nvidia A2 2 x AMD EPYC 9334 32-Core testing with a Giga Computing MZ73-LM1-000 v01000100 (F10 BIOS) and Gigabyte NVIDIA A2 15GB on Ubuntu 22.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2409263-SIDD-NVIDIAA69&grw&sro .
nvidia A2 Processor Motherboard Chipset Memory Disk Graphics Network OS Kernel Desktop Display Server Display Driver OpenCL Vulkan Compiler File-System Screen Resolution OpenGL Genoa 9334 Genoa Eypc 9334 2 x AMD EPYC 9334 32-Core @ 2.70GHz (64 Cores / 127 Threads) Giga Computing MZ73-LM1-000 v01000100 (F10 BIOS) AMD Device 14a4 8 x 32 GB DDR5-4800MT/s Micron MTC20F1045S1RC48BA2 1920GB KINGSTON SEDC600 Gigabyte NVIDIA A2 15GB 2 x Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMA Ubuntu 22.04 6.8.0-45-generic (x86_64) GNOME Shell 42.9 X Server 1.21.1.4 NVIDIA 535.183.01 OpenCL 3.0 CUDA 12.2.148 1.3.242 GCC 11.4.0 + CUDA 12.2 ext4 1920x1200 4.5 Mesa 23.2.1-1ubuntu3.1~22.04.2 (LLVM 15.0.7 256 bits) OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Processor Details - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa10113e OpenCL Details - Genoa 9334: GPU Compute Cores: 1280 Python Details - Genoa 9334: Python 3.10.12 Security Details - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected Compiler Details - Genoa Eypc 9334: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --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
nvidia A2 ncnn: Vulkan GPU - mobilenet ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - vgg16 ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3 ncnn: Vulkan GPU - yolov4-tiny ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU - regnety_400m ncnn: Vulkan GPU - vision_transformer ncnn: Vulkan GPU - FastestDet Genoa 9334 Genoa Eypc 9334 83.03 63.03 64.88 76.79 62.95 93.68 30.46 103.18 132.81 46.51 38.00 87.73 83.03 111.97 122.44 251.90 212.72 84.94 OpenBenchmarking.org
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mobilenet Genoa Eypc 9334 20 40 60 80 100 SE +/- 11.26, N = 9 83.03 MIN: 18.86 / MAX: 1407.98 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 Genoa Eypc 9334 14 28 42 56 70 SE +/- 8.23, N = 9 63.03 MIN: 11.36 / MAX: 1255.98 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 Genoa Eypc 9334 14 28 42 56 70 SE +/- 4.07, N = 9 64.88 MIN: 11.4 / MAX: 1445.01 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: shufflenet-v2 Genoa Eypc 9334 20 40 60 80 100 SE +/- 6.97, N = 9 76.79 MIN: 15.47 / MAX: 1695 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mnasnet Genoa Eypc 9334 14 28 42 56 70 SE +/- 10.99, N = 9 62.95 MIN: 10.19 / MAX: 1213.99 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: efficientnet-b0 Genoa Eypc 9334 20 40 60 80 100 SE +/- 8.45, N = 9 93.68 MIN: 15.66 / MAX: 2083 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: blazeface Genoa Eypc 9334 7 14 21 28 35 SE +/- 4.65, N = 9 30.46 MIN: 6.54 / MAX: 1049 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: googlenet Genoa Eypc 9334 20 40 60 80 100 SE +/- 13.25, N = 9 103.18 MIN: 20.42 / MAX: 1938 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vgg16 Genoa Eypc 9334 30 60 90 120 150 SE +/- 10.52, N = 9 132.81 MIN: 33.9 / MAX: 954.01 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet18 Genoa Eypc 9334 11 22 33 44 55 SE +/- 5.06, N = 9 46.51 MIN: 12.03 / MAX: 1021 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: alexnet Genoa Eypc 9334 9 18 27 36 45 SE +/- 7.69, N = 9 38.00 MIN: 7.83 / MAX: 434.39 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet50 Genoa Eypc 9334 20 40 60 80 100 SE +/- 9.20, N = 9 87.73 MIN: 20.74 / MAX: 1872 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 Genoa Eypc 9334 20 40 60 80 100 SE +/- 11.26, N = 9 83.03 MIN: 18.86 / MAX: 1407.98 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: yolov4-tiny Genoa Eypc 9334 30 60 90 120 150 SE +/- 10.00, N = 9 111.97 MIN: 26.87 / MAX: 932.29 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: squeezenet_ssd Genoa Eypc 9334 30 60 90 120 150 SE +/- 14.43, N = 9 122.44 MIN: 21.8 / MAX: 2196.01 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: regnety_400m Genoa Eypc 9334 60 120 180 240 300 SE +/- 24.14, N = 9 251.90 MIN: 50.56 / MAX: 9093 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vision_transformer Genoa Eypc 9334 50 100 150 200 250 SE +/- 21.02, N = 9 212.72 MIN: 46.24 / MAX: 2109 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: FastestDet Genoa Eypc 9334 20 40 60 80 100 SE +/- 8.16, N = 9 84.94 MIN: 15.35 / MAX: 1794.01 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Phoronix Test Suite v10.8.5