Intel Core i9-10980XE testing with a ASRock X299 Steel Legend (P1.30 BIOS) and NVIDIA NV132 11GB on Ubuntu 20.04 via the Phoronix Test Suite.
Intel Core i9-10980XE Processor: Intel Core i9-10980XE @ 4.80GHz (18 Cores / 36 Threads), Motherboard: ASRock X299 Steel Legend (P1.30 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 32GB, Disk: Samsung SSD 970 PRO 512GB, Graphics: NVIDIA NV132 11GB, Audio: Realtek ALC1220, Monitor: DELL P2415Q, Network: Intel I219-V + Intel I211
OS: Ubuntu 20.04, Kernel: 5.4.0-18-generic (x86_64), Desktop: GNOME Shell 3.35.91, Display Server: X Server 1.20.7, Display Driver: modesetting 1.20.7, OpenGL: 4.3 Mesa 20.0.0, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160
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,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: intel_pstate powersave - CPU Microcode: 0x500012cPython Notes: + Python 3.8.2Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: XZ 0 - Process: Decompression Intel Core i9-10980XE 30 60 90 120 150 127 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Zstd 1 - Process: Compression Intel Core i9-10980XE 120 240 360 480 600 SE +/- 2.40, N = 3 551 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Zstd 1 - Process: Decompression Intel Core i9-10980XE 300 600 900 1200 1500 1501 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Zstd 8 - Process: Compression Intel Core i9-10980XE 20 40 60 80 100 SE +/- 0.33, N = 3 92 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Zstd 8 - Process: Decompression Intel Core i9-10980XE 300 600 900 1200 1500 SE +/- 1.15, N = 3 1484 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Crush 0 - Process: Compression Intel Core i9-10980XE 30 60 90 120 150 SE +/- 0.67, N = 3 120 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Crush 0 - Process: Decompression Intel Core i9-10980XE 110 220 330 440 550 SE +/- 0.58, N = 3 528 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Brotli 0 - Process: Compression Intel Core i9-10980XE 110 220 330 440 550 SE +/- 1.86, N = 3 502 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Brotli 0 - Process: Decompression Intel Core i9-10980XE 150 300 450 600 750 SE +/- 0.58, N = 3 706 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Brotli 2 - Process: Compression Intel Core i9-10980XE 50 100 150 200 250 220 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Brotli 2 - Process: Decompression Intel Core i9-10980XE 200 400 600 800 1000 819 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Libdeflate 1 - Process: Compression Intel Core i9-10980XE 50 100 150 200 250 245 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Libdeflate 1 - Process: Decompression Intel Core i9-10980XE 300 600 900 1200 1500 1328 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 32 Intel Core i9-10980XE 2K 4K 6K 8K 10K SE +/- 251.82, N = 15 9348.4 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 64 Intel Core i9-10980XE 1700 3400 5100 6800 8500 SE +/- 26.45, N = 3 7741.3 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 32 Intel Core i9-10980XE 2K 4K 6K 8K 10K SE +/- 37.38, N = 3 8174.5 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 64 Intel Core i9-10980XE 1600 3200 4800 6400 8000 SE +/- 23.46, N = 3 7688.6 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 128 Intel Core i9-10980XE 1600 3200 4800 6400 8000 SE +/- 85.14, N = 15 7368.5 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 256 Intel Core i9-10980XE 2K 4K 6K 8K 10K SE +/- 12.99, N = 3 8319.0 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 512 Intel Core i9-10980XE 2K 4K 6K 8K 10K SE +/- 72.43, N = 3 9159.9 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 128 Intel Core i9-10980XE 2K 4K 6K 8K 10K SE +/- 150.73, N = 3 9082.7 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 256 Intel Core i9-10980XE 2K 4K 6K 8K 10K SE +/- 26.80, N = 3 7821.0 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 512 Intel Core i9-10980XE 1600 3200 4800 6400 8000 SE +/- 42.17, N = 3 7532.7 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 1024 Intel Core i9-10980XE 2K 4K 6K 8K 10K SE +/- 128.62, N = 15 9090.2 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 2048 Intel Core i9-10980XE 2K 4K 6K 8K 10K SE +/- 152.55, N = 12 8639.4 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 4096 Intel Core i9-10980XE 2K 4K 6K 8K 10K SE +/- 55.78, N = 3 8742.1 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 1024 Intel Core i9-10980XE 1600 3200 4800 6400 8000 SE +/- 43.99, N = 3 7470.8 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 2048 Intel Core i9-10980XE 1300 2600 3900 5200 6500 SE +/- 83.85, N = 3 6225.7 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 4096 Intel Core i9-10980XE 1200 2400 3600 4800 6000 SE +/- 31.92, N = 3 5815.0 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 32 Intel Core i9-10980XE 3K 6K 9K 12K 15K SE +/- 891.25, N = 15 15473 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 64 Intel Core i9-10980XE 4K 8K 12K 16K 20K SE +/- 212.92, N = 3 20197 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 32 Intel Core i9-10980XE 8K 16K 24K 32K 40K SE +/- 829.25, N = 15 39480 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 64 Intel Core i9-10980XE 9K 18K 27K 36K 45K SE +/- 109.88, N = 3 41365 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 128 Intel Core i9-10980XE 5K 10K 15K 20K 25K SE +/- 227.07, N = 13 23930 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 256 Intel Core i9-10980XE 9K 18K 27K 36K 45K SE +/- 649.23, N = 3 41174 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 512 Intel Core i9-10980XE 12K 24K 36K 48K 60K SE +/- 541.81, N = 15 53750 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 128 Intel Core i9-10980XE 7K 14K 21K 28K 35K SE +/- 52.19, N = 3 32346 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 256 Intel Core i9-10980XE 6K 12K 18K 24K 30K SE +/- 200.82, N = 3 27248 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 512 Intel Core i9-10980XE 6K 12K 18K 24K 30K SE +/- 52.40, N = 3 26566 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 1024 Intel Core i9-10980XE 14K 28K 42K 56K 70K SE +/- 665.39, N = 8 64013 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 2048 Intel Core i9-10980XE 13K 26K 39K 52K 65K SE +/- 890.34, N = 3 62453 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
MKL-DNN DNNL This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) 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. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_alexnet - Data Type: bf16bf16bf16 Intel Core i9-10980XE 200 400 600 800 1000 SE +/- 2.41, N = 3 875.60 MIN: 870.67 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 4096 Intel Core i9-10980XE 13K 26K 39K 52K 65K SE +/- 531.83, N = 3 59791 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
MKL-DNN DNNL This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) 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. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_alexnet - Data Type: f32 Intel Core i9-10980XE 30 60 90 120 150 SE +/- 0.59, N = 3 126.74 MIN: 125.1 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_all - Data Type: u8s8f32 Intel Core i9-10980XE 800 1600 2400 3200 4000 SE +/- 4.25, N = 3 3766.52 MIN: 3754.67 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_1d - Data Type: bf16bf16bf16 Intel Core i9-10980XE 2 4 6 8 10 SE +/- 0.01423, N = 3 8.63381 MIN: 8.51 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 1024 Intel Core i9-10980XE 6K 12K 18K 24K 30K SE +/- 280.62, N = 3 25883 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
MKL-DNN DNNL This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) 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. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_3d - Data Type: bf16bf16bf16 Intel Core i9-10980XE 5 10 15 20 25 SE +/- 0.04, N = 3 19.91 MIN: 19.58 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_all - Data Type: bf16bf16bf16 Intel Core i9-10980XE 1000 2000 3000 4000 5000 SE +/- 0.22, N = 3 4773.63 MIN: 4768.87 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch All - Data Type: bf16bf16bf16 Intel Core i9-10980XE 5 10 15 20 25 SE +/- 0.07, N = 3 20.31 MIN: 18.9 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 Intel Core i9-10980XE 1000 2000 3000 4000 5000 SE +/- 9.37, N = 3 4725.22 MIN: 4698.92 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch All - Data Type: u8s8f32 Intel Core i9-10980XE 1.3312 2.6624 3.9936 5.3248 6.656 SE +/- 0.05056, N = 3 5.91631 MIN: 5.65 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch 1D - Data Type: bf16bf16bf16 Intel Core i9-10980XE 1.2837 2.5674 3.8511 5.1348 6.4185 SE +/- 0.04695, N = 3 5.70514 MIN: 5.53 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch 1D - Data Type: u8s8f32 Intel Core i9-10980XE 0.1461 0.2922 0.4383 0.5844 0.7305 SE +/- 0.006861, N = 3 0.649125 MIN: 0.62 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch All - Data Type: f32 Intel Core i9-10980XE 4 8 12 16 20 SE +/- 0.01, N = 3 17.41 MIN: 17.14 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch 1D - Data Type: f32 Intel Core i9-10980XE 1.2118 2.4236 3.6354 4.8472 6.059 SE +/- 0.07604, N = 4 5.38576 MIN: 4.52 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_all - Data Type: f32 Intel Core i9-10980XE 300 600 900 1200 1500 SE +/- 0.20, N = 3 1373.07 MIN: 1368.75 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_3d - Data Type: f32 Intel Core i9-10980XE 3 6 9 12 15 SE +/- 0.03, N = 3 12.84 MIN: 12.65 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 Intel Core i9-10980XE 0.1036 0.2072 0.3108 0.4144 0.518 SE +/- 0.002075, N = 3 0.460571 MIN: 0.44 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_all - Data Type: f32 Intel Core i9-10980XE 200 400 600 800 1000 SE +/- 0.02, N = 3 1138.42 MIN: 1131.88 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Recurrent Neural Network Training - Data Type: f32 Intel Core i9-10980XE 30 60 90 120 150 SE +/- 0.13, N = 3 152.41 MIN: 150.81 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_3d - Data Type: u8s8f32 Intel Core i9-10980XE 1600 3200 