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.
A Kernel Notes: Transparent Huge Pages: madviseCompiler 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 -vProcessor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8701021Java Notes: OpenJDK Runtime Environment (build 11.0.13+8-Ubuntu-0ubuntu1.20.04)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
B 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: DELL S2409W, Network: Intel I211 + Realtek RTL8822BE 802.11a/b/g/n/ac
OS: Ubuntu 20.04, Kernel: 5.11.0-43-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.13, Vulkan: 1.2.128, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080
OpenBenchmarking.org FPS, More Is Better libgav1 0.17 Video Input: Summer Nature 4K B 3 A 14 28 42 56 70 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 63.67 63.71 63.77 1. (CXX) g++ options: -O3 -lpthread -lrt
OpenBenchmarking.org FPS, More Is Better libgav1 0.17 Video Input: Summer Nature 1080p B A 3 40 80 120 160 200 SE +/- 0.14, N = 3 SE +/- 0.16, N = 3 198.03 198.41 198.48 1. (CXX) g++ options: -O3 -lpthread -lrt
OpenBenchmarking.org FPS, More Is Better libgav1 0.17 Video Input: Chimera 1080p 10-bit B 3 A 12 24 36 48 60 SE +/- 0.10, N = 3 SE +/- 0.01, N = 3 51.69 51.75 51.81 1. (CXX) g++ options: -O3 -lpthread -lrt
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K B 3 A 0.0428 0.0856 0.1284 0.1712 0.214 SE +/- 0.00, N = 3 SE +/- 0.00, N = 4 0.18 0.18 0.19 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K B 3 A 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 6.00 6.00 6.03 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K B A 3 4 8 12 16 20 SE +/- 0.11, N = 15 SE +/- 0.18, N = 3 14.35 14.47 14.64 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K A B 3 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 10.92 10.94 10.94 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K B 3 A 9 18 27 36 45 SE +/- 0.41, N = 3 SE +/- 0.66, N = 3 40.21 40.53 41.47 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K A 3 B 12 24 36 48 60 SE +/- 0.75, N = 3 SE +/- 0.52, N = 15 49.39 50.85 51.51 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K A B 3 12 24 36 48 60 SE +/- 0.66, N = 15 SE +/- 0.82, N = 15 49.58 51.47 52.26 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p 3 A B 0.1013 0.2026 0.3039 0.4052 0.5065 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.44 0.45 0.45 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p 3 A B 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 10.27 10.28 10.29 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p B 3 A 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 8.37 8.45 8.52 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p 3 A B 7 14 21 28 35 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 28.11 28.26 28.26 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p B A 3 20 40 60 80 100 SE +/- 0.34, N = 3 SE +/- 0.30, N = 3 94.49 95.77 96.49 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p A 3 B 30 60 90 120 150 SE +/- 0.43, N = 3 SE +/- 0.58, N = 3 115.90 117.74 118.04 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p 3 B A 30 60 90 120 150 SE +/- 1.64, N = 4 SE +/- 0.98, N = 14 122.97 123.89 124.99 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
perf-bench This test profile is used for running Linux perf-bench, the benchmark support within the Linux kernel's perf tool. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GB/sec, More Is Better perf-bench Benchmark: Memcpy 1MB B A 3 4 8 12 16 20 SE +/- 0.20, N = 3 SE +/- 0.09, N = 3 14.44 14.47 14.87 1. (CC) gcc options: -pthread -shared -lunwind-x86_64 -lunwind -llzma -Xlinker -export-dynamic -O6 -ggdb3 -funwind-tables -std=gnu99 -fPIC -lnuma
OpenBenchmarking.org GB/sec, More Is Better perf-bench Benchmark: Memset 1MB 3 B A 16 32 48 64 80 SE +/- 0.77, N = 7 SE +/- 0.10, N = 3 69.68 72.61 73.52 1. (CC) gcc options: -pthread -shared -lunwind-x86_64 -lunwind -llzma -Xlinker -export-dynamic -O6 -ggdb3 -funwind-tables -std=gnu99 -fPIC -lnuma
OSPray OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: particle_volume/ao/real_time A B 3 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 23.47 23.59 23.64
OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: particle_volume/scivis/real_time A B 3 5 10 15 20 25 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 22.41 22.52 22.58
OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: particle_volume/pathtracer/real_time A B 3 50 100 150 200 250 SE +/- 0.20, N = 3 SE +/- 0.34, N = 3 241.19 241.55 241.93
OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: gravity_spheres_volume/dim_512/ao/real_time 3 A B 0.5881 1.1762 1.7643 2.3524 2.9405 SE +/- 0.00623, N = 3 SE +/- 0.00062, N = 3 2.35183 2.55935 2.61399
OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time 3 A B 0.5644 1.1288 1.6932 2.2576 2.822 SE +/- 0.00092, N = 3 SE +/- 0.00142, N = 3 2.26083 2.46619 2.50856
OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time 3 B A 0.9143 1.8286 2.7429 3.6572 4.5715 SE +/- 0.00418, N = 3 SE +/- 0.00423, N = 3 4.05074 4.06095 4.06373
