AMD EPYC 7F72 24-Core testing with a ASRockRack EPYCD8 (P2.10 BIOS) and ASPEED 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 2009304-FI-EPYC7F72E54 epyc-7f72-eo-september - Phoronix Test Suite epyc-7f72-eo-september AMD EPYC 7F72 24-Core testing with a ASRockRack EPYCD8 (P2.10 BIOS) and ASPEED on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2009304-FI-EPYC7F72E54&export=pdf&grr&sro .
epyc-7f72-eo-september Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server Display Driver Compiler File-System Screen Resolution EPYC 7F72 EPYC 7F72 x 2 3 AMD EPYC 7F72 24-Core @ 3.20GHz (24 Cores / 48 Threads) ASRockRack EPYCD8 (P2.10 BIOS) AMD Starship/Matisse 126GB 3841GB Micron_9300_MTFDHAL3T8TDP ASPEED AMD Starship/Matisse 2 x Intel I350 Ubuntu 20.04 5.9.0-050900rc6daily20200921-generic (x86_64) 20200920 GNOME Shell 3.36.4 X Server 1.20.8 modesetting 1.20.8 GCC 9.3.0 ext4 1024x768 OpenBenchmarking.org Compiler 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,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x830101c Python Details - Python 3.8.2 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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
epyc-7f72-eo-september caffe: GoogleNet - CPU - 1000 caffe: AlexNet - CPU - 1000 lczero: Eigen lczero: BLAS caffe: GoogleNet - CPU - 200 lczero: Rand hint: FLOAT caffe: GoogleNet - CPU - 100 caffe: AlexNet - CPU - 200 hmmer: Pfam Database Search byte: Dhrystone 2 ncnn: CPU - yolov4-tiny ncnn: CPU - resnet50 ncnn: CPU - alexnet ncnn: CPU - resnet18 ncnn: CPU - vgg16 ncnn: CPU - googlenet ncnn: CPU - blazeface ncnn: CPU - efficientnet-b0 ncnn: CPU - mnasnet ncnn: CPU - shufflenet-v2 ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: CPU - mobilenet ncnn: CPU - squeezenet couchdb: 100 - 1000 - 24 mlpack: scikit_qda caffe: AlexNet - CPU - 100 keydb: mlpack: scikit_ica mlpack: scikit_linearridgeregression mlpack: scikit_svm dolfyn: Computational Fluid Dynamics mafft: Multiple Sequence Alignment - LSU RNA ffte: N=256, 3D Complex FFT Routine EPYC 7F72 EPYC 7F72 x 2 3 2073 2227 164671 142.413 37756888.4 103.685 420383.50 18.627 9.465 121809.43318954 1902543 751617 2178 2256 379880 164311 328822812.22518 190013 150373 142.611 38374014.4 30.20 22.78 9.16 13.04 32.83 19.62 3.74 11.09 8.40 9.32 8.80 9.21 19.42 18.87 103.859 39.45 75293 421676.28 61.04 1.65 24.28 18.637 9.559 122399.72540484 1900487 752070 2165 2213 380086 166198 328868294.68809 189355 150269 142.595 37972490.0 30.14 22.71 9.42 13.05 32.85 19.74 3.77 11.03 8.45 9.33 8.81 9.26 19.93 19.38 104.448 39.30 75164 419756.03 60.77 1.65 24.28 18.540 9.644 121264.37712651 1900833 751645 2096 2228 379324 165528 328901110.00869 190069 150626 142.538 37884312.2 30.27 22.92 9.25 13.00 32.52 19.68 3.73 11.00 8.41 9.34 8.88 9.28 20.42 19.62 104.647 39.61 75300 419091.19 61.39 1.65 24.26 18.646 9.575 122021.48057904 OpenBenchmarking.org
Caffe Model: GoogleNet - Acceleration: CPU - Iterations: 1000 OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 1000 2 3 EPYC 7F72 x 400K 800K 1200K 1600K 2000K SE +/- 1530.16, N = 3 SE +/- 909.25, N = 3 SE +/- 2432.39, N = 3 1900487 1900833 1902543 1. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
