new satty

AMD Ryzen AI 9 365 testing with a ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 (UM5606WA.308 BIOS) and AMD Radeon 512MB on Ubuntu 24.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2408252-NE-NEWSATTY701&grr.

new sattyProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionabcdAMD Ryzen AI 9 365 @ 4.31GHz (10 Cores / 20 Threads)ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 (UM5606WA.308 BIOS)AMD Device 15074 x 6GB LPDDR5-7500MT/s Micron MT62F1536M32D4DS-0261024GB MTFDKBA1T0QFM-1BD1AABGBAMD Radeon 512MBAMD Rembrandt Radeon HD AudioMEDIATEK Device 7925Ubuntu 24.046.10.0-phx (x86_64)GNOME Shell 46.0X Server + Wayland4.6 Mesa 24.3~git2407280600.a211a5~oibaf~n (git-a211a51 2024-07-28 noble-oibaf-ppa) (LLVM 17.0.6 DRM 3.57)GCC 13.2.0ext42880x1800OpenBenchmarking.orgKernel Details- amdgpu.dcdebugmask=0x600 - Transparent Huge Pages: madviseCompiler Details- --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 Processor Details- Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - Platform Profile: balanced - CPU Microcode: 0xb204011 - ACPI Profile: balanced Python Details- Python 3.12.3Security Details- gather_data_sampling: Not affected + 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; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

new sattysvt-av1: Preset 3 - Beauty 4K 10-bitsvt-av1: Preset 3 - Bosphorus 4Kwhisperfile: Mediumsvt-av1: Preset 5 - Beauty 4K 10-bitsvt-av1: Preset 8 - Beauty 4K 10-bitsvt-av1: Preset 3 - Bosphorus 1080pwhisperfile: Smallsvt-av1: Preset 8 - Bosphorus 4Ksvt-av1: Preset 13 - Beauty 4K 10-bitonnx: ArcFace ResNet-100 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Standardsvt-av1: Preset 5 - Bosphorus 4Konnx: bertsquad-12 - CPU - Parallelonnx: bertsquad-12 - CPU - Parallelsvt-av1: Preset 5 - Bosphorus 1080ponnx: yolov4 - CPU - Standardonnx: yolov4 - CPU - Standardonnx: ZFNet-512 - CPU - Standardonnx: ZFNet-512 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Standardonnx: ResNet101_DUC_HDC-12 - CPU - Standardonnx: ResNet101_DUC_HDC-12 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Standardsimdjson: DistinctUserIDsimdjson: TopTweetsimdjson: PartialTweetsonnx: ResNet101_DUC_HDC-12 - CPU - Parallelonnx: ResNet101_DUC_HDC-12 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Parallelonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Parallelonnx: yolov4 - CPU - Parallelonnx: yolov4 - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: GPT-2 - CPU - Standardonnx: ZFNet-512 - CPU - Parallelonnx: ZFNet-512 - CPU - Parallelonnx: T5 Encoder - CPU - Parallelonnx: T5 Encoder - CPU - Parallelonnx: bertsquad-12 - CPU - Standardonnx: bertsquad-12 - CPU - Standardsimdjson: Kostyaonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Parallelonnx: T5 Encoder - CPU - Standardonnx: T5 Encoder - 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: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - Standardonnx: super-resolution-10 - CPU - Standardsimdjson: LargeRandwhisperfile: Tinysvt-av1: Preset 8 - Bosphorus 1080psvt-av1: Preset 13 - Bosphorus 4Ksvt-av1: Preset 13 - Bosphorus 1080pabcd0.5683.728754.780562.5733.69411.911259.9077730.8266.16443.614822.9274.61373216.66714.781180.9135.5273143.914154.2466.4830310.726693.2061.76819565.2441870.720.534553858.1991.165237.096.888.742146.340.4659071120.310.89260610.316896.8538229.0724.365337.6417130.74823.503342.54188.43551118.516116.2188.604234.5186.338311.58195.99672166.69938.125126.227625.131139.78717.35929135.8513.385374.691814.259770.118312.345480.99211.2552.71359106.46113.827474.7710.5653.491751.48152.5573.60611.437261.7424729.7456.15843.522.98724.49478222.38213.308181.8025.5002941.951160.3746.2352810.932391.44831.76734565.4831874.340.533521865.3121.155576.916.916.742244.40.4455511151.680.86829110.452195.5885240.944.150317.78951128.26323.820241.9768.30904120.311117.878.483684.4284.902911.77775.96555167.56737.79526.456625.365639.41927.1579139.67413.172575.902214.464269.127713.179875.86351.2552.63452100.454109.45455.7850.5733.796722.535192.633.70812.089257.3788431.6366.13542.078523.76364.42207226.0414.881169.55.899544.658144.4066.9247610.946291.33221.74432572.8611900.250.526244819.5571.220096.96.946.592190.940.4564241116.520.89563510.292297.0868229.0584.365597.84183127.42622.323444.7918.45631118.211111.1318.998054.4185.786611.65645.93691168.37138.194426.179925.178839.70866.90258144.82912.934477.300614.503668.93812.664178.95221.2552.49648107.482116.143476.2230.5503.410752.931232.4813.52311.564269.1770029.2586.14350.773019.71275.16479193.66812.942184.5125.4225342.091169.6165.8987812.046983.03271.92558519.4532122.370.471409942.9381.061017.047.026.832379.560.4203351198.570.83442310.590094.3693252.8833.955838.27490120.74123.496942.55688.52036117.354125.5457.967364.4689.508611.17206.07861164.44938.760325.798226.280838.05617.14811139.86513.785272.539515.607664.075113.900871.93721.2454.71240101.169112.326460.254OpenBenchmarking.org

