f1

AMD Ryzen 5 1600 Six-Core testing with a MSI B450-A PRO (MS-7B86) v2.0 (A.D0 BIOS) and XFX AMD Radeon RX 470/480/570/570X/580/580X/590 4GB 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 2108047-IB-F1767180826
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

NVIDIA GPU Compute 3 Tests
Vulkan Compute 3 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
XFX AMD Radeon RX 470
August 04
  23 Minutes
120W-cap
August 04
  26 Minutes
amdgpu
August 04
  3 Minutes
120W-cap-amdgpu
August 04
  1 Minute
120W-cap-amdgpu-compute
August 04
  7 Minutes
amdgpu2
August 04
  6 Minutes
amdgpu1
August 04
  4 Minutes
amdgpu3
August 04
  41 Minutes
120W-cap-amdgpu-2
August 04
  38 Minutes
cpu
August 04
  1 Hour, 34 Minutes
Invert Hiding All Results Option
  24 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):


f1ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionOpenCLXFX AMD Radeon RX 470120W-capamdgpu120W-cap-amdgpu120W-cap-amdgpu-computeamdgpu2amdgpu1amdgpu3120W-cap-amdgpu-2cpuAMD Ryzen 5 1600 Six-Core @ 3.20GHz (6 Cores / 12 Threads)MSI B450-A PRO (MS-7B86) v2.0 (A.D0 BIOS)AMD 17h16GB1000GB Western Digital WD10EZEX-08M + 240GB Patriot BurstXFX AMD Radeon RX 470/480/570/570X/580/580X/590 4GB (1226/1750MHz)AMD Ellesmere HDMI AudioVW225Realtek RTL8111/8168/8411Ubuntu 20.045.11.0-25-generic (x86_64)GNOME Shell 3.36.9X Server 1.20.94.6 Mesa 21.0.3 (LLVM 12.0.0)1.2.145Clang 12.0.1-++20210802051739+fed41342a82f-1~exp1~20210802152501.132ext41680x10504.6 Mesa 21.1.0-devel (LLVM 12.0.0)OpenCL 2.0 AMD-APP (3137.0)OpenBenchmarking.orgKernel Details- libahci.ignore_sss=1 amdgpu.ppfeaturemask=0xfffd7fff - Transparent Huge Pages: madviseProcessor Details- XFX AMD Radeon RX 470: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8001138- 120W-cap: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8001138- amdgpu: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8001138- 120W-cap-amdgpu: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8001138- 120W-cap-amdgpu-compute: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8001138- amdgpu2: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8001138- amdgpu1: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8001138- amdgpu3: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8001138- 120W-cap-amdgpu-2: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8001138- cpu: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x8001138Security 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 STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected Graphics Details- amdgpu, 120W-cap-amdgpu, 120W-cap-amdgpu-compute, amdgpu2, amdgpu1: GLAMORPython Details- amdgpu2: Python 3.8.10

f1vkpeak: fp32-scalarvkpeak: fp32-vec4vkpeak: fp64-scalarvkpeak: fp64-vec4vkpeak: int32-scalarvkpeak: int32-vec4betsy: ETC1 - Highestbetsy: ETC2 RGB - Highestglmark2: 1280 x 1024gputest: Furmark - 1024 x 768 - Windowedncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - googlenetncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - regnety_400mncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - shufflenet-v2ncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mXFX AMD Radeon RX 470120W-capamdgpu120W-cap-amdgpu120W-cap-amdgpu-computeamdgpu2amdgpu1amdgpu3120W-cap-amdgpu-2cpu4205.534158.75207.92207.48957.54969.064258.814172.91207.28208.60970.97985.9610.35712.47012.55712.24512.2457035704691868.653.424.652.943.6011.611.407.2017.433.486.479.0812.717.106.008.713.54.672.953.6211.621.417.2317.433.486.439.0812.737.135.9727.118.427.477.277.4511.402.7022.5985.0421.2217.3844.2441.8529.6118.71OpenBenchmarking.org

vkpeak

Vkpeak is a Vulkan compute benchmark inspired by OpenCL's clpeak. Vkpeak provides Vulkan compute performance measurements for FP16 / FP32 / FP64 / INT16 / INT32 scalar and vec4 performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-scalarXFX AMD Radeon RX 470120W-cap9001800270036004500SE +/- 38.11, N = 3SE +/- 11.57, N = 34205.534258.81
OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-scalarXFX AMD Radeon RX 470120W-cap7001400210028003500Min: 4158.49 / Avg: 4205.53 / Max: 4280.98Min: 4246.94 / Avg: 4258.81 / Max: 4281.94

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-vec4XFX AMD Radeon RX 470120W-cap9001800270036004500SE +/- 15.75, N = 3SE +/- 14.35, N = 34158.754172.91
OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-vec4XFX AMD Radeon RX 470120W-cap7001400210028003500Min: 4136.45 / Avg: 4158.75 / Max: 4189.17Min: 4157.36 / Avg: 4172.91 / Max: 4201.58

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-scalarXFX AMD Radeon RX 470120W-cap50100150200250SE +/- 0.68, N = 3SE +/- 1.30, N = 3207.92207.28
OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-scalarXFX AMD Radeon RX 470120W-cap4080120160200Min: 206.56 / Avg: 207.92 / Max: 208.61Min: 204.68 / Avg: 207.28 / Max: 208.6

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-vec4XFX AMD Radeon RX 470120W-cap50100150200250SE +/- 1.03, N = 3SE +/- 0.01, N = 3207.48208.60
OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-vec4XFX AMD Radeon RX 470120W-cap4080120160200Min: 205.43 / Avg: 207.48 / Max: 208.51Min: 208.59 / Avg: 208.6 / Max: 208.62

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-scalarXFX AMD Radeon RX 470120W-cap2004006008001000SE +/- 4.66, N = 3SE +/- 0.40, N = 3957.54970.97
OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-scalarXFX AMD Radeon RX 470120W-cap2004006008001000Min: 952.71 / Avg: 957.54 / Max: 966.85Min: 970.45 / Avg: 970.97 / Max: 971.75

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-vec4XFX AMD Radeon RX 470120W-cap2004006008001000SE +/- 5.15, N = 3SE +/- 0.27, N = 3969.06985.96
OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-vec4XFX AMD Radeon RX 470120W-cap2004006008001000Min: 963.87 / Avg: 969.06 / Max: 979.35Min: 985.44 / Avg: 985.96 / Max: 986.34

Betsy GPU Compressor

Betsy is an open-source GPU compressor of various GPU compression techniques. Betsy is written in GLSL for Vulkan/OpenGL (compute shader) support for GPU-based texture compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC1 - Quality: Highest120W-cap3691215SE +/- 0.03, N = 310.361. (CXX) clang++ options: -O3 -O2 -lpthread -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC2 RGB - Quality: Highest120W-capamdgpu120W-cap-amdgpu120W-cap-amdgpu-compute3691215SE +/- 0.27, N = 15SE +/- 0.29, N = 14SE +/- 0.04, N = 3SE +/- 0.04, N = 312.4712.5612.2512.251. (CXX) clang++ options: -O3 -O2 -lpthread -ldl
OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC2 RGB - Quality: Highest120W-capamdgpu120W-cap-amdgpu120W-cap-amdgpu-compute48121620Min: 12.18 / Avg: 12.47 / Max: 16.23Min: 12.22 / Avg: 12.56 / Max: 16.27Min: 12.21 / Avg: 12.25 / Max: 12.32Min: 12.18 / Avg: 12.25 / Max: 12.311. (CXX) clang++ options: -O3 -O2 -lpthread -ldl

GLmark2

This is a test of Linaro's glmark2 port, currently using the X11 OpenGL 2.0 target. GLmark2 is a basic OpenGL benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterGLmark2 2020.04Resolution: 1280 x 1024120W-cap-amdgpu-computeamdgpu21500300045006000750070357046

GpuTest

GpuTest is a cross-platform OpenGL benchmark developed at Geeks3D.com that offers tech demos such as FurMark, TessMark, and other workloads to stress various areas of GPUs and drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Furmark - Resolution: 1024 x 768 - Mode: Windowedamdgpu12K4K6K8K10KSE +/- 129.83, N = 39186

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 20210720Target: Vulkan GPU - Model: mobilenetamdgpu3120W-cap-amdgpu-2246810SE +/- 0.01, N = 3SE +/- 0.09, N = 38.658.71MIN: 8.42 / MAX: 28.57MIN: 8.43 / MAX: 26.591. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mobilenetamdgpu3120W-cap-amdgpu-23691215Min: 8.63 / Avg: 8.65 / Max: 8.67Min: 8.59 / Avg: 8.71 / Max: 8.881. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2amdgpu3120W-cap-amdgpu-20.78751.5752.36253.153.9375SE +/- 0.02, N = 3SE +/- 0.10, N = 33.423.50MIN: 3.36 / MAX: 17.85MIN: 3.36 / MAX: 6.231. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2amdgpu3120W-cap-amdgpu-2246810Min: 3.4 / Avg: 3.42 / Max: 3.45Min: 3.4 / Avg: 3.5 / Max: 3.71. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3amdgpu3120W-cap-amdgpu-21.05082.10163.15244.20325.254SE +/- 0.02, N = 3SE +/- 0.03, N = 34.654.67MIN: 4.59 / MAX: 18.53MIN: 4.54 / MAX: 18.031. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3amdgpu3120W-cap-amdgpu-2246810Min: 4.62 / Avg: 4.65 / Max: 4.68Min: 4.63 / Avg: 4.67 / Max: 4.741. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: shufflenet-v2amdgpu3120W-cap-amdgpu-20.66381.32761.99142.65523.319SE +/- 0.01, N = 3SE +/- 0.00, N = 32.942.95MIN: 2.82 / MAX: 4.7MIN: 2.82 / MAX: 4.81. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: shufflenet-v2amdgpu3120W-cap-amdgpu-2246810Min: 2.93 / Avg: 2.94 / Max: 2.95Min: 2.95 / Avg: 2.95 / Max: 2.961. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mnasnetamdgpu3120W-cap-amdgpu-20.81451.6292.44353.2584.0725SE +/- 0.01, N = 3SE +/- 0.02, N = 33.603.62MIN: 3.56 / MAX: 6.22MIN: 3.56 / MAX: 16.021. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mnasnetamdgpu3120W-cap-amdgpu-2246810Min: 3.59 / Avg: 3.6 / Max: 3.62Min: 3.6 / Avg: 3.62 / Max: 3.651. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: efficientnet-b0amdgpu3120W-cap-amdgpu-23691215SE +/- 0.01, N = 3SE +/- 0.01, N = 311.6111.62MIN: 11.1 / MAX: 17.11MIN: 11.11 / MAX: 16.431. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: efficientnet-b0amdgpu3120W-cap-amdgpu-23691215Min: 11.59 / Avg: 11.61 / Max: 11.62Min: 11.6 / Avg: 11.62 / Max: 11.651. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: blazefaceamdgpu3120W-cap-amdgpu-20.31730.63460.95191.26921.5865SE +/- 0.01, N = 3SE +/- 0.01, N = 31.401.41MIN: 1.33 / MAX: 2.17MIN: 1.34 / MAX: 3.811. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: blazefaceamdgpu3120W-cap-amdgpu-2246810Min: 1.39 / Avg: 1.4 / Max: 1.41Min: 1.39 / Avg: 1.41 / Max: 1.421. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: googlenetamdgpu3120W-cap-amdgpu-2246810SE +/- 0.01, N = 3SE +/- 0.02, N = 37.207.23MIN: 7.15 / MAX: 9.42MIN: 7.14 / MAX: 21.571. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: googlenetamdgpu3120W-cap-amdgpu-23691215Min: 7.19 / Avg: 7.2 / Max: 7.22Min: 7.2 / Avg: 7.23 / Max: 7.281. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: vgg16amdgpu3120W-cap-amdgpu-248121620SE +/- 0.03, N = 3SE +/- 0.05, N = 317.4317.43MIN: 17.01 / MAX: 20.67MIN: 16.89 / MAX: 20.761. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: vgg16amdgpu3120W-cap-amdgpu-248121620Min: 17.39 / Avg: 17.43 / Max: 17.49Min: 17.34 / Avg: 17.43 / Max: 17.481. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet18amdgpu3120W-cap-amdgpu-20.7831.5662.3493.1323.915SE +/- 0.01, N = 3SE +/- 0.01, N = 33.483.48MIN: 3.34 / MAX: 5.65MIN: 3.36 / MAX: 6.721. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet18amdgpu3120W-cap-amdgpu-2246810Min: 3.46 / Avg: 3.48 / Max: 3.5Min: 3.47 / Avg: 3.48 / Max: 3.51. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: alexnetamdgpu3120W-cap-amdgpu-2246810SE +/- 0.01, N = 3SE +/- 0.02, N = 36.476.43MIN: 6.14 / MAX: 8.48MIN: 6.14 / MAX: 20.061. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: alexnetamdgpu3120W-cap-amdgpu-23691215Min: 6.45 / Avg: 6.47 / Max: 6.5Min: 6.4 / Avg: 6.43 / Max: 6.471. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet50amdgpu3120W-cap-amdgpu-23691215SE +/- 0.03, N = 3SE +/- 0.03, N = 39.089.08MIN: 8.83 / MAX: 20.52MIN: 8.84 / MAX: 20.711. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet50amdgpu3120W-cap-amdgpu-23691215Min: 9.05 / Avg: 9.08 / Max: 9.14Min: 9.05 / Avg: 9.08 / Max: 9.141. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: yolov4-tinyamdgpu3120W-cap-amdgpu-23691215SE +/- 0.03, N = 3SE +/- 0.01, N = 312.7112.73MIN: 12.46 / MAX: 18.08MIN: 12.48 / MAX: 25.81. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: yolov4-tinyamdgpu3120W-cap-amdgpu-248121620Min: 12.67 / Avg: 12.71 / Max: 12.77Min: 12.72 / Avg: 12.73 / Max: 12.751. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: squeezenet_ssdamdgpu3120W-cap-amdgpu-2246810SE +/- 0.01, N = 3SE +/- 0.02, N = 37.107.13MIN: 6.93 / MAX: 10.04MIN: 6.95 / MAX: 21.371. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: squeezenet_ssdamdgpu3120W-cap-amdgpu-23691215Min: 7.09 / Avg: 7.1 / Max: 7.11Min: 7.09 / Avg: 7.13 / Max: 7.171. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: regnety_400mamdgpu3120W-cap-amdgpu-2246810SE +/- 0.02, N = 3SE +/- 0.01, N = 36.005.97MIN: 5.72 / MAX: 18.9MIN: 5.73 / MAX: 8.351. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: regnety_400mamdgpu3120W-cap-amdgpu-2246810Min: 5.96 / Avg: 6 / Max: 6.04Min: 5.96 / Avg: 5.97 / Max: 5.991. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mobilenetcpu612182430SE +/- 0.17, N = 327.11MIN: 26.49 / MAX: 46.941. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v2-v2 - Model: mobilenet-v2cpu246810SE +/- 0.24, N = 38.42MIN: 7.95 / MAX: 36.571. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v3-v3 - Model: mobilenet-v3cpu246810SE +/- 0.05, N = 37.47MIN: 7.13 / MAX: 21.221. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: shufflenet-v2cpu246810SE +/- 0.09, N = 37.27MIN: 7 / MAX: 10.531. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mnasnetcpu246810SE +/- 0.02, N = 37.45MIN: 7.32 / MAX: 10.41. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: efficientnet-b0cpu3691215SE +/- 0.07, N = 311.40MIN: 11.1 / MAX: 25.421. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: blazefacecpu0.60751.2151.82252.433.0375SE +/- 0.02, N = 32.70MIN: 2.6 / MAX: 5.321. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: googlenetcpu510152025SE +/- 0.13, N = 322.59MIN: 22.08 / MAX: 38.691. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: vgg16cpu20406080100SE +/- 1.35, N = 385.04MIN: 82.51 / MAX: 122.641. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet18cpu510152025SE +/- 0.06, N = 321.22MIN: 20.8 / MAX: 38.821. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: alexnetcpu48121620SE +/- 0.01, N = 317.38MIN: 17.16 / MAX: 30.651. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet50cpu1020304050SE +/- 0.39, N = 344.24MIN: 43.13 / MAX: 60.991. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: yolov4-tinycpu1020304050SE +/- 0.56, N = 341.85MIN: 40.66 / MAX: 57.991. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: squeezenet_ssdcpu714212835SE +/- 0.20, N = 329.61MIN: 28.91 / MAX: 46.641. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: regnety_400mcpu510152025SE +/- 0.13, N = 318.71MIN: 18.29 / MAX: 35.251. (CXX) clang++ options: -O3 -rdynamic -lomp -lpthread -pthread