AMD Ryzen 9 5900HX testing with a ASUS G513QY v1.0 (G513QY.318 BIOS) and ASUS AMD Cezanne 512MB on Arch rolling 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 2208131-NE-NCNNMNN5973 ncnn mnn 5900HX - Phoronix Test Suite ncnn mnn 5900HX AMD Ryzen 9 5900HX testing with a ASUS G513QY v1.0 (G513QY.318 BIOS) and ASUS AMD Cezanne 512MB on Arch rolling via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2208131-NE-NCNNMNN5973&grr&export=pdf&rdt .
ncnn mnn 5900HX Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution A B C AMD Ryzen 9 5900HX @ 3.30GHz (8 Cores / 16 Threads) ASUS G513QY v1.0 (G513QY.318 BIOS) AMD Renoir/Cezanne 16GB 512GB SAMSUNG MZVLQ512HBLU-00B00 ASUS AMD Cezanne 512MB (2500/1000MHz) AMD Navi 21/23 LQ156M1JW25 Realtek RTL8111/8168/8411 + MEDIATEK MT7921 802.11ax PCI Arch rolling 5.18.16-arch1-1 (x86_64) KDE Plasma 5.25.4 X Server 1.21.1.4 + Wayland 4.6 Mesa 22.1.4 (LLVM 14.0.6 DRM 3.46) 1.3.211 GCC 12.1.1 20220730 ext4 1920x1080 ASUS AMD Cezanne 512MB ASUS AMD Cezanne 512MB (2500/1000MHz) OpenBenchmarking.org Kernel Details - Transparent Huge Pages: always Compiler Details - --disable-libssp --disable-libstdcxx-pch --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=c,c++,ada,fortran,go,lto,objc,obj-c++,d --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-build-config=bootstrap-lto --with-linker-hash-style=gnu Processor Details - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - Platform Profile: balanced - CPU Microcode: 0xa50000c - ACPI Profile: balanced Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
ncnn mnn 5900HX ncnn: CPU - FastestDet ncnn: CPU - vision_transformer ncnn: CPU - regnety_400m ncnn: CPU - squeezenet_ssd 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 mnn: inception-v3 mnn: mobilenet-v1-1.0 mnn: MobileNetV2_224 mnn: SqueezeNetV1.0 mnn: resnet-v2-50 mnn: squeezenetv1.1 mnn: mobilenetV3 ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPU - FastestDet ncnn: Vulkan GPU - vision_transformer ncnn: Vulkan GPU - regnety_400m ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU - yolov4-tiny ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - vgg16 ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU - mobilenet A B C 2.57 165.65 7.12 20.87 27.42 22.95 10.67 12.45 73.11 13.96 0.77 5.78 2.81 2.25 3.07 4.17 14.98 28.004 2.369 2.490 4.463 21.260 2.382 1.136 5.06 1.86 147.83 3.00 4.05 6.67 1.66 2.33 7.18 3.79 1.07 5.02 1.89 1.77 2.30 1.88 4.48 2.60 167.99 7.10 20.94 27.46 23.12 10.82 12.67 73.05 14.01 0.77 5.78 2.73 2.21 3.01 4.19 15.24 28.452 2.351 2.443 4.523 21.355 2.410 1.137 5.06 1.91 146.00 3.03 4.08 6.65 1.65 2.3 7.21 3.94 1.11 5.06 1.93 1.82 2.34 1.92 4.48 2.69 165.92 7.08 20.94 27.59 22.80 10.65 12.54 72.93 14.00 0.76 5.75 2.72 2.28 3.02 4.14 15.30 28.788 2.334 2.471 4.506 21.226 2.405 1.141 5.08 1.91 145.82 3.06 3.98 6.68 1.66 2.32 7.22 3.96 1.11 5.09 1.94 1.83 2.35 1.92 4.49 OpenBenchmarking.org