SVT-AV1

Encoder Mode: Preset 3 - Input: Beauty 4K 10-bit

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 3 - Input: Beauty 4K 10-bitabcd0.12890.25780.38670.51560.6445SE +/- 0.004, N = 30.5680.5650.5730.5501. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 3 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 3 - Input: Bosphorus 4Kabcd0.85411.70822.56233.41644.2705SE +/- 0.037, N = 93.7283.4913.7963.4101. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Whisperfile

Model Size: Medium

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisperfile 20Aug24Model Size: Mediumabcd160320480640800SE +/- 2.92, N = 3754.78751.48722.54752.93

SVT-AV1

Encoder Mode: Preset 5 - Input: Beauty 4K 10-bit

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 5 - Input: Beauty 4K 10-bitabcd0.59181.18361.77542.36722.959SE +/- 0.016, N = 32.5732.5572.6302.4811. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 8 - Input: Beauty 4K 10-bit

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 8 - Input: Beauty 4K 10-bitabcd0.83431.66862.50293.33724.1715SE +/- 0.010, N = 33.6943.6063.7083.5231. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 3 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 3 - Input: Bosphorus 1080pabcd3691215SE +/- 0.05, N = 311.9111.4412.0911.561. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Whisperfile

Model Size: Small

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisperfile 20Aug24Model Size: Smallabcd60120180240300SE +/- 3.09, N = 3259.91261.74257.38269.18

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 8 - Input: Bosphorus 4Kabcd714212835SE +/- 0.19, N = 1530.8329.7531.6429.261. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 13 - Input: Beauty 4K 10-bit

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 13 - Input: Beauty 4K 10-bitabcd246810SE +/- 0.006, N = 36.1646.1586.1356.1431. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

ONNX Runtime

Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: ArcFace ResNet-100 - Device: CPU - Executor: Standardabcd1122334455SE +/- 0.41, N = 1543.6143.5042.0850.771. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ArcFace ResNet-100 - Device: CPU - Executor: Standardabcd612182430SE +/- 0.16, N = 1522.9322.9923.7619.711. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standardabcd1.16212.32423.48634.64845.8105SE +/- 0.03387, N = 154.613734.494784.422075.164791. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standardabcd50100150200250SE +/- 1.31, N = 15216.67222.38226.04193.671. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

SVT-AV1

Encoder Mode: Preset 5 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 5 - Input: Bosphorus 4Kabcd48121620SE +/- 0.15, N = 314.7813.3114.8812.941. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

ONNX Runtime

Model: bertsquad-12 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: bertsquad-12 - Device: CPU - Executor: Parallelabcd4080120160200SE +/- 1.19, N = 14180.91181.80169.50184.511. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: bertsquad-12 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: bertsquad-12 - Device: CPU - Executor: Parallelabcd1.32742.65483.98225.30966.637SE +/- 0.03573, N = 145.527315.500295.899505.422531. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

SVT-AV1

Encoder Mode: Preset 5 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 5 - Input: Bosphorus 1080pabcd1020304050SE +/- 0.37, N = 843.9141.9544.6642.091. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

ONNX Runtime

Model: yolov4 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: yolov4 - Device: CPU - Executor: Standardabcd4080120160200SE +/- 1.19, N = 12154.25160.37144.41169.621. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: yolov4 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: yolov4 - Device: CPU - Executor: Standardabcd246810SE +/- 0.04221, N = 126.483036.235286.924765.898781. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: ZFNet-512 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: ZFNet-512 - Device: CPU - Executor: Standardabcd3691215SE +/- 0.08, N = 1210.7310.9310.9512.051. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: ZFNet-512 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ZFNet-512 - Device: CPU - Executor: Standardabcd20406080100SE +/- 0.57, N = 1293.2191.4591.3383.031. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: CaffeNet 12-int8 - Device: CPU - Executor: Standardabcd0.43330.86661.29991.73322.1665SE +/- 0.01672, N = 121.768191.767341.744321.925581. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: CaffeNet 12-int8 - Device: CPU - Executor: Standardabcd120240360480600SE +/- 4.51, N = 12565.24565.48572.86519.451. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standardabcd5001000150020002500SE +/- 15.92, N = 101870.721874.341900.252122.371. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standardabcd0.12030.24060.36090.48120.6015SE +/- 0.003579, N = 100.5345530.5335210.5262440.4714091. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: fcn-resnet101-11 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: fcn-resnet101-11 - Device: CPU - Executor: Standardabcd2004006008001000SE +/- 9.14, N = 6858.20865.31819.56942.941. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: fcn-resnet101-11 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: fcn-resnet101-11 - Device: CPU - Executor: Standardabcd0.27450.5490.82351.0981.3725SE +/- 0.01056, N = 61.165231.155571.220091.061011. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

simdjson

Throughput Test: DistinctUserID

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: DistinctUserIDabcd246810SE +/- 0.08, N = 37.096.916.907.041. (CXX) g++ options: -O3 -lrt

simdjson

Throughput Test: TopTweet

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: TopTweetabcd246810SE +/- 0.02, N = 36.886.916.947.021. (CXX) g++ options: -O3 -lrt

simdjson

Throughput Test: PartialTweets

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: PartialTweetsabcd246810SE +/- 0.02, N = 38.746.746.596.831. (CXX) g++ options: -O3 -lrt

ONNX Runtime

Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Parallelabcd5001000150020002500SE +/- 24.44, N = 32146.342244.402190.942379.561. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Parallelabcd0.10480.20960.31440.41920.524SE +/- 0.004361, N = 30.4659070.4455510.4564240.4203351. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: fcn-resnet101-11 - Device: CPU - Executor: Parallelabcd30060090012001500SE +/- 9.16, N = 31120.311151.681116.521198.571. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: fcn-resnet101-11 - Device: CPU - Executor: Parallelabcd0.20150.4030.60450.8061.0075SE +/- 0.006409, N = 30.8926060.8682910.8956350.8344231. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: GPT-2 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: GPT-2 - Device: CPU - Executor: Parallelabcd3691215SE +/- 0.10, N = 310.3210.4510.2910.591. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: GPT-2 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: GPT-2 - Device: CPU - Executor: Parallelabcd20406080100SE +/- 0.87, N = 396.8595.5997.0994.371. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: yolov4 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: yolov4 - Device: CPU - Executor: Parallelabcd60120180240300SE +/- 3.53, N = 3229.07240.94229.06252.881. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: yolov4 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: yolov4 - Device: CPU - Executor: Parallelabcd0.98231.96462.94693.92924.9115SE +/- 0.05493, N = 34.365334.150314.365593.955831. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: GPT-2 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: GPT-2 - Device: CPU - Executor: Standardabcd246810SE +/- 0.02926, N = 37.641707.789517.841838.274901. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: GPT-2 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: GPT-2 - Device: CPU - Executor: Standardabcd306090120150SE +/- 0.43, N = 3130.75128.26127.43120.741. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: ZFNet-512 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: ZFNet-512 - Device: CPU - Executor: Parallelabcd612182430SE +/- 0.15, N = 323.5023.8222.3223.501. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: ZFNet-512 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ZFNet-512 - Device: CPU - Executor: Parallelabcd1020304050SE +/- 0.27, N = 342.5441.9844.7942.561. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: T5 Encoder - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: T5 Encoder - Device: CPU - Executor: Parallelabcd246810SE +/- 0.08432, N = 38.435518.309048.456318.520361. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: T5 Encoder - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: T5 Encoder - Device: CPU - Executor: Parallelabcd306090120150SE +/- 1.16, N = 3118.52120.31118.21117.351. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: bertsquad-12 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: bertsquad-12 - Device: CPU - Executor: Standardabcd306090120150SE +/- 1.55, N = 3116.22117.87111.13125.551. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: bertsquad-12 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: bertsquad-12 - Device: CPU - Executor: Standardabcd3691215SE +/- 0.09828, N = 38.604238.483688.998057.967361. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

simdjson

Throughput Test: Kostya

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: Kostyaabcd1.01482.02963.04444.05925.074SE +/- 0.02, N = 34.514.424.414.461. (CXX) g++ options: -O3 -lrt

ONNX Runtime

Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallelabcd20406080100SE +/- 0.32, N = 386.3484.9085.7989.511. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallelabcd3691215SE +/- 0.04, N = 311.5811.7811.6611.171. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: T5 Encoder - Device: CPU - Executor: Standard

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: T5 Encoder - Device: CPU - Executor: Standardabcd246810SE +/- 0.02319, N = 35.996725.965555.936916.078611. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: T5 Encoder - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: T5 Encoder - Device: CPU - Executor: Standardabcd4080120160200SE +/- 0.63, N = 3166.70167.57168.37164.451. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallelabcd918273645SE +/- 0.13, N = 338.1337.8038.1938.761. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallelabcd612182430SE +/- 0.09, N = 326.2326.4626.1825.801. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standardabcd612182430SE +/- 0.31, N = 325.1325.3725.1826.281. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standardabcd918273645SE +/- 0.45, N = 339.7939.4239.7138.061. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallelabcd246810SE +/- 0.04235, N = 37.359297.157906.902587.148111. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallelabcd306090120150SE +/- 0.82, N = 3135.85139.67144.83139.871. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallelabcd48121620SE +/- 0.12, N = 313.3913.1712.9313.791. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallelabcd20406080100SE +/- 0.61, N = 374.6975.9077.3072.541. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: super-resolution-10 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: super-resolution-10 - Device: CPU - Executor: Parallelabcd48121620SE +/- 0.16, N = 314.2614.4614.5015.611. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: super-resolution-10 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: super-resolution-10 - Device: CPU - Executor: Parallelabcd1632486480SE +/- 0.67, N = 370.1269.1368.9464.081. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: super-resolution-10 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.19Model: super-resolution-10 - Device: CPU - Executor: Standardabcd48121620SE +/- 0.11, N = 312.3513.1812.6613.901. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: super-resolution-10 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: super-resolution-10 - Device: CPU - Executor: Standardabcd20406080100SE +/- 0.54, N = 380.9975.8678.9571.941. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

simdjson

Throughput Test: LargeRandom

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: LargeRandomabcd0.28130.56260.84391.12521.4065SE +/- 0.00, N = 31.251.251.251.241. (CXX) g++ options: -O3 -lrt

Whisperfile

Model Size: Tiny

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisperfile 20Aug24Model Size: Tinyabcd1224364860SE +/- 0.38, N = 352.7152.6352.5054.71

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 8 - Input: Bosphorus 1080pabcd20406080100SE +/- 0.41, N = 3106.46100.45107.48101.171. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 13 - Input: Bosphorus 4Kabcd306090120150SE +/- 0.95, N = 3113.83109.45116.14112.331. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 13 - Input: Bosphorus 1080pabcd100200300400500SE +/- 3.20, N = 3474.77455.79476.22460.251. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq


Phoronix Test Suite v10.8.5