4800 6400 8000 SE +/- 5.18, N = 3 7651.80 MIN: 7630.39 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_alexnet - Data Type: u8s8f32 Intel Core i9-10980XE 9 18 27 36 45 SE +/- 0.12, N = 3 41.45 MIN: 40.76 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_1d - Data Type: f32 Intel Core i9-10980XE 0.41 0.82 1.23 1.64 2.05 SE +/- 0.01038, N = 3 1.82225 MIN: 1.78 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32 Intel Core i9-10980XE 14 28 42 56 70 SE +/- 0.11, N = 3 64.69 MIN: 63.5 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_3d - Data Type: f32 Intel Core i9-10980XE 0.5913 1.1826 1.7739 2.3652 2.9565 SE +/- 0.02031, N = 3 2.62800 MIN: 2.56 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_3d - Data Type: bf16bf16bf16 Intel Core i9-10980XE 3 6 9 12 15 SE +/- 0.04, N = 3 10.83 MIN: 10.63 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_googlenet_v3 - Data Type: u8s8f32 Intel Core i9-10980XE 5 10 15 20 25 SE +/- 0.06, N = 3 20.01 MIN: 19.6 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 2048 Intel Core i9-10980XE 5K 10K 15K 20K 25K SE +/- 143.22, N = 3 23142 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
MKL-DNN DNNL This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) 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. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_googlenet_v3 - Data Type: bf16bf16bf16 Intel Core i9-10980XE 50 100 150 200 250 SE +/- 0.07, N = 3 225.27 MIN: 224.08 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 4096 Intel Core i9-10980XE 4K 8K 12K 16K 20K SE +/- 208.86, N = 3 18701 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
Numenta Anomaly Benchmark Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial timeseries data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: EXPoSE Intel Core i9-10980XE 200 400 600 800 1000 SE +/- 3.29, N = 3 798.17
MKL-DNN DNNL This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) 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. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_all - Data Type: bf16bf16bf16 Intel Core i9-10980XE 800 1600 2400 3200 4000 SE +/- 0.44, N = 3 3756.50 MIN: 3751.93 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Read Intel Core i9-10980XE 20M 40M 60M 80M 100M SE +/- 36505.29, N = 3 93013702 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Sequential Fill Intel Core i9-10980XE 300K 600K 900K 1200K 1500K SE +/- 11182.63, N = 3 1520282 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Fill Sync Intel Core i9-10980XE 1000 2000 3000 4000 5000 SE +/- 30.56, N = 3 4691 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Read While Writing Intel Core i9-10980XE 900K 1800K 2700K 3600K 4500K SE +/- 42987.50, N = 3 4169333 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Fill Sync Intel Core i9-10980XE 0.1125 0.225 0.3375 0.45 0.5625 SE +/- 0.00, N = 3 0.5 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Fill Sync Intel Core i9-10980XE 2K 4K 6K 8K 10K SE +/- 239.07, N = 3 7817.14 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Overwrite Intel Core i9-10980XE 3 6 9 12 15 SE +/- 0.03, N = 3 10.5 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Overwrite Intel Core i9-10980XE 80 160 240 320 400 SE +/- 1.27, N = 3 378.30 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Random Fill Intel Core i9-10980XE 3 6 9 12 15 SE +/- 0.03, N = 3 10.5 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Fill Intel Core i9-10980XE 80 160 240 320 400 SE +/- 0.49, N = 3 377.42 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Read Intel Core i9-10980XE 6 12 18 24 30 SE +/- 0.08, N = 3 27.40 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Seek Random Intel Core i9-10980XE 8 16 24 32 40 SE +/- 0.18, N = 3 32.74 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Delete Intel Core i9-10980XE 80 160 240 320 400 SE +/- 0.34, N = 3 371.89 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Sequential Fill Intel Core i9-10980XE 3 6 9 12 15 SE +/- 0.00, N = 3 10.4 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Sequential Fill Intel Core i9-10980XE 80 160 240 320 400 SE +/- 0.92, N = 3 382.17 1. (CXX) g++ options: -O3 -lsnappy -lpthread
Intel Core i9-10980XE Processor: Intel Core i9-10980XE @ 4.80GHz (18 Cores / 36 Threads), Motherboard: ASRock X299 Steel Legend (P1.30 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 32GB, Disk: Samsung SSD 970 PRO 512GB, Graphics: NVIDIA NV132 11GB, Audio: Realtek ALC1220, Monitor: DELL P2415Q, Network: Intel I219-V + Intel I211
OS: Ubuntu 20.04, Kernel: 5.4.0-18-generic (x86_64), Desktop: GNOME Shell 3.35.91, Display Server: X Server 1.20.7, Display Driver: modesetting 1.20.7, OpenGL: 4.3 Mesa 20.0.0, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160
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,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: intel_pstate powersave - CPU Microcode: 0x500012cPython Notes: + Python 3.8.2Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled
Testing initiated at 26 March 2020 20:00 by user phoronix.