NCNN Target: CPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: FastestDet A B C 0.6053 1.2106 1.8159 2.4212 3.0265 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 2.57 2.60 2.69 MIN: 2.45 / MAX: 4.5 MIN: 2.48 / MAX: 2.85 MIN: 2.47 / MAX: 2.93 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vision_transformer A B C 40 80 120 160 200 SE +/- 0.19, N = 3 SE +/- 1.40, N = 3 SE +/- 0.19, N = 3 165.65 167.99 165.92 MIN: 161.51 / MAX: 171.84 MIN: 162.38 / MAX: 182.04 MIN: 162.68 / MAX: 172.94 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: regnety_400m A B C 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 7.12 7.10 7.08 MIN: 6.8 / MAX: 9.14 MIN: 6.81 / MAX: 8.28 MIN: 6.76 / MAX: 9.43 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: squeezenet_ssd A B C 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.14, N = 3 20.87 20.94 20.94 MIN: 20.53 / MAX: 22.66 MIN: 20.53 / MAX: 23.04 MIN: 20.47 / MAX: 22.83 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: yolov4-tiny A B C 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.12, N = 3 SE +/- 0.11, N = 3 27.42 27.46 27.59 MIN: 26.95 / MAX: 31.42 MIN: 26.83 / MAX: 29.49 MIN: 27.04 / MAX: 29.89 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet50 A B C 6 12 18 24 30 SE +/- 0.06, N = 3 SE +/- 0.13, N = 3 SE +/- 0.04, N = 3 22.95 23.12 22.80 MIN: 22.25 / MAX: 27.03 MIN: 22.33 / MAX: 25.11 MIN: 22.18 / MAX: 25.03 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: alexnet A B C 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 10.67 10.82 10.65 MIN: 10.41 / MAX: 11.91 MIN: 10.58 / MAX: 11.12 MIN: 10.36 / MAX: 11.27 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet18 A B C 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.04, N = 3 12.45 12.67 12.54 MIN: 12.16 / MAX: 14.15 MIN: 12.43 / MAX: 14.75 MIN: 12.23 / MAX: 14.03 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vgg16 A B C 16 32 48 64 80 SE +/- 0.07, N = 3 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 73.11 73.05 72.93 MIN: 72.51 / MAX: 88.36 MIN: 72.57 / MAX: 75.27 MIN: 72.43 / MAX: 75.61 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: googlenet A B C 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 13.96 14.01 14.00 MIN: 13.58 / MAX: 15.87 MIN: 13.59 / MAX: 15.88 MIN: 13.57 / MAX: 16.58 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: blazeface A B C 0.1733 0.3466 0.5199 0.6932 0.8665 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 0.77 0.77 0.76 MIN: 0.75 / MAX: 2.04 MIN: 0.75 / MAX: 0.95 MIN: 0.74 / MAX: 0.93 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: efficientnet-b0 A B C 1.3005 2.601 3.9015 5.202 6.5025 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 5.78 5.78 5.75 MIN: 5.56 / MAX: 7.73 MIN: 5.57 / MAX: 6.46 MIN: 5.56 / MAX: 7.72 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: mnasnet A B C 0.6323 1.2646 1.8969 2.5292 3.1615 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 2.81 2.73 2.72 MIN: 2.61 / MAX: 4.72 MIN: 2.61 / MAX: 3.88 MIN: 2.57 / MAX: 4.39 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: shufflenet-v2 A B C 0.513 1.026 1.539 2.052 2.565 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 2.25 2.21 2.28 MIN: 2.13 / MAX: 3.58 MIN: 2.14 / MAX: 2.38 MIN: 2.12 / MAX: 3.58 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v3-v3 - Model: mobilenet-v3 A B C 0.6908 1.3816 2.0724 2.7632 3.454 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 3.07 3.01 3.02 MIN: 2.9 / MAX: 4.97 MIN: 2.86 / MAX: 3.58 MIN: 2.84 / MAX: 4.66 