Caffe Model: AlexNet - Acceleration: CPU - Iterations: 1000 OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 1000 2 3 EPYC 7F72 x 160K 320K 480K 640K 800K SE +/- 654.75, N = 3 SE +/- 811.75, N = 3 SE +/- 670.58, N = 3 752070 751645 751617 1. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
LeelaChessZero Backend: Eigen OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: Eigen 2 3 EPYC 7F72 EPYC 7F72 x 500 1000 1500 2000 2500 SE +/- 11.22, N = 3 SE +/- 28.45, N = 9 SE +/- 23.67, N = 9 SE +/- 26.56, N = 3 2165 2096 2073 2178 1. (CXX) g++ options: -flto -pthread
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: BLAS 2 3 EPYC 7F72 EPYC 7F72 x 500 1000 1500 2000 2500 SE +/- 28.46, N = 5 SE +/- 9.53, N = 3 SE +/- 11.27, N = 3 SE +/- 24.04, N = 7 2213 2228 2227 2256 1. (CXX) g++ options: -flto -pthread
Caffe Model: GoogleNet - Acceleration: CPU - Iterations: 200 OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 200 2 3 EPYC 7F72 x 80K 160K 240K 320K 400K SE +/- 518.16, N = 3 SE +/- 266.02, N = 3 SE +/- 429.90, N = 3 380086 379324 379880 1. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
LeelaChessZero Backend: Random OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: Random 2 3 EPYC 7F72 EPYC 7F72 x 40K 80K 120K 160K 200K SE +/- 1148.31, N = 3 SE +/- 1873.00, N = 3 SE +/- 1317.43, N = 3 SE +/- 1500.11, N = 3 166198 165528 164671 164311 1. (CXX) g++ options: -flto -pthread
Hierarchical INTegration Test: FLOAT OpenBenchmarking.org QUIPs, More Is Better Hierarchical INTegration 1.0 Test: FLOAT 2 3 EPYC 7F72 x 70M 140M 210M 280M 350M SE +/- 40216.53, N = 3 SE +/- 377618.26, N = 3 SE +/- 53237.74, N = 3 328868294.69 328901110.01 328822812.23 1. (CC) gcc options: -O3 -march=native -lm
Caffe Model: GoogleNet - Acceleration: CPU - Iterations: 100 OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 100 2 3 EPYC 7F72 x 40K 80K 120K 160K 200K SE +/- 245.02, N = 3 SE +/- 407.34, N = 3 SE +/- 464.46, N = 3 189355 190069 190013 1. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
Caffe Model: AlexNet - Acceleration: CPU - Iterations: 200 OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 200 2 3 EPYC 7F72 x 30K 60K 90K 120K 150K SE +/- 69.27, N = 3 SE +/- 75.05, N = 3 SE +/- 211.31, N = 3 150269 150626 150373 1. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 3.3.1 Pfam Database Search 2 3 EPYC 7F72 EPYC 7F72 x 30 60 90 120 150 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.22, N = 3 SE +/- 0.05, N = 3 142.60 142.54 142.41 142.61 1. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm
BYTE Unix Benchmark Computational Test: Dhrystone 2 OpenBenchmarking.org LPS, More Is Better BYTE Unix Benchmark 3.6 Computational Test: Dhrystone 2 2 3 EPYC 7F72 EPYC 7F72 x 8M 16M 24M 32M 40M SE +/- 493714.96, N = 5 SE +/- 550044.12, N = 3 SE +/- 390690.78, N = 3 SE +/- 421072.96, N = 3 37972490.0 37884312.2 37756888.4 38374014.4
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: yolov4-tiny 2 3 EPYC 7F72 x 7 14 21 28 35 SE +/- 0.11, N = 7 SE +/- 0.21, N = 3 SE +/- 0.14, N = 3 30.14 30.27 30.20 MIN: 29.27 / MAX: 65.59 MIN: 29.38 / MAX: 33.06 MIN: 29.67 / MAX: 32.8 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: resnet50 2 3 EPYC 7F72 x 5 10 15 20 25 SE +/- 0.06, N = 7 SE +/- 0.23, N = 3 SE +/- 0.16, N = 3 22.71 22.92 22.78 MIN: 22.12 / MAX: 25.08 MIN: 22.33 / MAX: 105.21 MIN: 22.17 / MAX: 85.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: alexnet 2 3 EPYC 7F72 x 3 6 9 12 15 SE +/- 0.19, N = 6 SE +/- 0.23, N = 3 SE +/- 0.26, N = 3 9.42 9.25 9.16 MIN: 8.51 / MAX: 10.8 MIN: 8.56 / MAX: 12.4 MIN: 8.54 / MAX: 10.41 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: resnet18 2 3 EPYC 7F72 x 3 6 9 12 15 SE +/- 0.13, N = 7 SE +/- 0.13, N = 3 SE +/- 0.27, N = 3 13.05 13.00 13.04 MIN: 12.38 / MAX: 54.07 MIN: 12.56 / MAX: 14.64 MIN: 12.34 / MAX: 38.34 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: vgg16 2 3 EPYC 7F72 x 8 16 24 32 40 SE +/- 0.30, N = 7 SE +/- 0.22, N = 3 SE +/- 0.56, N = 3 32.85 32.52 32.83 MIN: 31.1 / MAX: 98.34 MIN: 31.78 / MAX: 34.87 MIN: 31.34 / MAX: 36.46 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: googlenet 2 3 EPYC 7F72 x 5 10 15 20 25 SE +/- 0.09, N = 7 SE +/- 0.17, N = 3 SE +/- 0.14, N = 3 19.74 19.68 19.62 MIN: 19.14 / MAX: 25.15 MIN: 19.15 / MAX: 21.9 MIN: 19.13 / MAX: 22.12 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: blazeface 2 3 EPYC 7F72 x 0.8483 1.6966 2.5449 3.3932 4.2415 SE +/- 0.01, N = 7 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 3.77 3.73 3.74 MIN: 3.58 / MAX: 6 MIN: 3.58 / MAX: 4.65 MIN: 3.46 / MAX: 4.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: efficientnet-b0 2 3 EPYC 7F72 x 3 6 9 12 15 SE +/- 0.06, N = 7 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 11.03 11.00 11.09 MIN: 10.67 / MAX: 16.51 MIN: 10.66 / MAX: 13.36 MIN: 10.74 / MAX: 13.3 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mnasnet 2 3 EPYC 7F72 x 2 4 6 8 10 SE +/- 0.03, N = 7 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 8.45 8.41 8.40 MIN: 8.05 / MAX: 10.2 MIN: 8.08 / MAX: 11.46 MIN: 8.11 / MAX: 10.16 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: shufflenet-v2 2 3 EPYC 7F72 x 3 6 9 12 15 SE +/- 0.06, N = 6 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 9.33 9.34 9.32 MIN: 9.05 / MAX: 11.33 MIN: 9.14 / MAX: 10.56 MIN: 9.09 / MAX: 14.74 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU-v3-v3 - Model: mobilenet-v3 2 3 EPYC 7F72 x 2 4 6 8 10 SE +/- 0.04, N = 7 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 8.81 8.88 8.80 MIN: 8.52 / MAX: 10.79 MIN: 8.49 / MAX: 76.01 MIN: 8.56 / MAX: 10.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU-v2-v2 - Model: mobilenet-v2 2 3 EPYC 7F72 x 3 6 9 12 15 SE +/- 0.04, N = 7 SE +/- 0.12, N = 3 SE +/- 0.05, N = 3 9.26 9.28 9.21 MIN: 8.75 / MAX: 11.07 MIN: 8.89 / MAX: 10.96 MIN: 8.89 / MAX: 10.51 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mobilenet 2 3 EPYC 7F72 x 5 10 15 20 25 SE +/- 0.28, N = 7 SE +/- 0.68, N = 3 SE +/- 0.01, N = 3 19.93 20.42 19.42 MIN: 18.87 / MAX: 22.76 MIN: 18.91 / MAX: 84.5 MIN: 18.9 / MAX: 21.51 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: squeezenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: squeezenet 2 3 EPYC 7F72 x 5 10 15 20 25 SE +/- 0.20, N = 7 SE +/- 0.30, N = 3 SE +/- 0.10, N = 3 19.38 19.62 18.87 MIN: 18.46 / MAX: 118.13 MIN: 18.65 / MAX: 21.93 MIN: 18.36 / MAX: 20.85 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Apache CouchDB Bulk Size: 100 - Inserts: 1000 - Rounds: 24 OpenBenchmarking.org Seconds, Fewer Is Better Apache CouchDB 3.1.1 Bulk Size: 100 - Inserts: 1000 - Rounds: 24 2 3 EPYC 7F72 EPYC 7F72 x 20 40 60 80 100 SE +/- 0.60, N = 3 SE +/- 0.60, N = 3 SE +/- 0.33, N = 3 SE +/- 0.06, N = 3 104.45 104.65 103.69 103.86 1. (CXX) g++ options: -std=c++14 -lmozjs-68 -lm -lerl_interface -lei -fPIC -MMD
Mlpack Benchmark Benchmark: scikit_qda OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_qda 2 3 EPYC 7F72 x 9 18 27 36 45 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 SE +/- 0.13, N = 3 39.30 39.61 39.45
Caffe Model: AlexNet - Acceleration: CPU - Iterations: 100 OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 100 2 3 EPYC 7F72 x 16K 32K 48K 64K 80K SE +/- 171.98, N = 3 SE +/- 215.05, N = 3 SE +/- 23.86, N = 3 75164 75300 75293 1. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
KeyDB OpenBenchmarking.org Ops/sec, More Is Better KeyDB 6.0.16 2 3 EPYC 7F72 EPYC 7F72 x 90K 180K 270K 360K 450K SE +/- 1309.71, N = 3 SE +/- 1744.78, N = 3 SE +/- 250.94, N = 3 SE +/- 2108.70, N = 3 419756.03 419091.19 420383.50 421676.28 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Mlpack Benchmark Benchmark: scikit_ica OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_ica 2 3 EPYC 7F72 x 14 28 42 56 70 SE +/- 0.99, N = 3 SE +/- 0.19, N = 3 SE +/- 0.88, N = 3 60.77 61.39 61.04
Mlpack Benchmark Benchmark: scikit_linearridgeregression OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_linearridgeregression 2 3 EPYC 7F72 x 0.3713 0.7426 1.1139 1.4852 1.8565 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 1.65 1.65 1.65
Mlpack Benchmark Benchmark: scikit_svm OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_svm 2 3 EPYC 7F72 x 6 12 18 24 30 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 24.28 24.26 24.28
Dolfyn Computational Fluid Dynamics OpenBenchmarking.org Seconds, Fewer Is Better Dolfyn 0.527 Computational Fluid Dynamics 2 3 EPYC 7F72 EPYC 7F72 x 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 18.54 18.65 18.63 18.64
Timed MAFFT Alignment Multiple Sequence Alignment - LSU RNA OpenBenchmarking.org Seconds, Fewer Is Better Timed MAFFT Alignment 7.471 Multiple Sequence Alignment - LSU RNA 2 3 EPYC 7F72 EPYC 7F72 x 3 6 9 12 15 SE +/- 0.053, N = 3 SE +/- 0.057, N = 3 SE +/- 0.055, N = 3 SE +/- 0.028, N = 3 9.644 9.575 9.465 9.559 1. (CC) gcc options: -std=c99 -O3 -lm -lpthread
FFTE N=256, 3D Complex FFT Routine OpenBenchmarking.org MFLOPS, More Is Better FFTE 7.0 N=256, 3D Complex FFT Routine 2 3 EPYC 7F72 EPYC 7F72 x 30K 60K 90K 120K 150K SE +/- 807.96, N = 3 SE +/- 254.91, N = 3 SE +/- 630.92, N = 3 SE +/- 285.55, N = 3 121264.38 122021.48 121809.43 122399.73 1. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp
Phoronix Test Suite v10.8.4