0.01568, N = 3 SE +/- 0.01991, N = 3 2.77572 2.78793 2.79548 MIN: 2.65 MIN: 2.63 MIN: 2.63 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU 3 2 1 800 1600 2400 3200 4000 SE +/- 12.83, N = 3 SE +/- 13.00, N = 3 SE +/- 13.24, N = 3 3747.44 3764.83 3771.02 MIN: 3684.06 MIN: 3699.18 MIN: 3719.14 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU 3 2 1 2 4 6 8 10 SE +/- 0.03095, N = 3 SE +/- 0.04876, N = 3 SE +/- 0.10060, N = 3 6.12171 6.12533 6.15886 MIN: 5.87 MIN: 5.89 MIN: 5.84 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
GraphicsMagick Operation: Rotate OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Rotate 3 2 1 200 400 600 800 1000 SE +/- 1.15, N = 3 SE +/- 1.86, N = 3 SE +/- 3.06, N = 3 851 846 849 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU 3 2 1 1.1111 2.2222 3.3333 4.4444 5.5555 SE +/- 0.01083, N = 3 SE +/- 0.03223, N = 3 SE +/- 0.00858, N = 3 4.91964 4.93803 4.90950 MIN: 4.82 MIN: 4.8 MIN: 4.81 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU 3 2 1 800 1600 2400 3200 4000 SE +/- 13.59, N = 3 SE +/- 14.92, N = 3 SE +/- 28.06, N = 3 3752.15 3768.24 3770.04 MIN: 3695.13 MIN: 3711.2 MIN: 3712.68 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
GraphicsMagick Operation: Enhanced OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Enhanced 3 2 1 50 100 150 200 250 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 214 213 213 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
oneDNN Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU 3 2 1 0.5705 1.141 1.7115 2.282 2.8525 SE +/- 0.02336, N = 3 SE +/- 0.01188, N = 3 SE +/- 0.01920, N = 3 2.53552 2.52521 2.52954 MIN: 2.46 MIN: 2.45 MIN: 2.47 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
GraphicsMagick Operation: Noise-Gaussian OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Noise-Gaussian 3 2 1 60 120 180 240 300 268 267 267 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Swirl OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Swirl 3 2 1 120 240 360 480 600 SE +/- 2.91, N = 3 SE +/- 1.86, N = 3 SE +/- 0.88, N = 3 573 573 575 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU 3 2 1 1.0136 2.0272 3.0408 4.0544 5.068 SE +/- 0.01172, N = 3 SE +/- 0.00277, N = 3 SE +/- 0.00257, N = 3 4.50496 4.49317 4.48965 MIN: 4.4 MIN: 4.37 MIN: 4.37 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU 3 2 1 1.0981 2.1962 3.2943 4.3924 5.4905 SE +/- 0.00553, N = 3 SE +/- 0.00199, N = 3 SE +/- 0.00398, N = 3 4.86841 4.88063 4.86878 MIN: 4.79 MIN: 4.81 MIN: 4.7 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 3.3.1 Pfam Database Search 3 2 1 20 40 60 80 100 SE +/- 0.13, N = 3 SE +/- 0.10, N = 3 SE +/- 0.25, N = 3 98.56 98.41 98.33 1. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU 3 2 1 2 4 6 8 10 SE +/- 0.00848, N = 3 SE +/- 0.00280, N = 3 SE +/- 0.00490, N = 3 6.47200 6.47656 6.46414 MIN: 6.24 MIN: 6.29 MIN: 6.27 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU 3 2 1 0.4986 0.9972 1.4958 1.9944 2.493 SE +/- 0.00084, N = 3 SE +/- 0.00062, N = 3 SE +/- 0.00129, N = 3 2.21205 2.21160 2.21579 MIN: 2.15 MIN: 2.15 MIN: 2.15 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Resizing 3 2 1 300 600 900 1200 1500 SE +/- 0.67, N = 3 SE +/- 2.08, N = 3 1164 1165 1163 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU 3 2 1 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 20.04 20.01 20.03 MIN: 19.59 MIN: 19.67 MIN: 19.61 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second 2 1 80K 160K 240K 320K 400K SE +/- 1349.13, N = 3 SE +/- 5758.12, N = 3 383539.03 383032.55 1. (CC) gcc options: -O2 -lrt" -lrt
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU 3 2 1 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 22.26 22.25 22.27 MIN: 22.07 MIN: 22.01 MIN: 22.06 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: HWB Color Space 3 2 1 300 600 900 1200 1500 SE +/- 0.67, N = 3 SE +/- 1.20, N = 3 SE +/- 0.33, N = 3 1366 1366 1366 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Sharpen 3 2 1 30 60 90 120 150 140 140 140 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Compile Bench Test: Initial Create OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Initial Create 3 2 1 160 320 480 640 800 SE +/- 10.61, N = 3 SE +/- 28.61, N = 3 SE +/- 31.98, N = 3 738.06 702.73 669.49
Phoronix Test Suite v10.8.5