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v2-v2 - Model: mobilenet-v2 A B C 0.9428 1.8856 2.8284 3.7712 4.714 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 4.17 4.19 4.14 MIN: 3.95 / MAX: 6.1 MIN: 3.95 / MAX: 4.8 MIN: 3.94 / MAX: 5.91 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: mobilenet A B C 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.22, N = 3 SE +/- 0.21, N = 3 14.98 15.24 15.30 MIN: 14.64 / MAX: 17.32 MIN: 14.69 / MAX: 17.39 MIN: 14.68 / MAX: 17.72 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.0 Model: inception-v3 A B C 7 14 21 28 35 SE +/- 0.05, N = 3 SE +/- 0.15, N = 3 SE +/- 0.29, N = 3 28.00 28.45 28.79 MIN: 26.69 / MAX: 32.71 MIN: 26.85 / MAX: 35.34 MIN: 27.03 / MAX: 33.35 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.0 Model: mobilenet-v1-1.0 A B C 0.533 1.066 1.599 2.132 2.665 SE +/- 0.004, N = 3 SE +/- 0.018, N = 3 SE +/- 0.035, N = 3 2.369 2.351 2.334 MIN: 2.2 / MAX: 4.92 MIN: 2.18 / MAX: 4.33 MIN: 2.18 / MAX: 4.51 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.0 Model: MobileNetV2_224 A B C 0.5603 1.1206 1.6809 2.2412 2.8015 SE +/- 0.018, N = 3 SE +/- 0.024, N = 3 SE +/- 0.008, N = 3 2.490 2.443 2.471 MIN: 2.2 / MAX: 6.31 MIN: 2.16 / MAX: 5.14 MIN: 2.23 / MAX: 4.69 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.0 Model: SqueezeNetV1.0 A B C 1.0177 2.0354 3.0531 4.0708 5.0885 SE +/- 0.051, N = 3 SE +/- 0.039, N = 3 SE +/- 0.014, N = 3 4.463 4.523 4.506 MIN: 4.13 / MAX: 6.63 MIN: 4.23 / MAX: 7 MIN: 4.21 / MAX: 6.46 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.0 Model: resnet-v2-50 A B C 5 10 15 20 25 SE +/- 0.10, N = 3 SE +/- 0.02, N = 3 SE +/- 0.13, N = 3 21.26 21.36 21.23 MIN: 19.91 / MAX: 24.58 MIN: 19.93 / MAX: 26.59 MIN: 19.87 / MAX: 28.06 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: squeezenetv1.1 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.0 Model: squeezenetv1.1 A B C 0.5423 1.0846 1.6269 2.1692 2.7115 SE +/- 0.027, N = 3 SE +/- 0.021, N = 3 SE +/- 0.001, N = 3 2.382 2.410 2.405 MIN: 2.16 / MAX: 4.13 MIN: 2.19 / MAX: 4.13 MIN: 2.2 / MAX: 4.47 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.0 Model: mobilenetV3 A B C 0.2567 0.5134 0.7701 1.0268 1.2835 SE +/- 0.004, N = 3 SE +/- 0.004, N = 3 SE +/- 0.008, N = 3 1.136 1.137 1.141 MIN: 1.12 / MAX: 2.75 MIN: 1.12 / MAX: 2.74 MIN: 1.12 / MAX: 2.74 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: resnet50 A B C 1.143 2.286 3.429 4.572 5.715 SE +/- 0.00, N = 2 SE +/- 0.02, N = 2 SE +/- 0.00, N = 2 5.06 5.06 5.08 MIN: 4.99 / MAX: 7.58 MIN: 4.99 / MAX: 5.21 MIN: 5 / MAX: 6.08 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: FastestDet A B C 0.4298 0.8596 1.2894 1.7192 2.149 SE +/- 0.01, N = 3 SE +/- 0.01, N = 2 SE +/- 0.00, N = 3 1.86 1.91 1.91 MIN: 1.81 / MAX: 3.74 MIN: 1.82 / MAX: 2.06 MIN: 1.82 / MAX: 2.32 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: vision_transformer A B C 30 60 90 120 150 SE +/- 0.62, N = 3 SE +/- 0.24, N = 3 SE +/- 0.23, N = 3 147.83 146.00 145.82 MIN: 143.13 / MAX: 154.5 MIN: 143.21 / MAX: 150.77 MIN: 142.07 / MAX: 152.