newa

Intel Core i7-1185G7 testing with a Dell XPS 13 9310 0DXP1F (3.7.0 BIOS) and Intel Xe TGL GT2 8GB on Ubuntu 24.04 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 2408221-NE-NEWA6453334
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
Show Result Confidence Charts

Limit displaying results to tests within:

Creator Workloads 2 Tests
HPC - High Performance Computing 3 Tests
Machine Learning 3 Tests
Multi-Core 2 Tests
Programmer / Developer System Benchmarks 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
Performance Per
Dollar
Date
Run
  Test
  Duration
a
August 21
  5 Hours, 13 Minutes
b
August 21
  5 Hours, 13 Minutes
c
August 22
  5 Hours, 13 Minutes
Invert Hiding All Results Option
  5 Hours, 13 Minutes

Only show results where is faster than
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):


newaOpenBenchmarking.orgPhoronix Test SuiteIntel Core i7-1185G7 @ 4.80GHz (4 Cores / 8 Threads)Dell XPS 13 9310 0DXP1F (3.7.0 BIOS)Intel Tiger Lake-LP8 x 2GB LPDDR4-4267MT/sMicron 2300 NVMe 512GBIntel Xe TGL GT2 8GBRealtek ALC289Intel Wi-Fi 6 AX201Ubuntu 24.046.10.0-061000rc4daily20240621-generic (x86_64)GNOME Shell 46.0X Server + Wayland4.6 Mesa 24.3~git2407210600.0cc23b~oibaf~n (git-0cc23b6 2024-07-21 noble-oibaf-ppa)GCC 13.2.0ext41920x1200ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionNewa BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/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-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: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xb6 - Thermald 2.5.6- Python 3.12.3- gather_data_sampling: Mitigation of Microcode + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: SW sequence; BHI: SW loop KVM: SW loop + srbds: Not affected + tsx_async_abort: Not affected

abcResult OverviewPhoronix Test Suite100%101%101%102%ONNX RuntimeEtcpakBuild2SVT-AV1simdjsonMobile Neural NetworkY-CruncherXNNPACK

newasvt-av1: Preset 3 - Beauty 4K 10-bitsvt-av1: Preset 3 - Bosphorus 4Ksvt-av1: Preset 5 - Beauty 4K 10-bitsvt-av1: Preset 8 - Beauty 4K 10-bitsvt-av1: Preset 3 - Bosphorus 1080pbuild2: Time To Compilesvt-av1: Preset 5 - Bosphorus 4Kxnnpack: QU8MobileNetV3Smallxnnpack: QU8MobileNetV3Largexnnpack: QU8MobileNetV2xnnpack: FP16MobileNetV3Smallxnnpack: FP16MobileNetV3Largexnnpack: FP16MobileNetV2xnnpack: FP32MobileNetV3Smallxnnpack: FP32MobileNetV3Largexnnpack: FP32MobileNetV2svt-av1: Preset 13 - Beauty 4K 10-bitmnn: inception-v3mnn: mobilenet-v1-1.0mnn: MobileNetV2_224mnn: SqueezeNetV1.0mnn: resnet-v2-50mnn: squeezenetv1.1mnn: mobilenetV3mnn: nasnetsvt-av1: Preset 8 - Bosphorus 4Ksvt-av1: Preset 5 - Bosphorus 1080petcpak: Multi-Threaded - ETC2svt-av1: Preset 8 - Bosphorus 1080psimdjson: DistinctUserIDsimdjson: TopTweetsimdjson: PartialTweetsonnx: ResNet101_DUC_HDC-12 - CPU - Parallelonnx: ResNet101_DUC_HDC-12 - CPU - Parallelonnx: ResNet101_DUC_HDC-12 - CPU - Standardonnx: ResNet101_DUC_HDC-12 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Standardonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Parallelsimdjson: Kostyaonnx: bertsquad-12 - CPU - Parallelonnx: bertsquad-12 - CPU - Parallelonnx: ZFNet-512 - CPU - Parallelonnx: ZFNet-512 - CPU - Parallelonnx: yolov4 - CPU - Parallelonnx: yolov4 - CPU - Parallelonnx: T5 Encoder - CPU - Parallelonnx: T5 Encoder - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: GPT-2 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Parallelonnx: bertsquad-12 - CPU - Standardonnx: bertsquad-12 - CPU - Standardonnx: ZFNet-512 - CPU - Standardonnx: ZFNet-512 - CPU - Standardonnx: yolov4 - CPU - Standardonnx: yolov4 - CPU - Standardy-cruncher: 1Bonnx: T5 Encoder - CPU - Standardonnx: T5 Encoder - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - Standardonnx: super-resolution-10 - CPU - Standardsimdjson: LargeRandsvt-av1: Preset 13 - Bosphorus 4Ky-cruncher: 500Msvt-av1: Preset 13 - Bosphorus 1080pabc0.231.4511.1451.6425.364536.8215.9814214923591402417846961068311627584.09836.8674.3073.5925.71620.2043.441.71213.78913.41820.224105.93648.2358.087.687.424649.640.215073495.650.286072022.320.494481393.350.71769512.350980.91093.54256.4633.8991529.52833.8638341.2962.9299711.176489.46189.66051103.421115.9568.62386150.8656.6281718.896952.9115205.2554.871958.0046.87576145.38564.56215.488346.2121.63929.490433.90524.40374226.99310.381196.31353.05091327.68.47108118.01737.120926.937323.041543.39311.2348.6425.727219.8010.231.4521.1441.6345.372538.5815.909814216123611403420346781067309127574.21936.664.3093.555.85520.073.4951.72813.11513.41420.189106.99748.278.17.77.455096.380.1962183305.270.3025472401.330.4164351364.890.73265713.400674.58413.51249.4114.009429.806933.5469342.0392.9236111.177889.44539.59821104.102112.8838.8586150.6126.639318.921652.8429209.5494.7720757.9446.97865143.24165.682615.224149.566120.173828.449835.1464.27347233.8919.9977899.99673.07148325.3878.49614117.67236.66727.270622.94643.57271.2348.425.761219.3780.2291.4551.1461.6375.356539.2245.945806215323531398416446851069309627664.22636.9354.2333.5395.80620.2483.4441.71113.8613.68820.142107.02548.2128.077.687.443756.020.2662393500.580.28566619710.5073551417.720.70535813.118376.19263.48255.4473.9146529.393334.0189363.0192.754659.45416105.749.67918103.236114.0758.76598150.7596.6328618.943252.7814204.7984.8827857.8647.00365142.73565.336515.304747.683220.970530.258933.04444.2768233.7239.67201103.3563.04188328.5778.571116.64336.738227.217823.267142.9721.2249.33425.751219.561OpenBenchmarking.org

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 3 - Input: Beauty 4K 10-bitabc0.05180.10360.15540.20720.2590.2300.2300.2291. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 3 - Input: Bosphorus 4Kabc0.32740.65480.98221.30961.6371.4511.4521.4551. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 5 - Input: Beauty 4K 10-bitabc0.25790.51580.77371.03161.28951.1451.1441.1461. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 8 - Input: Beauty 4K 10-bitabc0.36950.7391.10851.4781.84751.6421.6341.6371. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 3 - Input: Bosphorus 1080pabc1.20872.41743.62614.83486.04355.3645.3725.3561. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Build2

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.17Time To Compileabc120240360480600536.82538.58539.22

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 5 - Input: Bosphorus 4Kabc1.33762.67524.01285.35046.6885.9005.9095.9451. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

XNNPACK

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: QU8MobileNetV3Smallabc20040060080010008148148061. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: QU8MobileNetV3Largeabc50010001500200025002149216121531. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: QU8MobileNetV2abc50010001500200025002359236123531. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: FP16MobileNetV3Smallabc300600900120015001402140313981. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: FP16MobileNetV3Largeabc90018002700360045004178420341641. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: FP16MobileNetV2abc100020003000400050004696467846851. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: FP32MobileNetV3Smallabc20040060080010001068106710691. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: FP32MobileNetV3Largeabc70014002100280035003116309130961. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: FP32MobileNetV2abc60012001800240030002758275727661. (CXX) g++ options: -O3 -lrt -lm

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 13 - Input: Beauty 4K 10-bitabc0.95091.90182.85273.80364.75454.0984.2194.2261. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Mobile Neural Network

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: inception-v3abc81624324036.8736.6636.94MIN: 36.19 / MAX: 64.27MIN: 34.95 / MAX: 59.06MIN: 36.09 / MAX: 57.311. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: mobilenet-v1-1.0abc0.96951.9392.90853.8784.84754.3074.3094.233MIN: 4.12 / MAX: 15.8MIN: 4.11 / MAX: 20.08MIN: 4.09 / MAX: 16.181. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: MobileNetV2_224abc0.80821.61642.42463.23284.0413.5923.5503.539MIN: 3.44 / MAX: 17.94MIN: 3.45 / MAX: 14.62MIN: 3.35 / MAX: 14.31. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: SqueezeNetV1.0abc1.31742.63483.95225.26966.5875.7165.8555.806MIN: 5.38 / MAX: 21.36MIN: 5.39 / MAX: 21.29MIN: 5.53 / MAX: 28.761. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: resnet-v2-50abc51015202520.2020.0720.25MIN: 19.66 / MAX: 37.22MIN: 19.47 / MAX: 37.21MIN: 19.59 / MAX: 38.681. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: squeezenetv1.1abc0.78641.57282.35923.14563.9323.4403.4953.444MIN: 3.29 / MAX: 11.21MIN: 3.28 / MAX: 12.97MIN: 3.25 / MAX: 17.711. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: mobilenetV3abc0.38880.77761.16641.55521.9441.7121.7281.711MIN: 1.67 / MAX: 8.57MIN: 1.69 / MAX: 8.49MIN: 1.63 / MAX: 10.041. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: nasnetabc4812162013.7913.1213.86MIN: 13.38 / MAX: 39.78MIN: 12.49 / MAX: 33.2MIN: 13.38 / MAX: 33.371. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 8 - Input: Bosphorus 4Kabc4812162013.4213.4113.691. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 5 - Input: Bosphorus 1080pabc51015202520.2220.1920.141. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Etcpak

OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 2.0Benchmark: Multi-Threaded - Configuration: ETC2abc20406080100105.94107.00107.031. (CXX) g++ options: -flto -pthread

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 8 - Input: Bosphorus 1080pabc112233445548.2448.2748.211. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

simdjson

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: DistinctUserIDabc2468108.088.108.071. (CXX) g++ options: -O3 -lrt

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: TopTweetabc2468107.687.707.681. (CXX) g++ options: -O3 -lrt

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: PartialTweetsabc2468107.427.457.441. (CXX) g++ options: -O3 -lrt

ONNX Runtime

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Parallelabc110022003300440055004649.645096.383756.021. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Parallelabc0.05990.11980.17970.23960.29950.2150700.1962180.2662391. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standardabc80016002400320040003495.653305.273500.581. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standardabc0.06810.13620.20430.27240.34050.2860700.3025470.2856661. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: fcn-resnet101-11 - Device: CPU - Executor: Parallelabc50010001500200025002022.322401.331971.001. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: fcn-resnet101-11 - Device: CPU - Executor: Parallelabc0.11420.22840.34260.45680.5710.4944800.4164350.5073551. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: fcn-resnet101-11 - Device: CPU - Executor: Standardabc300600900120015001393.351364.891417.721. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: fcn-resnet101-11 - Device: CPU - Executor: Standardabc0.16480.32960.49440.65920.8240.7176950.7326570.7053581. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: GPT-2 - Device: CPU - Executor: Parallelabc369121512.3513.4013.121. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: GPT-2 - Device: CPU - Executor: Parallelabc2040608010080.9174.5876.191. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

simdjson

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: Kostyaabc0.79651.5932.38953.1863.98253.543.513.481. (CXX) g++ options: -O3 -lrt

ONNX Runtime

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: bertsquad-12 - Device: CPU - Executor: Parallelabc60120180240300256.46249.41255.451. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: bertsquad-12 - Device: CPU - Executor: Parallelabc0.90211.80422.70633.60844.51053.899154.009403.914651. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: ZFNet-512 - Device: CPU - Executor: Parallelabc71421283529.5329.8129.391. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ZFNet-512 - Device: CPU - Executor: Parallelabc81624324033.8633.5534.021. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: yolov4 - Device: CPU - Executor: Parallelabc80160240320400341.30342.04363.021. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: yolov4 - Device: CPU - Executor: Parallelabc0.65921.31841.97762.63683.2962.929972.923612.754651. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: T5 Encoder - Device: CPU - Executor: Parallelabc369121511.1764011.177809.454161. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: T5 Encoder - Device: CPU - Executor: Parallelabc2040608010089.4689.45105.741. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: GPT-2 - Device: CPU - Executor: Standardabc36912159.660519.598219.679181. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: GPT-2 - Device: CPU - Executor: Standardabc20406080100103.42104.10103.241. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallelabc306090120150115.96112.88114.081. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallelabc2468108.623868.858608.765981. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: bertsquad-12 - Device: CPU - Executor: Standardabc306090120150150.87150.61150.761. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: bertsquad-12 - Device: CPU - Executor: Standardabc2468106.628176.639306.632861. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: ZFNet-512 - Device: CPU - Executor: Standardabc51015202518.9018.9218.941. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ZFNet-512 - Device: CPU - Executor: Standardabc122436486052.9152.8452.781. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: yolov4 - Device: CPU - Executor: Standardabc50100150200250205.26209.55204.801. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: yolov4 - Device: CPU - Executor: Standardabc1.09862.19723.29584.39445.4934.871904.772074.882781. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

Y-Cruncher

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.5Pi Digits To Calculate: 1Babc132639526558.0057.9457.86

ONNX Runtime

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: T5 Encoder - Device: CPU - Executor: Standardabc2468106.875766.978657.003651. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: T5 Encoder - Device: CPU - Executor: Standardabc306090120150145.39143.24142.741. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: ArcFace ResNet-100 - Device: CPU - Executor: Standardabc153045607564.5665.6865.341. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ArcFace ResNet-100 - Device: CPU - Executor: Standardabc4812162015.4915.2215.301. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallelabc112233445546.2149.5747.681. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallelabc51015202521.6420.1720.971. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standardabc71421283529.4928.4530.261. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standardabc81624324033.9135.1533.041. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallelabc0.99081.98162.97243.96324.9544.403744.273474.276801. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallelabc50100150200250226.99233.89233.721. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallelabc369121510.381109.997789.672011. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallelabc2040608010096.31100.00103.361. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: CaffeNet 12-int8 - Device: CPU - Executor: Standardabc0.69111.38222.07332.76443.45553.050913.071483.041881. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: CaffeNet 12-int8 - Device: CPU - Executor: Standardabc70140210280350327.60325.39328.581. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standardabc2468108.471088.496148.571001. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standardabc306090120150118.02117.67116.641. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: super-resolution-10 - Device: CPU - Executor: Parallelabc91827364537.1236.6736.741. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: super-resolution-10 - Device: CPU - Executor: Parallelabc61218243026.9427.2727.221. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: super-resolution-10 - Device: CPU - Executor: Standardabc61218243023.0422.9523.271. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: super-resolution-10 - Device: CPU - Executor: Standardabc102030405043.3943.5742.971. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

simdjson

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: LargeRandomabc0.27680.55360.83041.10721.3841.231.231.221. (CXX) g++ options: -O3 -lrt

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 13 - Input: Bosphorus 4Kabc112233445548.6448.4049.331. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Y-Cruncher

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.5Pi Digits To Calculate: 500Mabc61218243025.7325.7625.75

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 13 - Input: Bosphorus 1080pabc50100150200250219.80219.38219.561. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

86 Results Shown

SVT-AV1:
  Preset 3 - Beauty 4K 10-bit
  Preset 3 - Bosphorus 4K
  Preset 5 - Beauty 4K 10-bit
  Preset 8 - Beauty 4K 10-bit
  Preset 3 - Bosphorus 1080p
Build2
SVT-AV1
XNNPACK:
  QU8MobileNetV3Small
  QU8MobileNetV3Large
  QU8MobileNetV2
  FP16MobileNetV3Small
  FP16MobileNetV3Large
  FP16MobileNetV2
  FP32MobileNetV3Small
  FP32MobileNetV3Large
  FP32MobileNetV2
SVT-AV1
Mobile Neural Network:
  inception-v3
  mobilenet-v1-1.0
  MobileNetV2_224
  SqueezeNetV1.0
  resnet-v2-50
  squeezenetv1.1
  mobilenetV3
  nasnet
SVT-AV1:
  Preset 8 - Bosphorus 4K
  Preset 5 - Bosphorus 1080p
Etcpak
SVT-AV1
simdjson:
  DistinctUserID
  TopTweet
  PartialTweets
ONNX Runtime:
  ResNet101_DUC_HDC-12 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  ResNet101_DUC_HDC-12 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  fcn-resnet101-11 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  fcn-resnet101-11 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  GPT-2 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
simdjson
ONNX Runtime:
  bertsquad-12 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  ZFNet-512 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  yolov4 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  T5 Encoder - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  GPT-2 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  ArcFace ResNet-100 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  bertsquad-12 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  ZFNet-512 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  yolov4 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
Y-Cruncher
ONNX Runtime:
  T5 Encoder - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  ArcFace ResNet-100 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  Faster R-CNN R-50-FPN-int8 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  Faster R-CNN R-50-FPN-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  CaffeNet 12-int8 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  ResNet50 v1-12-int8 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  CaffeNet 12-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  ResNet50 v1-12-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  super-resolution-10 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  super-resolution-10 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
simdjson
SVT-AV1
Y-Cruncher
SVT-AV1