ncnn mnn alderlake p

Intel Core i7-1280P testing with a MSI MS-14C6 (E14C6IMS.115 BIOS) and MSI Intel ADL GT2 15GB 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 2208135-NE-NCNNMNNAL41
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:

HPC - High Performance Computing 2 Tests
Machine Learning 2 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
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
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
A
August 13
  20 Hours, 11 Minutes
B
August 13
  2 Hours, 12 Minutes
C
August 14
  2 Hours, 1 Minute
Invert Hiding All Results Option
  8 Hours, 8 Minutes

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


ncnn mnn alderlake pOpenBenchmarking.orgPhoronix Test Suite 10.8.4Intel Core i7-1280P @ 4.80GHz (14 Cores / 20 Threads)MSI MS-14C6 (E14C6IMS.115 BIOS)Intel Alder Lake PCH16GB1024GB Micron_3400_MTFDKBA1T0TFHMSI Intel ADL GT2 15GB (1450MHz)Intel Alder Lake PCH-P HD AudioIntel Alder Lake-P PCH CNVi WiFiArch rolling5.18.16-arch1-1 (x86_64)KDE Plasma 5.25.4X Server 1.21.1.4 + Wayland4.6 Mesa 22.1.41.3.211GCC 12.1.1 20220730ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionNcnn Mnn Alderlake P BenchmarksSystem Logs- 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++,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 - Scaling Governor: intel_cpufreq schedutil - CPU Microcode: 0x41c- 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

ABCResult OverviewPhoronix Test Suite 10.8.4100%133%166%200%NCNNMobile Neural NetworkNCNNMobile Neural NetworkNCNNNCNNNCNNMobile Neural NetworkMobile Neural NetworkNCNNNCNNNCNNMobile Neural NetworkMobile Neural NetworkNCNNNCNNNCNNNCNNNCNNNCNNNCNNMobile Neural NetworkNCNNNCNNNCNNVulkan GPU - yolov4-tinyresnet-v2-50CPU - mnasnetsqueezenetv1.1Vulkan GPU - mnasnetVulkan GPU - shufflenet-v2Vulkan GPU-v3-v3 - mobilenet-v3inception-v3mobilenet-v1-1.0Vulkan GPU - regnety_400mVulkan GPU - FastestDetVulkan GPU - resnet50SqueezeNetV1.0mobilenetV3Vulkan GPU - googlenetVulkan GPU-v2-v2 - mobilenet-v2Vulkan GPU - squeezenet_ssdVulkan GPU - mobilenetVulkan GPU - alexnetVulkan GPU - vgg16Vulkan GPU - vision_transformerMobileNetV2_224Vulkan GPU - efficientnet-b0Vulkan GPU - blazefaceVulkan GPU - resnet18

ncnn mnn alderlake pmnn: mobilenetV3mnn: squeezenetv1.1mnn: resnet-v2-50mnn: SqueezeNetV1.0mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3ncnn: 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_400mncnn: CPU - vision_transformerncnn: CPU - FastestDetncnn: 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: Vulkan GPU - vision_transformerncnn: Vulkan GPU - FastestDetABC3.1056.64454.10410.4085.8567.00156.99116.723.523.254.314.237.981.6713.6544.8810.677.6623.5125.1015.8014.00332.685.6211.724.024.533.054.089.281.1713.3472.6713.1110.8023.2645.6510.026.12508.634.593.0926.84742.59310.5685.7937.06357.27315.853.562.983.353.155.871.6712.9141.2210.157.3222.2223.6714.813.47322.165.3512.273.894.942.694.539.041.1414.573.6312.8911.2623.869.4610.585.42509.424.82.8535.58335.4249.5545.6616.15149.28615.863.592.983.383.155.361.5812.8441.1410.137.3122.2623.5914.7813.35321.3711.653.734.252.573.89.031.1413.6970.6412.8110.7521.4729.829.895.42489.734.33OpenBenchmarking.org

Mobile Neural Network

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenetV3ABC0.69861.39722.09582.79443.493SE +/- 0.034, N = 123.1053.0922.853MIN: 2.64 / MAX: 7.34MIN: 2.82 / MAX: 6.95MIN: 2.68 / MAX: 3.271. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenetV3ABC246810Min: 2.79 / Avg: 3.11 / Max: 3.311. (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

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: squeezenetv1.1ABC246810SE +/- 0.103, N = 126.6446.8475.583MIN: 5.69 / MAX: 12.68MIN: 6.71 / MAX: 11.63MIN: 5.46 / MAX: 5.91. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: squeezenetv1.1ABC3691215Min: 5.78 / Avg: 6.64 / Max: 6.921. (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

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: resnet-v2-50ABC1224364860SE +/- 1.74, N = 1254.1042.5935.42MIN: 25.35 / MAX: 63.96MIN: 29.52 / MAX: 53.86MIN: 25.55 / MAX: 46.821. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: resnet-v2-50ABC1122334455Min: 35.7 / Avg: 54.1 / Max: 57.641. (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

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: SqueezeNetV1.0ABC3691215SE +/- 0.117, N = 1210.40810.5689.554MIN: 9.15 / MAX: 15.71MIN: 10.3 / MAX: 14.69MIN: 9.44 / MAX: 10.431. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: SqueezeNetV1.0ABC3691215Min: 9.36 / Avg: 10.41 / Max: 10.71. (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

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: MobileNetV2_224ABC1.31762.63523.95285.27046.588SE +/- 0.033, N = 125.8565.7935.661MIN: 5.41 / MAX: 26.24MIN: 5.7 / MAX: 6.18MIN: 5.55 / MAX: 6.041. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: MobileNetV2_224ABC246810Min: 5.53 / Avg: 5.86 / Max: 5.951. (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

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenet-v1-1.0ABC246810SE +/- 0.091, N = 127.0017.0636.151MIN: 6.16 / MAX: 11.52MIN: 6.75 / MAX: 12.29MIN: 5.64 / MAX: 6.561. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenet-v1-1.0ABC3691215Min: 6.22 / Avg: 7 / Max: 7.211. (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