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: regnety_400m A B C 0.6885 1.377 2.0655 2.754 3.4425 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 3.00 3.03 3.06 MIN: 2.93 / MAX: 3.17 MIN: 2.96 / MAX: 3.25 MIN: 2.93 / MAX: 3.65 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: squeezenet_ssd A B C 0.918 1.836 2.754 3.672 4.59 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.14, N = 3 4.05 4.08 3.98 MIN: 3.93 / MAX: 4.48 MIN: 3.96 / MAX: 5.28 MIN: 3.65 / MAX: 5.45 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: yolov4-tiny A B C 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 6.67 6.65 6.68 MIN: 6.58 / MAX: 7.31 MIN: 6.58 / MAX: 7.04 MIN: 6.56 / MAX: 8.07 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: alexnet A B C 0.3735 0.747 1.1205 1.494 1.8675 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 1.66 1.65 1.66 MIN: 1.6 / MAX: 2.65 MIN: 1.61 / MAX: 1.94 MIN: 1.61 / MAX: 2.88 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: resnet18 A B C 0.5243 1.0486 1.5729 2.0972 2.6215 SE +/- 0.03, N = 2 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 2.33 2.30 2.32 MIN: 2.24 / MAX: 3.45 MIN: 2.27 / MAX: 2.56 MIN: 2.27 / MAX: 3.53 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: vgg16 A B C 2 4 6 8 10 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 7.18 7.21 7.22 MIN: 6.68 / MAX: 8.37 MIN: 6.7 / MAX: 11.48 MIN: 6.68 / MAX: 15.04 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: googlenet A B C 0.891 1.782 2.673 3.564 4.455 SE +/- 0.10, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 3.79 3.94 3.96 MIN: 3.55 / MAX: 4.51 MIN: 3.84 / MAX: 4.16 MIN: 3.82 / MAX: 4.23 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: blazeface A B C 0.2498 0.4996 0.7494 0.9992 1.249 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 1.07 1.11 1.11 MIN: 1 / MAX: 1.36 MIN: 0.99 / MAX: 1.4 MIN: 1 / MAX: 1.29 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: efficientnet-b0 A B C 1.1453 2.2906 3.4359 4.5812 5.7265 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 5.02 5.06 5.09 MIN: 4.95 / MAX: 5.24 MIN: 4.94 / MAX: 7.39 MIN: 4.96 / MAX: 9.35 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: mnasnet A B C 0.4365 0.873 1.3095 1.746 2.1825 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 1.89 1.93 1.94 MIN: 1.83 / MAX: 3.17 MIN: 1.82 / MAX: 3.16 MIN: 1.8 / MAX: 3.08 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: shufflenet-v2 A B C 0.4118 0.8236 1.2354 1.6472 2.059 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 1.77 1.82 1.83 MIN: 1.72 / MAX: 2.71 MIN: 1.73 / MAX: 3.21 MIN: 1.75 / MAX: 2.83 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 A B C 0.5288 1.0576 1.5864 2.1152 2.644 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 2.30 2.34 2.35 MIN: 2.25 / MAX: 3.64 MIN: 2.23 / MAX: 2.78 MIN: 2.23 / MAX: 3.68 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 A B C 0.432 0.864 1.296 1.728 2.16 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.88 1.92 1.92 MIN: 1.82 / MAX: 3.01 MIN: 1.78 / MAX: 2.93 MIN: 1.81 / MAX: 3.17 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: mobilenet A B C 1.0103 2.0206 3.0309 4.0412 5.0515 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 4.48 4.48 4.49 MIN: 4.41 / MAX: 6.04 MIN: 4.39 / MAX: 5.72 MIN: 4.42 / MAX: 5.82 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Phoronix Test Suite v10.8.4