ncnn R7-7950X

AMD Ryzen 9 7950X3D 16-Core testing with a MSI MAG X670E TOMAHAWK WIFI (MS-7E12) v1.0 (1.80 BIOS) and NVIDIA RTX A6000 48GB on Ubuntu 22.04 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 2407054-SIDD-NCNNR7788
Jump To Table - Results

Statistics

Remove Outliers Before Calculating Averages

Graph Settings

Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
A6000 48GB
July 05
  1 Hour, 1 Minute
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


ncnn R7-7950XOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 7950X3D 16-Core @ 5.76GHz (16 Cores / 32 Threads)MSI MAG X670E TOMAHAWK WIFI (MS-7E12) v1.0 (1.80 BIOS)AMD Device 14d84 x 32GB DRAM-3600MT/s F5-6800J3445G32G2000GB Samsung SSD 990 PRO 2TB + 2 x 6001GB TOSHIBA MG08ADA6NVIDIA RTX A6000 48GBNVIDIA GA102 HD AudioBenQ GW2480LRealtek RTL8125 2.5GbE + MEDIATEK Device 0616Ubuntu 22.046.5.0-41-generic (x86_64)GNOME Shell 42.9X Server 1.21.1.4NVIDIA 535.183.014.6.01.3.242GCC 11.4.0 + CUDA 12.2ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionNcnn R7-7950X BenchmarksSystem Logs- Transparent Huge Pages: madvise- --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 - Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601206 - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: 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

ncnn R7-7950Xncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3ncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU - FastestDetncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU-v3-v3 - mobilenet-v3A6000 48GB41.8110.599.0616.7210.5213.335.516.4836.929.843.804.143.9610.523.831.605.133.96OpenBenchmarking.org

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vision_transformerA6000 48GB1020304050SE +/- 0.55, N = 341.81MIN: 35.48 / MAX: 161.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: regnety_400mA6000 48GB3691215SE +/- 0.18, N = 310.59MIN: 9.36 / MAX: 100.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: squeezenet_ssdA6000 48GB3691215SE +/- 0.19, N = 39.06MIN: 7.52 / MAX: 128.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: yolov4-tinyA6000 48GB48121620SE +/- 0.31, N = 316.72MIN: 13.94 / MAX: 163.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3A6000 48GB3691215SE +/- 0.14, N = 310.52MIN: 8.86 / MAX: 113.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet50A6000 48GB3691215SE +/- 0.22, N = 313.33MIN: 11.19 / MAX: 131.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: alexnetA6000 48GB1.23982.47963.71944.95926.199SE +/- 0.16, N = 35.51MIN: 4.25 / MAX: 71.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet18A6000 48GB246810SE +/- 0.11, N = 36.48MIN: 5.04 / MAX: 126.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vgg16A6000 48GB816243240SE +/- 0.66, N = 336.92MIN: 28.79 / MAX: 237.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: googlenetA6000 48GB3691215SE +/- 0.14, N = 39.84MIN: 8.2 / MAX: 125.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mnasnetA6000 48GB0.8551.712.5653.424.275SE +/- 0.04, N = 33.80MIN: 3.1 / MAX: 56.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: shufflenet-v2A6000 48GB0.93151.8632.79453.7264.6575SE +/- 0.11, N = 34.14MIN: 3.65 / MAX: 99.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2A6000 48GB0.8911.7822.6733.5644.455SE +/- 0.05, N = 33.96MIN: 3.11 / MAX: 116.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mobilenetA6000 48GB3691215SE +/- 0.14, N = 310.52MIN: 8.86 / MAX: 113.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: FastestDetA6000 48GB0.86181.72362.58543.44724.309SE +/- 0.41, N = 33.83MIN: 2.89 / MAX: 57.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: blazefaceA6000 48GB0.360.721.081.441.8SE +/- 0.15, N = 31.60MIN: 1.26 / MAX: 61.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: efficientnet-b0A6000 48GB1.15432.30863.46294.61725.7715SE +/- 0.29, N = 35.13MIN: 4.29 / MAX: 142.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3A6000 48GB0.8911.7822.6733.5644.455SE +/- 0.31, N = 33.96MIN: 2.93 / MAX: 216.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread