nn cxl x

Intel Core i9-10980XE testing with a ASRock X299 Steel Legend (P1.30 BIOS) and llvmpipe on Ubuntu 22.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2208136-PTS-NNCXLX6264&grs&sro.

nn cxl xProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionABCIntel Core i9-10980XE @ 4.80GHz (18 Cores / 36 Threads)ASRock X299 Steel Legend (P1.30 BIOS)Intel Sky Lake-E DMI3 Registers32GBSamsung SSD 970 PRO 512GBllvmpipeRealtek ALC1220Intel I219-V + Intel I211Ubuntu 22.045.19.0-051900rc7-generic (x86_64)GNOME Shell 42.2X Server 1.21.1.34.5 Mesa 22.0.1 (LLVM 13.0.1 256 bits)1.2.204GCC 11.2.0ext41024x768OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --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-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/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 Processor Details- Scaling Governor: intel_cpufreq schedutil - CPU Microcode: 0x5003302Security Details- itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of Enhanced IBRS + 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: Mitigation of TSX disabled

nn cxl xmnn: mobilenetV3mnn: mobilenet-v1-1.0mnn: resnet-v2-50svt-av1: Preset 10 - Bosphorus 1080pmnn: MobileNetV2_224mnn: SqueezeNetV1.0ncnn: CPU - efficientnet-b0mnn: inception-v3ncnn: CPU - mobilenetncnn: CPU - alexnetsvt-av1: Preset 12 - Bosphorus 1080pmnn: squeezenetv1.1ncnn: CPU - vgg16ncnn: CPU - regnety_400mncnn: CPU - FastestDetsvt-av1: Preset 8 - Bosphorus 1080pncnn: CPU - blazefacesvt-av1: Preset 10 - Bosphorus 4Ksvt-av1: Preset 8 - Bosphorus 4Ksvt-av1: Preset 12 - Bosphorus 4Kncnn: CPU - googlenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - squeezenet_ssdncnn: CPU - resnet50svt-av1: Preset 4 - Bosphorus 4Kncnn: CPU - resnet18ncnn: CPU - yolov4-tinysvt-av1: Preset 4 - Bosphorus 1080pncnn: CPU - shufflenet-v2ncnn: CPU - vision_transformerncnn: CPU - mnasnetncnn: CPU-v3-v3 - mobilenet-v3ABC2.1742.4159.902150.993.4774.4967.2720.44814.736.09166.3882.40432.5218.66.4973.7982.374.12839.346104.0111.585.5617.814.881.5498.5524.23.675.44151.664.814.952.1822.60210.099141.193.6674.7337.0621.33614.56.08168.9532.42331.6419.076.6175.4362.3572.91639.108105.7211.635.4917.6414.691.5668.6424.113.6645.48152.084.794.961.92.5589.374148.7323.4424.4496.9620.67714.176.27171.432.35232.3118.896.4674.6292.3472.56938.6105.92211.445.4817.5714.861.5678.59243.645.46151.344.84.95OpenBenchmarking.org

Mobile Neural Network

Model: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenetV3ABC0.4910.9821.4731.9642.4552.1742.1821.900MIN: 2.09 / MAX: 2.27MIN: 2.11 / MAX: 2.64MIN: 1.82 / MAX: 2.011. (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.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenet-v1-1.0ABC0.58551.1711.75652.3422.92752.4152.6022.558MIN: 2.25 / MAX: 2.72MIN: 2.4 / MAX: 2.97MIN: 2.36 / MAX: 2.931. (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.orgms, Fewer Is BetterMobile Neural Network 2.0Model: resnet-v2-50ABC36912159.90210.0999.374MIN: 9.29 / MAX: 11.83MIN: 9.37 / MAX: 11.3MIN: 9.11 / MAX: 10.641. (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

SVT-AV1

Encoder Mode: Preset 10 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 10 - Input: Bosphorus 1080pABC306090120150150.99141.19148.731. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Mobile Neural Network

Model: MobileNetV2_224

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: MobileNetV2_224ABC0.82511.65022.47533.30044.12553.4773.6673.442MIN: 3.2 / MAX: 4.39MIN: 3.45 / MAX: 3.93MIN: 3.17 / MAX: 4.621. (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.orgms, Fewer Is BetterMobile Neural Network 2.0Model: SqueezeNetV1.0ABC1.06492.12983.19474.25965.32454.4964.7334.449MIN: 4.43 / MAX: 4.77MIN: 4.62 / MAX: 5.32MIN: 4.4 / MAX: 5.751. (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: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0ABC2468107.277.066.96MIN: 7.16 / MAX: 9.22MIN: 6.94 / MAX: 9.1MIN: 6.86 / MAX: 8.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Mobile Neural Network

Model: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: inception-v3ABC51015202520.4521.3420.68MIN: 20.24 / MAX: 21.04MIN: 21.11 / MAX: 22.3MIN: 20.43 / MAX: 21.911. (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: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetABC4812162014.7314.5014.17MIN: 14.63 / MAX: 15.32MIN: 14.38 / MAX: 15.22MIN: 14.08 / MAX: 14.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetABC2468106.096.086.27MIN: 5.99 / MAX: 8.04MIN: 5.97 / MAX: 7.86MIN: 6.16 / MAX: 8.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

SVT-AV1

Encoder Mode: Preset 12 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 12 - Input: Bosphorus 1080pABC4080120160200166.39168.95171.431. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Mobile Neural Network

Model: squeezenetv1.1

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: squeezenetv1.1ABC0.54521.09041.63562.18082.7262.4042.4232.352MIN: 2.26 / MAX: 2.97MIN: 2.28 / MAX: 2.82MIN: 2.18 / MAX: 2.941. (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: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16ABC81624324032.5231.6432.31MIN: 32.2 / MAX: 44.81MIN: 31.44 / MAX: 33.12MIN: 32.01 / MAX: 43.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mABC51015202518.6019.0718.89MIN: 18.24 / MAX: 20.47MIN: 18.73 / MAX: 21.84MIN: 18.57 / MAX: 20.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetABC2468106.496.616.46MIN: 6.42 / MAX: 6.99MIN: 6.51 / MAX: 12.67MIN: 6.38 / MAX: 6.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 8 - Input: Bosphorus 1080pABC2040608010073.8075.4474.631. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceABC0.52881.05761.58642.11522.6442.302.352.34MIN: 2.25 / MAX: 3.61MIN: 2.29 / MAX: 4.16MIN: 2.26 / MAX: 5.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

SVT-AV1

Encoder Mode: Preset 10 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 10 - Input: Bosphorus 4KABC163248648074.1372.9272.571. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 8 - Input: Bosphorus 4KABC91827364539.3539.1138.601. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 12 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 12 - Input: Bosphorus 4KABC20406080100104.01105.72105.921. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetABC369121511.5811.6311.44MIN: 11.39 / MAX: 13.52MIN: 11.45 / MAX: 13.61MIN: 11.26 / MAX: 13.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2ABC1.2512.5023.7535.0046.2555.565.495.48MIN: 5.47 / MAX: 6.95MIN: 5.37 / MAX: 7.38MIN: 5.39 / MAX: 7.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdABC4812162017.8017.6417.57MIN: 17.65 / MAX: 18.65MIN: 17.43 / MAX: 18.21MIN: 17.36 / MAX: 18.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50ABC4812162014.8814.6914.86MIN: 14.7 / MAX: 16.82MIN: 14.46 / MAX: 17.13MIN: 14.69 / MAX: 16.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 4 - Input: Bosphorus 4KABC0.35260.70521.05781.41041.7631.5491.5661.5671. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18ABC2468108.558.648.59MIN: 8.44 / MAX: 10.5MIN: 8.36 / MAX: 19.47MIN: 8.47 / MAX: 10.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyABC61218243024.2024.1124.00MIN: 22.79 / MAX: 31.02MIN: 22.88 / MAX: 31.49MIN: 22.8 / MAX: 30.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 4 - Input: Bosphorus 1080pABC0.82581.65162.47743.30324.1293.6703.6643.6401. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2ABC1.2332.4663.6994.9326.1655.445.485.46MIN: 5.34 / MAX: 6.85MIN: 5.32 / MAX: 6.92MIN: 5.37 / MAX: 6.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerABC306090120150151.66152.08151.34MIN: 148.67 / MAX: 180.74MIN: 149.28 / MAX: 180.96MIN: 149.5 / MAX: 177.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetABC1.08232.16463.24694.32925.41154.814.794.80MIN: 4.72 / MAX: 6.64MIN: 4.68 / MAX: 6.58MIN: 4.72 / MAX: 6.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v3-v3 - Model: mobilenet-v3ABC1.1162.2323.3484.4645.584.954.964.95MIN: 4.84 / MAX: 6.8MIN: 4.86 / MAX: 6.8MIN: 4.84 / MAX: 6.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Phoronix Test Suite v10.8.4