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Update Random A 3 B 140K 280K 420K 560K 700K SE +/- 1748.11, N = 3 SE +/- 1055.36, N = 3 654775 654806 656248 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Read While Writing A B 3 700K 1400K 2100K 2800K 3500K SE +/- 9707.64, N = 3 SE +/- 10292.52, N = 3 3222053 3254000 3256160 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Read Random Write Random A 3 B 500K 1000K 1500K 2000K 2500K SE +/- 5611.13, N = 3 SE +/- 18963.04, N = 3 2368822 2380613 2383189 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
perf-bench This test profile is used for running Linux perf-bench, the benchmark support within the Linux kernel's perf tool. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Epoll Wait A B 3 7K 14K 21K 28K 35K SE +/- 344.15, N = 3 SE +/- 354.56, N = 3 29976 32098 33429 1. (CC) gcc options: -pthread -shared -lunwind-x86_64 -lunwind -llzma -Xlinker -export-dynamic -O6 -ggdb3 -funwind-tables -std=gnu99 -fPIC -lnuma
OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Futex Hash A B 3 1000K 2000K 3000K 4000K 5000K SE +/- 3374.73, N = 3 SE +/- 6656.67, N = 3 4799340 4819775 4823523 1. (CC) gcc options: -pthread -shared -lunwind-x86_64 -lunwind -llzma -Xlinker -export-dynamic -O6 -ggdb3 -funwind-tables -std=gnu99 -fPIC -lnuma
OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Sched Pipe 3 B A 90K 180K 270K 360K 450K SE +/- 2490.82, N = 3 SE +/- 3062.78, N = 3 403227 403760 403883 1. (CC) gcc options: -pthread -shared -lunwind-x86_64 -lunwind -llzma -Xlinker -export-dynamic -O6 -ggdb3 -funwind-tables -std=gnu99 -fPIC -lnuma
OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Futex Lock-Pi B 3 A 100 200 300 400 500 SE +/- 5.21, N = 6 SE +/- 5.17, N = 3 461 461 482 1. (CC) gcc options: -pthread -shared -lunwind-x86_64 -lunwind -llzma -Xlinker -export-dynamic -O6 -ggdb3 -funwind-tables -std=gnu99 -fPIC -lnuma
OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Syscall Basic 3 A B 5M 10M 15M 20M 25M SE +/- 147824.81, N = 3 SE +/- 156358.13, N = 3 20407433 20487873 21592179 1. (CC) gcc options: -pthread -shared -lunwind-x86_64 -lunwind -llzma -Xlinker -export-dynamic -O6 -ggdb3 -funwind-tables -std=gnu99 -fPIC -lnuma
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 Intel oneAPI. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU B A 3 1.0494 2.0988 3.1482 4.1976 5.247 SE +/- 0.00368, N = 3 SE +/- 0.00958, N = 3 4.66399 4.66061 4.65093 MIN: 4.46 MIN: 4.46 MIN: 4.43 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU A B 3 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 11.04 10.65 10.28 MIN: 10.91 MIN: 10.46 MIN: 9.94 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU 3 B A 0.2927 0.5854 0.8781 1.1708 1.4635 SE +/- 0.00084, N = 3 SE +/- 0.00156, N = 3 1.30085 1.30043 1.29867 MIN: 1.28 MIN: 1.28 MIN: 1.28 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU A 3 B 0.1779 0.3558 0.5337 0.7116 0.8895 SE +/- 0.006963, N = 3 SE +/- 0.004439, N = 3 0.790537 0.789330 0.788060 MIN: 0.75 MIN: 0.73 MIN: 0.73 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU
A: The test run did not produce a result.
B: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
3: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU
A: The test run did not produce a result.
B: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
3: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU A B 3 5 10 15 20 25 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 20.62 20.58 20.53 MIN: 20.48 MIN: 20.41 MIN: 20.37 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU B 3 A 0.9667 1.9334 2.9001 3.8668 4.8335 SE +/- 0.02203, N = 3 SE +/- 0.02789, N = 3 4.29655 4.21857 4.17083 MIN: 3.93 MIN: 3.9 MIN: 3.93 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU B A 3 0.9901 1.9802 2.9703 3.9604 4.9505 SE +/- 0.02200, N = 3 SE +/- 0.01112, N = 3 4.40032 4.37595 4.37283 MIN: 4.28 MIN: 4.28 MIN: 4.26 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU A B 3 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 23.24 23.04 22.99 MIN: 23.08 MIN: 22.84 MIN: 22.71 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU B A 3 0.4157 0.8314 1.2471 1.6628 2.0785 SE +/- 0.00549, N = 3 SE +/- 0.00506, N = 3 1.84743 1.84739 1.84706 MIN: 1.78 MIN: 1.78 MIN: 1.79 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU 3 B A 0.5767 1.1534 1.7301 2.3068 2.8835 SE +/- 0.01307, N = 3 SE +/- 0.00703, N = 3 2.56316 2.55214 2.54310 MIN: 2.46 MIN: 2.44 MIN: 2.48 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU B A 3 1100 2200 3300 4400 5500 SE +/- 21.94, N = 3 SE +/- 15.57, N = 3 5136.73 5129.54 5075.49 MIN: 5068.06 MIN: 5095.07 MIN: 5015.99 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU A B 3 600 1200 1800 2400 3000 SE +/- 26.03, N = 3 SE +/- 28.67, N = 3 2677.16 2638.95 2581.96 MIN: 2661.56 MIN: 2574.31 MIN: 2502.81 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU B A 3 1100 2200 3300 4400 5500 SE +/- 34.54, N = 3 SE +/- 19.61, N = 3 5119.53 5117.44 5091.02 MIN: 5034.39 MIN: 5086.78 MIN: 5027.14 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU
A: The test run did not produce a result.
B: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
3: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU
A: The test run did not produce a result.
B: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
3: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU
A: The test run did not produce a result.
B: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
3: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU B A 3 600 1200 1800 2400 3000 SE +/- 41.03, N = 3 SE +/- 7.94, N = 3 2610.48 2600.06 2540.71 MIN: 2529.82 MIN: 2582.7 MIN: 2495.84 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU 3 B A 0.179 0.358 0.537 0.716 0.895 SE +/- 0.000562, N = 3 SE +/- 0.004119, N = 3 0.795531 0.792154 0.789443 MIN: 0.75 MIN: 0.74 MIN: 0.74 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU B A 3 1100 2200 3300 4400 5500 SE +/- 12.81, N = 3 SE +/- 56.24, N = 3 5149.07 5135.11 5093.46 MIN: 5102.61 MIN: 5111.68 MIN: 4939.21 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU A B 3 600 1200 1800 2400 3000 SE +/- 20.31, N = 3 SE +/- 15.15, N = 3 2653.01 2596.92 2556.63 MIN: 2610.08 MIN: 2539.82 MIN: 2510.01 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU 3 B A 0.1579 0.3158 0.4737 0.6316 0.7895 SE +/- 0.005860, N = 3 SE +/- 0.001462, N = 3 0.701676 0.680813 0.679415 MIN: 0.63 MIN: 0.61 MIN: 0.62 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU
A: The test run did not produce a result.
B: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
3: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
OSPray Studio Intel OSPray Studio is an open-source, interactive visualization and ray-tracing software package. OSPray Studio makes use of Intel OSPray, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer A B 3 400 800 1200 1600 2000 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 1854 1852 1850 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer 3 B A 400 800 1200 1600 2000 SE +/- 2.65, N = 3 SE +/- 1.86, N = 3 1907 1906 1904 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer 3 B A 500 1000 1500 2000 2500 SE +/- 1.76, N = 3 2223 2219 2216 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer A 3 B 6K 12K 18K 24K 30K SE +/- 13.72, N = 3 29566 29541 29498 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer A 3 B 14K 28K 42K 56K 70K SE +/- 54.01, N = 3 SE +/- 76.21, N = 3 65388 65296 65291 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer A 3 B 7K 14K 21K 28K 35K SE +/- 11.15, N = 3 SE +/- 17.17, N = 3 30384 30296 30283 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer B A 3 14K 28K 42K 56K 70K SE +/- 63.26, N = 3 SE +/- 128.74, N = 3 67035 66843 66701 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer 3 A B 8K 16K 24K 32K 40K SE +/- 45.40, N = 3 SE +/- 21.28, N = 3 35404 35312 35299 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer A 3 B 16K 32K 48K 64K 80K SE +/- 50.93, N = 3 SE +/- 55.43, N = 3 76950 76892 76891 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.10 Encoder Speed: 10, Lossless B A 3 1.2749 2.5498 3.8247 5.0996 6.3745 SE +/- 0.046, N = 3 SE +/- 0.019, N = 3 5.666 5.622 5.596 1. (CXX) g++ options: -O3 -fPIC -lm
A Kernel Notes: Transparent Huge Pages: madviseCompiler 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 -vProcessor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8701021Java Notes: OpenJDK Runtime Environment (build 11.0.13+8-Ubuntu-0ubuntu1.20.04)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 11 April 2022 18:30 by user phoronix.
B Kernel Notes: Transparent Huge Pages: madviseCompiler 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 -vProcessor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8701021Java Notes: OpenJDK Runtime Environment (build 11.0.13+8-Ubuntu-0ubuntu1.20.04)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 11 April 2022 20:26 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: DELL S2409W, Network: Intel I211 + Realtek RTL8822BE 802.11a/b/g/n/ac
OS: Ubuntu 20.04, Kernel: 5.11.0-43-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.13, Vulkan: 1.2.128, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler 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 -vProcessor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8701021Java Notes: OpenJDK Runtime Environment (build 11.0.13+8-Ubuntu-0ubuntu1.20.04)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 12 April 2022 04:33 by user phoronix.