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: inception-v3ABC1326395265SE +/- 0.71, N = 1256.9957.2749.29MIN: 50.82 / MAX: 79.99MIN: 51.21 / MAX: 62.84MIN: 48.8 / MAX: 59.331. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: inception-v3ABC1122334455Min: 51.65 / Avg: 56.99 / Max: 58.211. (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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetABC48121620SE +/- 0.17, N = 316.7215.8514.55MIN: 16.2 / MAX: 20.54MIN: 15.19 / MAX: 16.79MIN: 14.24 / MAX: 14.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetABC48121620Min: 16.51 / Avg: 16.72 / Max: 17.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2ABC0.80781.61562.42343.23124.039SE +/- 0.04, N = 33.523.563.55MIN: 3.43 / MAX: 3.77MIN: 3.52 / MAX: 3.76MIN: 3.51 / MAX: 3.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2ABC246810Min: 3.47 / Avg: 3.52 / Max: 3.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v3-v3 - Model: mobilenet-v3ABC0.73131.46262.19392.92523.6565SE +/- 0.21, N = 33.252.982.96MIN: 2.96 / MAX: 4.66MIN: 2.94 / MAX: 3.33MIN: 2.93 / MAX: 3.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v3-v3 - Model: mobilenet-v3ABC246810Min: 2.99 / Avg: 3.25 / Max: 3.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2ABC0.96981.93962.90943.87924.849SE +/- 0.48, N = 34.313.353.32MIN: 3.32 / MAX: 5.02MIN: 3.31 / MAX: 3.43MIN: 3.29 / MAX: 3.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2ABC246810Min: 3.36 / Avg: 4.31 / Max: 4.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetABC0.95181.90362.85543.80724.759SE +/- 0.53, N = 34.233.153.15MIN: 3.14 / MAX: 5.36MIN: 3.12 / MAX: 3.38MIN: 3.1 / MAX: 3.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetABC246810Min: 3.17 / Avg: 4.23 / Max: 4.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0ABC246810SE +/- 0.05, N = 37.985.875.37MIN: 7.65 / MAX: 8.77MIN: 5.32 / MAX: 7.74MIN: 5.32 / MAX: 5.821. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0ABC3691215Min: 7.88 / Avg: 7.98 / Max: 8.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceABC0.37580.75161.12741.50321.879SE +/- 0.02, N = 31.671.671.45MIN: 1.57 / MAX: 2MIN: 1.59 / MAX: 1.91MIN: 1.41 / MAX: 1.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceABC246810Min: 1.64 / Avg: 1.67 / Max: 1.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetABC48121620SE +/- 0.05, N = 313.6512.9111.73MIN: 12.66 / MAX: 14.19MIN: 12.2 / MAX: 24.6MIN: 11.21 / MAX: 20.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetABC48121620Min: 13.56 / Avg: 13.65 / Max: 13.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16ABC1020304050SE +/- 0.19, N = 344.8841.2237.40MIN: 40.62 / MAX: 52.28MIN: 38.97 / MAX: 41.77MIN: 36.67 / MAX: 37.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16ABC918273645Min: 44.5 / Avg: 44.88 / Max: 45.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18ABC3691215SE +/- 0.02, N = 310.6710.159.34MIN: 10.06 / MAX: 11.02MIN: 9.65 / MAX: 12.03MIN: 8.94 / MAX: 9.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18ABC3691215Min: 10.64 / Avg: 10.67 / Max: 10.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetABC246810SE +/- 0.02, N = 37.667.326.81MIN: 7.19 / MAX: 7.98MIN: 6.96 / MAX: 10.38MIN: 6.33 / MAX: 9.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetABC3691215Min: 7.62 / Avg: 7.66 / Max: 7.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50ABC612182430SE +/- 0.05, N = 323.5122.2220.37MIN: 22.4 / MAX: 24.27MIN: 21.82 / MAX: 22.67MIN: 19.92 / MAX: 20.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50ABC510152025Min: 23.42 / Avg: 23.51 / Max: 23.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyABC612182430SE +/- 0.22, N = 325.1023.6721.85MIN: 24.42 / MAX: 26.07MIN: 23.36 / MAX: 26.66MIN: 21.44 / MAX: 22.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyABC612182430Min: 24.86 / Avg: 25.1 / Max: 25.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdABC48121620SE +/- 0.08, N = 315.8014.8013.70MIN: 15.35 / MAX: 20.36MIN: 14.52 / MAX: 15.22MIN: 13.45 / MAX: 14.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdABC48121620Min: 15.67 / Avg: 15.8 / Max: 15.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mABC48121620SE +/- 0.07, N = 314.0013.4712.06MIN: 13.54 / MAX: 24.86MIN: 13.23 / MAX: 14.67MIN: 10.07 / MAX: 12.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mABC48121620Min: 13.9 / Avg: 14 / Max: 14.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerABC70140210280350SE +/- 3.40, N = 3332.68322.16310.75MIN: 328.62 / MAX: 346.54MIN: 320.38 / MAX: 331.08MIN: 304.99 / MAX: 326.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerABC60120180240300Min: 329.21 / Avg: 332.68 / Max: 339.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetAB1.26452.5293.79355.0586.3225SE +/- 0.03, N = 35.625.35MIN: 5.41 / MAX: 6.47MIN: 5.24 / MAX: 5.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetAB246810Min: 5.59 / Avg: 5.62 / Max: 5.