rx480common_vkvCompute AMD Ryzen 7 3800X 8-Core testing with a MSI MEG X570 ACE (MS-7C35) v1.0 (1.E2 BIOS) and AMD Radeon RX 480 8GB on Garuda Soaring via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2205228-NE-RX480COMM24&gru .
rx480common_vkvCompute Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution rx480common_vkvCompute AMD Ryzen 7 3800X 8-Core @ 3.90GHz (8 Cores / 16 Threads) MSI MEG X570 ACE (MS-7C35) v1.0 (1.E2 BIOS) AMD Starship/Matisse 32GB 1000GB Samsung SSD 980 PRO 1TB + 250GB Samsung SSD 860 AMD Radeon RX 480 8GB (1266/2000MHz) AMD Ellesmere HDMI Audio Acer VG270K Intel I211 + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX200 Garuda Soaring 5.17.9-zen1-1-zen (x86_64) KDE Plasma 5.24.5 X Server 1.21.1.3 4.6 Mesa 22.0.4 (LLVM 13.0.1 DRM 3.44) 1.3.204 GCC 12.1.0 + Clang 13.0.1 btrfs 3840x2160 OpenBenchmarking.org - Transparent Huge Pages: always - --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++ --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 - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x8701021 - GLAMOR - BAR1 / Visible vRAM Size: 256 MB - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
rx480common_vkvCompute vkpeak: fp32-scalar vkpeak: fp32-vec4 vkpeak: fp64-scalar vkpeak: fp64-vec4 vkpeak: int32-scalar vkpeak: int32-vec4 vkresample: 2x - Single 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 GPU - yolov4-tiny ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU - regnety_400m realsr-ncnn: 4x - No realsr-ncnn: 4x - Yes waifu2x-ncnn: 2x - 3 - Yes betsy: ETC2 RGB - Highest rx480common_vkvCompute 4996.90 4885.55 333.04 307.50 1149.94 1147.77 35.056 6.38 3.31 4.57 2.68 3.49 11.56 1.21 7.20 16.41 3.08 6.51 8.22 8.63 6.27 6.82 16.492 116.644 9.550 OpenBenchmarking.org
vkpeak fp32-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp32-scalar rx480common_vkvCompute 1100 2200 3300 4400 5500 SE +/- 7.39, N = 3 4996.90
vkpeak fp32-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp32-vec4 rx480common_vkvCompute 1000 2000 3000 4000 5000 SE +/- 4.29, N = 3 4885.55
vkpeak fp64-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp64-scalar rx480common_vkvCompute 70 140 210 280 350 SE +/- 10.54, N = 3 333.04
vkpeak fp64-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp64-vec4 rx480common_vkvCompute 70 140 210 280 350 SE +/- 2.07, N = 3 307.50
vkpeak int32-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int32-scalar rx480common_vkvCompute 200 400 600 800 1000 SE +/- 0.39, N = 3 1149.94
vkpeak int32-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int32-vec4 rx480common_vkvCompute 200 400 600 800 1000 SE +/- 4.34, N = 3 1147.77
VkResample Upscale: 2x - Precision: Single OpenBenchmarking.org ms, Fewer Is Better VkResample 1.0 Upscale: 2x - Precision: Single rx480common_vkvCompute 8 16 24 32 40 SE +/- 0.20, N = 3 35.06 1. (CXX) g++ options: -O3
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: mobilenet rx480common_vkvCompute 2 4 6 8 10 SE +/- 0.02, N = 3 6.38 MIN: 6.31 / MAX: 7.25 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 rx480common_vkvCompute 0.7448 1.4896 2.2344 2.9792 3.724 SE +/- 0.02, N = 3 3.31 MIN: 3.04 / MAX: 8.27 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 rx480common_vkvCompute 1.0283 2.0566 3.0849 4.1132 5.1415 SE +/- 0.01, N = 3 4.57 MIN: 4.22 / MAX: 11.24 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: shufflenet-v2 rx480common_vkvCompute 0.603 1.206 1.809 2.412 3.015 SE +/- 0.02, N = 3 2.68 MIN: 2.48 / MAX: 6.59 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: mnasnet rx480common_vkvCompute 0.7853 1.5706 2.3559 3.1412 3.9265 SE +/- 0.01, N = 3 3.49 MIN: 3.22 / MAX: 7.85 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: efficientnet-b0 rx480common_vkvCompute 3 6 9 12 15 SE +/- 0.04, N = 3 11.56 MIN: 10.47 / MAX: 17.83 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: blazeface rx480common_vkvCompute 0.2723 0.5446 0.8169 1.0892 1.3615 SE +/- 0.01, N = 3 1.21 MIN: 1.13 / MAX: 5.94 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: googlenet rx480common_vkvCompute 2 4 6 8 10 SE +/- 0.03, N = 3 7.20 MIN: 6.59 / MAX: 16.26 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: vgg16 rx480common_vkvCompute 4 8 12 16 20 SE +/- 0.02, N = 3 16.41 MIN: 16.2 / MAX: 19.91 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: resnet18 rx480common_vkvCompute 0.693 1.386 2.079 2.772 3.465 SE +/- 0.02, N = 3 3.08 MIN: 2.92 / MAX: 6.4 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: alexnet rx480common_vkvCompute 2 4 6 8 10 SE +/- 0.02, N = 3 6.51 MIN: 5.91 / MAX: 13.01 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: resnet50 rx480common_vkvCompute 2 4 6 8 10 SE +/- 0.03, N = 3 8.22 MIN: 8.04 / MAX: 15.38 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: yolov4-tiny rx480common_vkvCompute 2 4 6 8 10 SE +/- 0.03, N = 3 8.63 MIN: 8.48 / MAX: 17.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: squeezenet_ssd rx480common_vkvCompute 2 4 6 8 10 SE +/- 0.04, N = 3 6.27 MIN: 6.11 / MAX: 10.35 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: regnety_400m rx480common_vkvCompute 2 4 6 8 10 SE +/- 0.21, N = 3 6.82 MIN: 5.32 / MAX: 14.96 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
RealSR-NCNN Scale: 4x - TAA: No OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: No rx480common_vkvCompute 4 8 12 16 20 SE +/- 0.01, N = 3 16.49
RealSR-NCNN Scale: 4x - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: Yes rx480common_vkvCompute 30 60 90 120 150 SE +/- 0.40, N = 3 116.64
Waifu2x-NCNN Vulkan Scale: 2x - Denoise: 3 - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better Waifu2x-NCNN Vulkan 20200818 Scale: 2x - Denoise: 3 - TAA: Yes rx480common_vkvCompute 3 6 9 12 15 SE +/- 0.006, N = 3 9.550
Phoronix Test Suite v10.8.4