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mobilenetABC3691215SE +/- 0.28, N = 1211.7212.2711.65MIN: 9.53 / MAX: 24.46MIN: 10.89 / MAX: 19.93MIN: 10.75 / MAX: 13.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mobilenetABC48121620Min: 10.05 / Avg: 11.72 / Max: 13.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2ABC0.90451.8092.71353.6184.5225SE +/- 0.14, N = 124.023.893.73MIN: 3.32 / MAX: 6.9MIN: 3.57 / MAX: 4.1MIN: 3.44 / MAX: 3.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2ABC246810Min: 3.76 / Avg: 4.02 / Max: 5.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3ABC1.11152.2233.33454.4465.5575SE +/- 0.12, N = 124.534.944.25MIN: 3.95 / MAX: 6.26MIN: 4.17 / MAX: 7.32MIN: 4.01 / MAX: 6.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3ABC246810Min: 4.22 / Avg: 4.53 / Max: 5.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: shufflenet-v2ABC0.68631.37262.05892.74523.4315SE +/- 0.18, N = 123.052.692.57MIN: 2.42 / MAX: 5.3MIN: 2.48 / MAX: 2.99MIN: 2.36 / MAX: 2.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: shufflenet-v2ABC246810Min: 2.65 / Avg: 3.05 / Max: 4.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mnasnetABC1.01932.03863.05794.07725.0965SE +/- 0.11, N = 124.084.533.80MIN: 3.57 / MAX: 5.6MIN: 3.68 / MAX: 5.19MIN: 3.6 / MAX: 3.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mnasnetABC246810Min: 3.82 / Avg: 4.08 / Max: 5.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: efficientnet-b0ABC3691215SE +/- 0.09, N = 129.289.049.03MIN: 8.19 / MAX: 12MIN: 8.85 / MAX: 11.19MIN: 8.83 / MAX: 9.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: efficientnet-b0ABC3691215Min: 9.05 / Avg: 9.28 / Max: 10.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: blazefaceABC0.26330.52660.78991.05321.3165SE +/- 0.03, N = 121.171.141.14MIN: 0.92 / MAX: 2.06MIN: 0.98 / MAX: 1.52MIN: 0.98 / MAX: 1.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: blazefaceABC246810Min: 1.12 / Avg: 1.17 / Max: 1.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: googlenetABC48121620SE +/- 0.16, N = 1213.3414.5013.69MIN: 10.54 / MAX: 16.98MIN: 12.38 / MAX: 16MIN: 12.06 / MAX: 15.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: googlenetABC48121620Min: 12.7 / Avg: 13.34 / Max: 14.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vgg16ABC1632486480SE +/- 0.28, N = 1272.6773.6370.64MIN: 43.07 / MAX: 78.48MIN: 69.53 / MAX: 74.49MIN: 63.52 / MAX: 71.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vgg16ABC1428425670Min: 71.67 / Avg: 72.67 / Max: 74.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet18ABC3691215SE +/- 0.09, N = 1213.1112.8912.81MIN: 11.19 / MAX: 16.64MIN: 12.25 / MAX: 15.33MIN: 12.12 / MAX: 13.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet18ABC48121620Min: 12.81 / Avg: 13.11 / Max: 14.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: alexnetABC3691215SE +/- 0.02, N = 1210.8011.2610.75MIN: 7.28 / MAX: 13.01MIN: 7.89 / MAX: 13.07MIN: 10.41 / MAX: 11.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: alexnetABC3691215Min: 10.76 / Avg: 10.8 / Max: 10.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet50ABC612182430SE +/- 0.32, N = 1223.2623.8021.47MIN: 20.63 / MAX: 26.52MIN: 21.07 / MAX: 25.25MIN: 20.74 / MAX: 24.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet50ABC612182430Min: 21.65 / Avg: 23.26 / Max: 24.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: yolov4-tinyABC1530456075SE +/- 3.07, N = 1245.6569.4629.82MIN: 19.69 / MAX: 108.9MIN: 21.1 / MAX: 108.29MIN: 20.72 / MAX: 68.141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: yolov4-tinyABC1326395265Min: 29.47 / Avg: 45.65 / Max: 63.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: squeezenet_ssdABC3691215SE +/- 0.10, N = 1210.0210.589.89MIN: 9.28 / MAX: 40.24MIN: 9.75 / MAX: 12.46MIN: 9.64 / MAX: 10.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: squeezenet_ssdABC3691215Min: 9.59 / Avg: 10.02 / Max: 10.821. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: regnety_400mABC246810SE +/- 0.21, N = 126.125.425.42MIN: 5.16 / MAX: 9.07MIN: 5.18 / MAX: 8.31MIN: 4.77 / MAX: 7.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: regnety_400mABC246810Min: 5.38 / Avg: 6.12 / Max: 7.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vision_transformerABC110220330440550SE +/- 3.55, N = 12508.63509.42489.73MIN: 335.21 / MAX: 1310.95MIN: 386.46 / MAX: 1081.95MIN: 353.26 / MAX: 601.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vision_transformerABC90180270360450Min: 477.54 / Avg: 508.63 / Max: 527.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: FastestDetABC1.082.163.244.325.4SE +/- 0.17, N = 124.594.804.33MIN: 3.21 / MAX: 7.11MIN: 4.52 / MAX: 5.04MIN: 4.09 / MAX: 4.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: FastestDetABC246810Min: 3.5 / Avg: 4.59 / Max: 5.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread