AMD AOCC 4.0 Benchmarks

AMD Ryzen 9 7950X compiler benchmarks by Michael Larabel for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2211152-PTS-AMDAOCC460&rdt&gru.

AMD AOCC 4.0 BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2AMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR X670E HERO (0703 BIOS)AMD Device 14d832GB1000GB Sabrent Rocket 4.0 PlusAMD Radeon RX 6800 16GB (2475/1000MHz)AMD Navi 21/23ASUS MG28UIntel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Ubuntu 22.106.1.0-060100rc3daily20221103-generic (x86_64)GNOME Shell 43.0X Server + Wayland4.6 Mesa 22.2.1 (LLVM 15.0.2 DRM 3.49)1.3.224Clang 14.0.6ext43840x2160Clang 14.0.6-2GCC 12.2.0GCC 13.0.0 20221114 + clang (GCC) 13.0.0 20221114 (experimental)Clang 15.0.2-1OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseEnvironment Details- CXXFLAGS="-O3 -march=native -flto" CFLAGS="-O3 -march=native -flto"Compiler Details- AOCC 4.0: Optimized build with assertions; Default target: x86_64-unknown-linux-gnu; Host CPU: znver4- GCC 12.2: --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-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-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/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 - GCC 13.0 14 Nov: --disable-multilibProcessor Details- Scaling Governor: amd-pstate schedutil (Boost: Enabled) - CPU Microcode: 0xa601203Graphics Details- BAR1 / Visible vRAM Size: 16368 MB - vBIOS Version: 113-D4120900-101Python Details- Python 3.10.7Security Details- 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

AMD AOCC 4.0 Benchmarksopenssl: SHA256quadray: 1 - 4Kquadray: 5 - 4Kquadray: 1 - 1080pquadray: 5 - 1080popenvino: Face Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUyquake2: Software CPU - On - On - 1920 x 1080yquake2: Software CPU - Off - On - 1920 x 1080yquake2: Software CPU - On - Off - 1920 x 1080yquake2: Software CPU - Off - Off - 1920 x 1080yquake2: Software CPU Color Light - On - On - 1920 x 1080yquake2: Software CPU Color Light - Off - On - 1920 x 1080yquake2: Software CPU Color Light - On - Off - 1920 x 1080yquake2: Software CPU Color Light - Off - Off - 1920 x 1080aom-av1: Speed 6 Two-Pass - Bosphorus 4Kaom-av1: Speed 10 Realtime - Bosphorus 4Kkvazaar: Bosphorus 4K - Very Fastkvazaar: Bosphorus 4K - Ultra Fastkvazaar: Bosphorus 1080p - Very Fastkvazaar: Bosphorus 1080p - Ultra Fastsvt-av1: Preset 4 - Bosphorus 4Ksvt-av1: Preset 8 - Bosphorus 4Ksvt-av1: Preset 10 - Bosphorus 4Ksvt-av1: Preset 12 - Bosphorus 4Ksvt-hevc: 1 - Bosphorus 4Ksvt-hevc: 7 - Bosphorus 4Ksvt-hevc: 10 - Bosphorus 4Ksvt-vp9: VMAF Optimized - Bosphorus 4Ksvt-vp9: PSNR/SSIM Optimized - Bosphorus 4Ksvt-vp9: Visual Quality Optimized - Bosphorus 4Ksimdjson: Kostyasimdjson: TopTweetsimdjson: LargeRandsimdjson: PartialTweetssimdjson: DistinctUserIDonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: yolov4 - CPU - Parallelonnx: yolov4 - CPU - Standardonnx: bertsquad-12 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Standardonnx: super-resolution-10 - CPU - Parallelgraphics-magick: Swirlgraphics-magick: Rotategraphics-magick: Sharpengraphics-magick: Enhancedgraphics-magick: Resizinggraphics-magick: Noise-Gaussiangraphics-magick: HWB Color Spacecoremark: CoreMark Size 666 - Iterations Per Secondxsbench: securemark: SecureMark-TLSblosc: blosclz shuffleblosc: blosclz bitshufflecompress-zstd: 3 - Compression Speedcompress-zstd: 3 - Decompression Speedcompress-zstd: 19 - Compression Speedcompress-zstd: 19 - Decompression Speedcompress-zstd: 19, Long Mode - Compression Speedcompress-zstd: 19, Long Mode - Decompression Speednettle: aes256nettle: chachanettle: sha512nettle: poly1305-aestjbench: Decompression Throughputsockperf: Throughputquantlib: cryptopp: Keyed Algorithmscryptopp: Unkeyed Algorithmsjpegxl: PNG - 90jpegxl: JPEG - 90jpegxl: PNG - 100jpegxl: JPEG - 100jpegxl-decode: 1jpegxl-decode: Allwebp: Defaultwebp: Quality 100webp: Quality 100, Losslesswebp: Quality 100, Highest Compressionwebp: Quality 100, Lossless, Highest Compressionastcenc: Fastastcenc: Mediumastcenc: Thoroughastcenc: Exhaustivelczero: BLASlczero: Eigentscp: AI Chess Performancelammps: Rhodopsin Proteindragonflydb: 50 - 1:5dragonflydb: 50 - 5:1redis: SET - 50pjsip: INVITEpjsip: OPTIONS, Statefulpjsip: OPTIONS, Statelessliquid-dsp: 8 - 256 - 57liquid-dsp: 16 - 256 - 57liquid-dsp: 32 - 256 - 57openssl: RSA4096clomp: Static OMP Speedupkripke: openssl: RSA4096caffe: AlexNet - CPU - 100caffe: GoogleNet - CPU - 100onednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: IP Shapes 1D - bf16bf16bf16 - CPUonednn: IP Shapes 3D - bf16bf16bf16 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPUopenjpeg: NASA Curiosity Panorama M34draco: Liondraco: Church Facadencnn: 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_400mtnn: CPU - DenseNettnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v2tnn: CPU - SqueezeNet v1.1openvino: Face Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUdolfyn: Computational Fluid Dynamicsmocassin: Dust 2D tau100.0avifenc: 0avifenc: 2avifenc: 6avifenc: 6, Losslessavifenc: 10, Losslessc-ray: Total Time - 4K, 16 Rays Per Pixelpovray: Trace Timeprimesieve: 1e12aobench: 2048 x 2048 - Total Timeencode-flac: WAV To FLACencode-mp3: WAV To MP3espeak: Text-To-Speech Synthesisngspice: C2670ngspice: C7552tachyon: Total Timecpp-perf-bench: Atolcpp-perf-bench: Ctypecpp-perf-bench: Math Librarycpp-perf-bench: Stepanov Vectorcpp-perf-bench: Function Objectscpp-perf-bench: Stepanov Abstractionsqlite-speedtest: Timed Time - Size 1,000toktx: UASTC 3toktx: Zstd Compression 19AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.24042616378726.432.05102.798.1214.297.537.37752.2728.191847.731439.92133.332896.901664.7744290.7363880.92196.3205.6198.1205.7185.3189.9188.2191.820.7565.4447.3385.35113.72219.333.07876.511131.294188.4006.68108.32171.09112.44121.78111.785.8510.851.5911.8211.9771359147569576917135235622079113141395247061226096071710946032.288205708134647594123837.213508.95092.25461.279.15018.654.65117.88564.641528.82864.294255.91318.2872498790954532.31048.647843591.18363413.5013.131.080.8577.27286.4429.6517.672.176.330.89427.3331160.959919.90602.016017481945247706317.9105728724.375242954.594701871.553449370124523896243333175483333318866000006026.225.0125045767394139.127653739340.3385810.3470170.5778341.500165.287850.4050971138.833.273671.38455574.0081139.44574.9050.1331690.22237873991337343248.573.172.692.962.723.851.217.8524.837.184.7911.6214.3811.277.552455.642244.04544.592217.835557.011055.291081.0110.62283.074.325.5559.955.524.800.360.2510.7676463.11431.3782.9434.2292.77327.45316.1026.24521.5799.9284.73214.53558.25556.31255.486725.51931.359164.79939.3809.02316.93234.7744.95711.3463994881885726.232.04101.898.0714.377.467.29752.4128.151851.091434.10133.592887.981654.6644085.2563331.0417.7664.8244.6282.97107.85210.453.02074.608130.107183.1916.64105.55170.79111.35120.82110.255.6210.601.5611.1510.7770628980563566923135235327818949138289646658227055871580981244.486204675600147262424796.813989.25045.25463.578.94913.254.65055.88566.171536.84864.874231.63320.1623448837564669.51086.846641593.20981413.1913.101.070.9462.29264.4829.4517.512.066.160.83404.4496155.089519.27961.981417021861294257917.688809823333158406666717236000006016.623.7109794900395258.1469761049420.3435950.3377600.5833771.511765.319300.4084321138.263.395811.40766575.6021142.95575.9420.1363430.22410164416376347829.093.442.993.253.024.251.378.5425.967.365.1912.3214.6811.809.413634.328431.56261.105302.022555.001066.071092.8710.62283.724.325.5759.835.544.830.360.2510.7716565.22832.3783.0794.3772.76120.13416.5686.17221.7049.2804.62020.54357.71156.21654.972925.46231.627164.38540.1799.24617.03036.0724.98211.6393686423280026.482.08102.318.2214.297.507.34757.5128.091837.191429.51134.422879.681658.3044470.5963460.60185.1192.0185.9192.2171.2176.2172.5176.419.3268.2441.7880.31102.77204.743.06776.398131.043187.3726.64106.57172.53109.95122.32111.605.899.901.839.859.80712689405685649181342361222293951473988343639274166415331066150.945207623450843281023526.413017.34978.65432.180.34932.054.64974.48521.411515.12858.304182.31314.7590718891034501.1881.352348481.75523412.9812.541.040.8568.44263.9028.0216.612.234.480.88289.2890132.587619.45492.007116971725249682117.2645707956.745275879.834498344.3552799330125825834506667162723333316806000006014.622.8133327173393865.823685657420.4799060.3565460.7259781.543795.327800.4214191140.343.364121.38696580.3301139.55578.8220.1398620.22851471222348644248.683.713.243.763.304.641.598.6624.567.494.9912.2514.0312.4312.014513.705412.94469.923388.439557.361060.871085.3310.55284.354.355.5959.475.554.820.360.2510.7876468.52334.8453.2025.0283.07718.99415.9556.18719.76210.5204.40917.83263.74658.28255.483325.42732.277166.57535.1969.25115.72734.2254.95811.6853738534308326.301.93102.067.65191.4199.0192.3201.0181.3184.4178.5185.320.7268.3044.1282.56108.11210.393.10976.360132.746188.6166.63107.16173.36110.49122.36111.616.0310.221.809.639.281454912341627262565814381117817.247150631826243289624105.013286.54976.25485.882.24988.954.35073.88490.461507.34859.964188.14322.49125190031013.0112.761.030.8566.30245.5428.1816.802.284.600.89294.5724135.191319.77252.0276249222817.0445757620.865271140.494675697.053389389124028650876667127443333316331666676029.122.6132057600394339.823696649870.5242830.3564070.6629051.533055.305010.4188601139.643.426861.40503582.0031142.22578.9550.1403490.227918696088.683.723.263.743.324.571.588.6524.397.494.9812.2614.1212.2711.8410.5106366.26633.7513.1054.6752.94719.32619.90210.8104.38717.76962.67660.29455.280925.54533.773169.47935.5089.21115.73234.7344.96111.6163791626787026.151.92102.347.6014.357.477.43742.4428.271845.311438.37135.002895.021645.5744075.7563386.5717.9268.7145.3184.80109.33213.393.05874.817129.155184.1506.63105.69171.02110.81121.26111.241390876454583265558315841004815.006942675223845495724197.713694.25030.85458.678.84894.655.34928.98553.151523.44863.734214.74321.2164558976614783.91075.790605596.86578317.9817.461.110.8763.32266.8929.2317.002.156.210.90412.2096156.453219.43011.988616861863285702217.385566352750154426666716549333336030.923.6108977267395636.4468001074140.3437490.3622850.5823811.513695.303370.4085941137.493.464441.39579575.1251142.00576.2190.1363100.22444962689370046499.243.532.993.313.074.351.418.6325.527.415.1612.3214.9411.979.622499.824337.48149.433232.435555.051065.311071.5010.76282.594.335.5659.205.524.850.360.2510.8226465.15032.3123.0444.3632.72520.15314.8346.24321.3939.4354.52958.95556.47755.083626.05631.784165.54640.2849.33317.18336.0174.98311.457OpenBenchmarking.org

OpenSSL

Algorithm: SHA256

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.0Algorithm: SHA256AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.29000M18000M27000M36000M45000MSE +/- 138604481.51, N = 3SE +/- 97264370.12, N = 3SE +/- 115194474.21, N = 3SE +/- 51284060.91, N = 3SE +/- 115974592.12, N = 34042616378739948818857368642328003738534308337916267870-Qunused-arguments-Qunused-arguments-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=native -flto -lssl -lcrypto -ldl

QuadRay

Scene: 1 - Resolution: 4K

OpenBenchmarking.orgFPS, More Is BetterQuadRay 2022.05.25Scene: 1 - Resolution: 4KAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2612182430SE +/- 0.12, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 326.4326.2326.4826.3026.151. (CXX) g++ options: -O3 -pthread -lm -lstdc++ -lX11 -lXext -lpthread

QuadRay

Scene: 5 - Resolution: 4K

OpenBenchmarking.orgFPS, More Is BetterQuadRay 2022.05.25Scene: 5 - Resolution: 4KAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.4680.9361.4041.8722.34SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.052.042.081.931.921. (CXX) g++ options: -O3 -pthread -lm -lstdc++ -lX11 -lXext -lpthread

QuadRay

Scene: 1 - Resolution: 1080p

OpenBenchmarking.orgFPS, More Is BetterQuadRay 2022.05.25Scene: 1 - Resolution: 1080pAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.220406080100SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.20, N = 3SE +/- 0.11, N = 3102.79101.89102.31102.06102.341. (CXX) g++ options: -O3 -pthread -lm -lstdc++ -lX11 -lXext -lpthread

QuadRay

Scene: 5 - Resolution: 1080p

OpenBenchmarking.orgFPS, More Is BetterQuadRay 2022.05.25Scene: 5 - Resolution: 1080pAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2246810SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 38.128.078.227.657.601. (CXX) g++ options: -O3 -pthread -lm -lstdc++ -lX11 -lXext -lpthread

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Face Detection FP16 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.248121620SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 314.2914.3714.2914.35-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Detection FP16 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.2246810SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 37.537.467.507.47-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Detection FP32 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.2246810SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 37.377.297.347.43-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.2160320480640800SE +/- 6.50, N = 3SE +/- 4.19, N = 3SE +/- 1.28, N = 3SE +/- 2.68, N = 3752.27752.41757.51742.44-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Face Detection FP16-INT8 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.2714212835SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.02, N = 3SE +/- 0.11, N = 328.1928.1528.0928.27-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.2400800120016002000SE +/- 1.21, N = 3SE +/- 1.75, N = 3SE +/- 0.70, N = 3SE +/- 4.72, N = 31847.731851.091837.191845.31-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.230060090012001500SE +/- 0.72, N = 3SE +/- 1.62, N = 3SE +/- 1.86, N = 3SE +/- 0.50, N = 31439.921434.101429.511438.37-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Machine Translation EN To DE FP16 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.2306090120150SE +/- 0.90, N = 3SE +/- 0.76, N = 3SE +/- 1.44, N = 3SE +/- 0.62, N = 3133.33133.59134.42135.00-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.26001200180024003000SE +/- 0.61, N = 3SE +/- 0.54, N = 3SE +/- 2.62, N = 3SE +/- 1.94, N = 32896.902887.982879.682895.02-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.2400800120016002000SE +/- 6.39, N = 3SE +/- 4.79, N = 3SE +/- 6.49, N = 3SE +/- 17.91, N = 41664.771654.661658.301645.57-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.210K20K30K40K50KSE +/- 34.34, N = 3SE +/- 43.19, N = 3SE +/- 46.50, N = 3SE +/- 16.19, N = 344290.7344085.2544470.5944075.75-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.214K28K42K56K70KSE +/- 68.00, N = 3SE +/- 21.27, N = 3SE +/- 73.58, N = 3SE +/- 31.56, N = 363880.9263331.0463460.6063386.57-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

yquake2

Renderer: Software CPU - AF: On - MSAA: On - Resolution: 1920 x 1080

OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 8.10Renderer: Software CPU - AF: On - MSAA: On - Resolution: 1920 x 1080AOCC 4.0GCC 12.2GCC 13.0 14 Nov4080120160200SE +/- 0.15, N = 3SE +/- 0.91, N = 3SE +/- 0.43, N = 3196.3185.1191.41. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O3 -march=native -flto -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC

yquake2

Renderer: Software CPU - AF: Off - MSAA: On - Resolution: 1920 x 1080

OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 8.10Renderer: Software CPU - AF: Off - MSAA: On - Resolution: 1920 x 1080AOCC 4.0GCC 12.2GCC 13.0 14 Nov50100150200250SE +/- 1.56, N = 3SE +/- 0.15, N = 3SE +/- 0.64, N = 3205.6192.0199.01. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O3 -march=native -flto -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC

yquake2

Renderer: Software CPU - AF: On - MSAA: Off - Resolution: 1920 x 1080

OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 8.10Renderer: Software CPU - AF: On - MSAA: Off - Resolution: 1920 x 1080AOCC 4.0GCC 12.2GCC 13.0 14 Nov4080120160200SE +/- 2.06, N = 3SE +/- 1.68, N = 3SE +/- 0.30, N = 3198.1185.9192.31. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O3 -march=native -flto -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC

yquake2

Renderer: Software CPU - AF: Off - MSAA: Off - Resolution: 1920 x 1080

OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 8.10Renderer: Software CPU - AF: Off - MSAA: Off - Resolution: 1920 x 1080AOCC 4.0GCC 12.2GCC 13.0 14 Nov50100150200250SE +/- 1.48, N = 3SE +/- 0.24, N = 3SE +/- 0.63, N = 3205.7192.2201.01. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O3 -march=native -flto -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC

yquake2

Renderer: Software CPU Color Light - AF: On - MSAA: On - Resolution: 1920 x 1080

OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 8.10Renderer: Software CPU Color Light - AF: On - MSAA: On - Resolution: 1920 x 1080AOCC 4.0GCC 12.2GCC 13.0 14 Nov4080120160200SE +/- 0.68, N = 3SE +/- 0.93, N = 3SE +/- 0.33, N = 3185.3171.2181.31. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O3 -march=native -flto -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC

yquake2

Renderer: Software CPU Color Light - AF: Off - MSAA: On - Resolution: 1920 x 1080

OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 8.10Renderer: Software CPU Color Light - AF: Off - MSAA: On - Resolution: 1920 x 1080AOCC 4.0GCC 12.2GCC 13.0 14 Nov4080120160200SE +/- 0.54, N = 3SE +/- 0.37, N = 3SE +/- 0.78, N = 3189.9176.2184.41. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O3 -march=native -flto -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC

yquake2

Renderer: Software CPU Color Light - AF: On - MSAA: Off - Resolution: 1920 x 1080

OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 8.10Renderer: Software CPU Color Light - AF: On - MSAA: Off - Resolution: 1920 x 1080AOCC 4.0GCC 12.2GCC 13.0 14 Nov4080120160200SE +/- 1.77, N = 3SE +/- 0.26, N = 3SE +/- 0.50, N = 3188.2172.5178.51. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O3 -march=native -flto -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC

yquake2

Renderer: Software CPU Color Light - AF: Off - MSAA: Off - Resolution: 1920 x 1080

OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 8.10Renderer: Software CPU Color Light - AF: Off - MSAA: Off - Resolution: 1920 x 1080AOCC 4.0GCC 12.2GCC 13.0 14 Nov4080120160200SE +/- 2.19, N = 4SE +/- 0.52, N = 3SE +/- 0.95, N = 3191.8176.4185.31. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O3 -march=native -flto -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC

AOM AV1

Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4KAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2510152025SE +/- 0.11, N = 3SE +/- 0.11, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 320.7517.7619.3220.7217.921. (CXX) g++ options: -O3 -march=native -flto -std=c++11 -U_FORTIFY_SOURCE -lm

AOM AV1

Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4KAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.21530456075SE +/- 0.19, N = 3SE +/- 0.19, N = 3SE +/- 0.03, N = 3SE +/- 0.12, N = 3SE +/- 0.21, N = 365.4464.8268.2468.3068.711. (CXX) g++ options: -O3 -march=native -flto -std=c++11 -U_FORTIFY_SOURCE -lm

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Very Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: Very FastAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.21122334455SE +/- 0.42, N = 3SE +/- 0.17, N = 3SE +/- 0.42, N = 3SE +/- 0.61, N = 3SE +/- 0.22, N = 347.3344.6241.7844.1245.31-lpthread-lpthread1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -flto -lm -lrt

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Ultra Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: Ultra FastAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.220406080100SE +/- 0.03, N = 3SE +/- 0.28, N = 3SE +/- 0.29, N = 3SE +/- 0.22, N = 3SE +/- 0.30, N = 385.3582.9780.3182.5684.80-lpthread-lpthread1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -flto -lm -lrt

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Very Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 1080p - Video Preset: Very FastAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2306090120150SE +/- 0.04, N = 3SE +/- 0.13, N = 3SE +/- 0.39, N = 3SE +/- 0.32, N = 3SE +/- 0.27, N = 3113.72107.85102.77108.11109.33-lpthread-lpthread1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -flto -lm -lrt

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Ultra Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 1080p - Video Preset: Ultra FastAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.250100150200250SE +/- 0.25, N = 3SE +/- 1.14, N = 3SE +/- 0.80, N = 3SE +/- 0.51, N = 3SE +/- 0.89, N = 3219.33210.45204.74210.39213.39-lpthread-lpthread1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -flto -lm -lrt

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 4 - Input: Bosphorus 4KAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.69951.3992.09852.7983.4975SE +/- 0.006, N = 3SE +/- 0.008, N = 3SE +/- 0.008, N = 3SE +/- 0.012, N = 3SE +/- 0.012, N = 33.0783.0203.0673.1093.0581. (CXX) g++ options: -O3 -march=native -flto -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 4KAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.220406080100SE +/- 0.54, N = 3SE +/- 0.17, N = 3SE +/- 0.25, N = 3SE +/- 0.70, N = 3SE +/- 0.42, N = 376.5174.6176.4076.3674.821. (CXX) g++ options: -O3 -march=native -flto -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 10 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 10 - Input: Bosphorus 4KAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2306090120150SE +/- 0.71, N = 3SE +/- 0.71, N = 3SE +/- 1.43, N = 3SE +/- 1.28, N = 3SE +/- 1.02, N = 3131.29130.11131.04132.75129.161. (CXX) g++ options: -O3 -march=native -flto -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 4KAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.24080120160200SE +/- 0.95, N = 3SE +/- 0.91, N = 3SE +/- 0.19, N = 3SE +/- 0.64, N = 3SE +/- 0.49, N = 3188.40183.19187.37188.62184.151. (CXX) g++ options: -O3 -march=native -flto -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-HEVC

Tuning: 1 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 4KAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2246810SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 36.686.646.646.636.631. (CC) gcc options: -O3 -march=native -flto -fPIE -fPIC -O2 -pie -rdynamic -lpthread -lrt

SVT-HEVC

Tuning: 7 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 4KAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.220406080100SE +/- 0.09, N = 3SE +/- 0.35, N = 3SE +/- 0.16, N = 3SE +/- 0.19, N = 3SE +/- 0.07, N = 3108.32105.55106.57107.16105.691. (CC) gcc options: -O3 -march=native -flto -fPIE -fPIC -O2 -pie -rdynamic -lpthread -lrt

SVT-HEVC

Tuning: 10 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 4KAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.24080120160200SE +/- 0.26, N = 3SE +/- 0.19, N = 3SE +/- 0.31, N = 3SE +/- 0.18, N = 3SE +/- 0.29, N = 3171.09170.79172.53173.36171.021. (CC) gcc options: -O3 -march=native -flto -fPIE -fPIC -O2 -pie -rdynamic -lpthread -lrt

SVT-VP9

Tuning: VMAF Optimized - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 4KAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2306090120150SE +/- 1.06, N = 15SE +/- 1.13, N = 15SE +/- 1.87, N = 15SE +/- 1.85, N = 15SE +/- 1.81, N = 15112.44111.35109.95110.49110.811. (CC) gcc options: -O3 -fcommon -march=native -flto -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

SVT-VP9

Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4KAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2306090120150SE +/- 0.09, N = 3SE +/- 0.15, N = 3SE +/- 0.11, N = 3SE +/- 0.13, N = 3SE +/- 0.22, N = 3121.78120.82122.32122.36121.261. (CC) gcc options: -O3 -fcommon -march=native -flto -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

SVT-VP9

Tuning: Visual Quality Optimized - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 4KAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2306090120150SE +/- 0.03, N = 3SE +/- 0.26, N = 3SE +/- 0.07, N = 3SE +/- 0.23, N = 3SE +/- 0.17, N = 3111.78110.25111.60111.61111.241. (CC) gcc options: -O3 -fcommon -march=native -flto -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

simdjson

Throughput Test: Kostya

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: KostyaAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 Nov246810SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 35.855.625.896.031. (CXX) g++ options: -O3 -march=native -flto

simdjson

Throughput Test: TopTweet

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: TopTweetAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 Nov3691215SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 310.8510.609.9010.221. (CXX) g++ options: -O3 -march=native -flto

simdjson

Throughput Test: LargeRandom

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: LargeRandomAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 Nov0.41180.82361.23541.64722.059SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.591.561.831.801. (CXX) g++ options: -O3 -march=native -flto

simdjson

Throughput Test: PartialTweets

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: PartialTweetsAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 Nov3691215SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 311.8211.159.859.631. (CXX) g++ options: -O3 -march=native -flto

simdjson

Throughput Test: DistinctUserID

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: DistinctUserIDAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 Nov3691215SE +/- 0.10, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 311.9710.779.809.281. (CXX) g++ options: -O3 -march=native -flto

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: ParallelAOCC 4.0LLVM Clang 14GCC 12.215003000450060007500SE +/- 19.11, N = 3SE +/- 21.71, N = 3SE +/- 34.87, N = 3713570627126-flto=thin-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native -flto -ffunction-sections -fdata-sections -mtune=native -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: StandardAOCC 4.0LLVM Clang 14GCC 12.22K4K6K8K10KSE +/- 98.49, N = 5SE +/- 123.19, N = 3SE +/- 107.39, N = 12914789808940-flto=thin-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native -flto -ffunction-sections -fdata-sections -mtune=native -ldl -lrt

ONNX Runtime

Model: yolov4 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: yolov4 - Device: CPU - Executor: ParallelAOCC 4.0LLVM Clang 14GCC 12.2120240360480600SE +/- 0.73, N = 3SE +/- 0.44, N = 3SE +/- 0.29, N = 3569563568-flto=thin-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native -flto -ffunction-sections -fdata-sections -mtune=native -ldl -lrt

ONNX Runtime

Model: yolov4 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: yolov4 - Device: CPU - Executor: StandardAOCC 4.0LLVM Clang 14GCC 12.2120240360480600SE +/- 3.33, N = 3SE +/- 5.06, N = 3SE +/- 21.40, N = 9576566564-flto=thin-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native -flto -ffunction-sections -fdata-sections -mtune=native -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: ParallelAOCC 4.0LLVM Clang 14GCC 12.22004006008001000SE +/- 3.50, N = 3SE +/- 2.52, N = 3SE +/- 1.09, N = 3917923918-flto=thin-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native -flto -ffunction-sections -fdata-sections -mtune=native -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelAOCC 4.0LLVM Clang 14GCC 12.2306090120150SE +/- 0.58, N = 3SE +/- 0.50, N = 3SE +/- 0.17, N = 3135135134-flto=thin-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native -flto -ffunction-sections -fdata-sections -mtune=native -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelAOCC 4.0LLVM Clang 14GCC 12.25001000150020002500SE +/- 4.18, N = 3SE +/- 2.92, N = 3SE +/- 3.09, N = 3235623532361-flto=thin-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native -flto -ffunction-sections -fdata-sections -mtune=native -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardAOCC 4.0LLVM Clang 14GCC 12.26001200180024003000SE +/- 23.09, N = 12SE +/- 34.72, N = 12SE +/- 81.96, N = 12220727812222-flto=thin-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native -flto -ffunction-sections -fdata-sections -mtune=native -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: ParallelAOCC 4.0LLVM Clang 14GCC 12.22K4K6K8K10KSE +/- 69.59, N = 3SE +/- 110.94, N = 3SE +/- 88.15, N = 6911389499395-flto=thin-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native -flto -ffunction-sections -fdata-sections -mtune=native -ldl -lrt

GraphicsMagick

Operation: Swirl

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: SwirlAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.230060090012001500SE +/- 2.96, N = 3SE +/- 4.91, N = 3SE +/- 4.18, N = 3SE +/- 2.19, N = 3SE +/- 2.33, N = 3141313821473145413901. (CC) gcc options: -fopenmp -O3 -march=native -flto -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Rotate

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: RotateAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.22004006008001000SE +/- 1.20, N = 3SE +/- 7.17, N = 3SE +/- 3.18, N = 3SE +/- 2.89, N = 3SE +/- 0.88, N = 39528969889128761. (CC) gcc options: -fopenmp -O3 -march=native -flto -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Sharpen

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: SharpenAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2100200300400500SE +/- 0.67, N = 3SE +/- 2.73, N = 3SE +/- 0.58, N = 3SE +/- 0.67, N = 3SE +/- 0.88, N = 34704663433414541. (CC) gcc options: -fopenmp -O3 -march=native -flto -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Enhanced

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: EnhancedAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2140280420560700SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 36125826396275831. (CC) gcc options: -fopenmp -O3 -march=native -flto -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Resizing

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: ResizingAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.26001200180024003000SE +/- 5.17, N = 3SE +/- 3.79, N = 3SE +/- 2.52, N = 3SE +/- 8.67, N = 3SE +/- 4.67, N = 3260927052741262526551. (CC) gcc options: -fopenmp -O3 -march=native -flto -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Noise-Gaussian

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: Noise-GaussianAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2140280420560700SE +/- 0.67, N = 3SE +/- 2.03, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 1.20, N = 36075876646585831. (CC) gcc options: -fopenmp -O3 -march=native -flto -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: HWB Color Space

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: HWB Color SpaceAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2400800120016002000SE +/- 12.35, N = 3SE +/- 9.17, N = 3SE +/- 1.33, N = 3SE +/- 4.93, N = 3SE +/- 5.36, N = 3171015801533143815841. (CC) gcc options: -fopenmp -O3 -march=native -flto -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

Coremark

CoreMark Size 666 - Iterations Per Second

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2200K400K600K800K1000KSE +/- 973.61, N = 3SE +/- 521.77, N = 3SE +/- 799.86, N = 3SE +/- 1075.50, N = 3SE +/- 368.05, N = 3946032.29981244.491066150.951117817.251004815.011. (CC) gcc options: -O2 -O3 -march=native -flto -lrt" -lrt

Xsbench

OpenBenchmarking.orgLookups/s, More Is BetterXsbench 2017-07-06AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.21.5M3M4.5M6M7.5MSE +/- 4600.85, N = 3SE +/- 7500.25, N = 3SE +/- 1443.86, N = 3SE +/- 4489.29, N = 3SE +/- 2015.53, N = 3708134667560016234508631826267522381. (CC) gcc options: -std=gnu99 -fopenmp -O3 -lm

SecureMark

Benchmark: SecureMark-TLS

OpenBenchmarking.orgmarks, More Is BetterSecureMark 1.0.4Benchmark: SecureMark-TLSAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2100K200K300K400K500KSE +/- 454.53, N = 3SE +/- 535.99, N = 3SE +/- 2377.52, N = 3SE +/- 1407.45, N = 3SE +/- 2486.77, N = 34759414726244328104328964549571. (CC) gcc options: -pedantic -O3

C-Blosc

Test: blosclz shuffle

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.3Test: blosclz shuffleAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.25K10K15K20K25KSE +/- 238.69, N = 3SE +/- 81.78, N = 3SE +/- 90.86, N = 3SE +/- 203.38, N = 3SE +/- 173.15, N = 323837.224796.823526.424105.024197.7

C-Blosc

Test: blosclz bitshuffle

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.3Test: blosclz bitshuffleAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.23K6K9K12K15KSE +/- 81.98, N = 3SE +/- 152.49, N = 3SE +/- 76.49, N = 3SE +/- 38.45, N = 3SE +/- 150.84, N = 313508.913989.213017.313286.513694.2

Zstd Compression

Compression Level: 3 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3 - Compression SpeedAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.211002200330044005500SE +/- 10.48, N = 3SE +/- 13.86, N = 3SE +/- 14.32, N = 3SE +/- 10.83, N = 3SE +/- 28.62, N = 35092.25045.24978.64976.25030.81. (CC) gcc options: -O3 -march=native -flto -pthread -lz -llzma

Zstd Compression

Compression Level: 3 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3 - Decompression SpeedAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.212002400360048006000SE +/- 57.07, N = 3SE +/- 59.43, N = 3SE +/- 8.08, N = 3SE +/- 8.47, N = 3SE +/- 4.13, N = 35461.25463.55432.15485.85458.61. (CC) gcc options: -O3 -march=native -flto -pthread -lz -llzma

Zstd Compression

Compression Level: 19 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Compression SpeedAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.220406080100SE +/- 0.27, N = 3SE +/- 0.07, N = 3SE +/- 0.52, N = 3SE +/- 0.50, N = 3SE +/- 0.52, N = 379.178.980.382.278.81. (CC) gcc options: -O3 -march=native -flto -pthread -lz -llzma

Zstd Compression

Compression Level: 19 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Decompression SpeedAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.211002200330044005500SE +/- 41.19, N = 3SE +/- 21.62, N = 3SE +/- 20.04, N = 3SE +/- 72.80, N = 3SE +/- 29.56, N = 35018.64913.24932.04988.94894.61. (CC) gcc options: -O3 -march=native -flto -pthread -lz -llzma

Zstd Compression

Compression Level: 19, Long Mode - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Compression SpeedAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.21224364860SE +/- 0.15, N = 3SE +/- 0.12, N = 3SE +/- 0.17, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 354.654.654.654.355.31. (CC) gcc options: -O3 -march=native -flto -pthread -lz -llzma

Zstd Compression

Compression Level: 19, Long Mode - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression SpeedAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.211002200330044005500SE +/- 24.94, N = 3SE +/- 33.82, N = 3SE +/- 49.55, N = 3SE +/- 81.06, N = 3SE +/- 45.42, N = 35117.85055.84974.45073.84928.91. (CC) gcc options: -O3 -march=native -flto -pthread -lz -llzma

Nettle

Test: aes256

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.8Test: aes256AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.22K4K6K8K10KSE +/- 116.25, N = 3SE +/- 47.83, N = 3SE +/- 53.19, N = 3SE +/- 1.22, N = 3SE +/- 0.32, N = 38564.648566.178521.418490.468553.15MIN: 6283.86 / MAX: 12924.64MIN: 6405.01 / MAX: 12818.56-lhogweed - MIN: 6434.82 / MAX: 12801.5-lhogweed - MIN: 6473.53 / MAX: 12523.15MIN: 6494.58 / MAX: 12673.871. (CC) gcc options: -O3 -march=native -flto -ggdb3 -lnettle -lgmp -lm -lcrypto

Nettle

Test: chacha

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.8Test: chachaAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.230060090012001500SE +/- 2.93, N = 3SE +/- 10.11, N = 3SE +/- 9.98, N = 3SE +/- 0.01, N = 3SE +/- 0.55, N = 31528.821536.841515.121507.341523.44MIN: 773.94 / MAX: 4229.15MIN: 773.42 / MAX: 4324.28-lhogweed - MIN: 754.38 / MAX: 4226.47-lhogweed - MIN: 757.05 / MAX: 4174.74MIN: 773.19 / MAX: 4193.521. (CC) gcc options: -O3 -march=native -flto -ggdb3 -lnettle -lgmp -lm -lcrypto

Nettle

Test: sha512

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.8Test: sha512AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.22004006008001000SE +/- 0.77, N = 3SE +/- 0.60, N = 3SE +/- 0.38, N = 3SE +/- 0.35, N = 3SE +/- 0.75, N = 3864.29864.87858.30859.96863.73-lhogweed-lhogweed1. (CC) gcc options: -O3 -march=native -flto -ggdb3 -lnettle -lgmp -lm -lcrypto

Nettle

Test: poly1305-aes

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.8Test: poly1305-aesAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.29001800270036004500SE +/- 5.55, N = 3SE +/- 4.96, N = 3SE +/- 6.07, N = 3SE +/- 18.65, N = 3SE +/- 1.66, N = 34255.914231.634182.314188.144214.74-lhogweed-lhogweed1. (CC) gcc options: -O3 -march=native -flto -ggdb3 -lnettle -lgmp -lm -lcrypto

libjpeg-turbo tjbench

Test: Decompression Throughput

OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.1.0Test: Decompression ThroughputAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.270140210280350SE +/- 0.79, N = 3SE +/- 0.31, N = 3SE +/- 0.85, N = 3SE +/- 0.46, N = 3SE +/- 0.23, N = 3318.29320.16314.76322.49321.221. (CC) gcc options: -O3 -march=native -flto -rdynamic -lm

Sockperf

Test: Throughput

OpenBenchmarking.orgMessages Per Second, More Is BetterSockperf 3.7Test: ThroughputAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2200K400K600K800K1000KSE +/- 1831.17, N = 5SE +/- 4602.76, N = 5SE +/- 3167.67, N = 5SE +/- 2684.21, N = 5SE +/- 3955.76, N = 58790958837568891039003108976611. (CXX) g++ options: --param -O3 -march=native -flto -rdynamic

QuantLib

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.21AOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.210002000300040005000SE +/- 7.07, N = 3SE +/- 66.71, N = 3SE +/- 52.72, N = 12SE +/- 83.36, N = 124532.34669.54501.14783.91. (CXX) g++ options: -O3 -march=native -rdynamic

Crypto++

Test: Keyed Algorithms

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Keyed AlgorithmsAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.22004006008001000SE +/- 2.11, N = 3SE +/- 0.29, N = 3SE +/- 1.11, N = 3SE +/- 3.44, N = 31048.651086.85881.351075.791. (CXX) g++ options: -O3 -march=native -flto -fPIC -pthread -pipe

Crypto++

Test: Unkeyed Algorithms

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Unkeyed AlgorithmsAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.2130260390520650SE +/- 0.53, N = 3SE +/- 5.89, N = 3SE +/- 3.68, N = 3SE +/- 4.73, N = 3591.18593.21481.76596.871. (CXX) g++ options: -O3 -march=native -flto -fPIC -pthread -pipe

JPEG XL libjxl

Input: PNG - Quality: 90

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: PNG - Quality: 90AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.248121620SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 313.5013.1912.9813.0117.98-Xclang -mrelax-all-Xclang -mrelax-all-Xclang -mrelax-all1. (CXX) g++ options: -O3 -march=native -flto -fno-rtti -funwind-tables -O2 -fPIE -pie -latomic

JPEG XL libjxl

Input: JPEG - Quality: 90

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: JPEG - Quality: 90AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.248121620SE +/- 0.08, N = 3SE +/- 0.11, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 3SE +/- 0.11, N = 313.1313.1012.5412.7617.46-Xclang -mrelax-all-Xclang -mrelax-all-Xclang -mrelax-all1. (CXX) g++ options: -O3 -march=native -flto -fno-rtti -funwind-tables -O2 -fPIE -pie -latomic

JPEG XL libjxl

Input: PNG - Quality: 100

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: PNG - Quality: 100AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.24980.49960.74940.99921.249SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 5SE +/- 0.01, N = 3SE +/- 0.01, N = 31.081.071.041.031.11-Xclang -mrelax-all-Xclang -mrelax-all-Xclang -mrelax-all1. (CXX) g++ options: -O3 -march=native -flto -fno-rtti -funwind-tables -O2 -fPIE -pie -latomic

JPEG XL libjxl

Input: JPEG - Quality: 100

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: JPEG - Quality: 100AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.21150.4230.63450.8461.0575SE +/- 0.01, N = 6SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 6SE +/- 0.01, N = 90.850.940.850.850.87-Xclang -mrelax-all-Xclang -mrelax-all-Xclang -mrelax-all1. (CXX) g++ options: -O3 -march=native -flto -fno-rtti -funwind-tables -O2 -fPIE -pie -latomic

JPEG XL Decoding libjxl

CPU Threads: 1

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL Decoding libjxl 0.7CPU Threads: 1AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.220406080100SE +/- 0.16, N = 3SE +/- 0.16, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 377.2762.2968.4466.3063.32

JPEG XL Decoding libjxl

CPU Threads: All

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL Decoding libjxl 0.7CPU Threads: AllAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.260120180240300SE +/- 2.69, N = 3SE +/- 1.06, N = 3SE +/- 3.47, N = 3SE +/- 1.42, N = 3SE +/- 1.97, N = 3286.44264.48263.90245.54266.89

WebP Image Encode

Encode Settings: Default

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: DefaultAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2714212835SE +/- 0.02, N = 3SE +/- 0.40, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 329.6529.4528.0228.1829.23-lpng16 -ljpeg-lpng16 -ljpeg -ltiff-lpng16 -ljpeg -ltiff1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -flto -lm

WebP Image Encode

Encode Settings: Quality 100

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.248121620SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.11, N = 3SE +/- 0.06, N = 3SE +/- 0.24, N = 317.6717.5116.6116.8017.00-lpng16 -ljpeg-lpng16 -ljpeg -ltiff-lpng16 -ljpeg -ltiff1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -flto -lm

WebP Image Encode

Encode Settings: Quality 100, Lossless

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, LosslessAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.5131.0261.5392.0522.565SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 32.172.062.232.282.15-lpng16 -ljpeg-lpng16 -ljpeg -ltiff-lpng16 -ljpeg -ltiff1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -flto -lm

WebP Image Encode

Encode Settings: Quality 100, Highest Compression

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Highest CompressionAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2246810SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 36.336.164.484.606.21-lpng16 -ljpeg-lpng16 -ljpeg -ltiff-lpng16 -ljpeg -ltiff1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -flto -lm

WebP Image Encode

Encode Settings: Quality 100, Lossless, Highest Compression

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Lossless, Highest CompressionAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.20250.4050.60750.811.0125SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.890.830.880.890.90-lpng16 -ljpeg-lpng16 -ljpeg -ltiff-lpng16 -ljpeg -ltiff1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -flto -lm

ASTC Encoder

Preset: Fast

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: FastAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.290180270360450SE +/- 0.03, N = 3SE +/- 0.36, N = 3SE +/- 1.00, N = 3SE +/- 0.15, N = 3SE +/- 0.42, N = 3427.33404.45289.29294.57412.211. (CXX) g++ options: -O3 -march=native -flto -pthread

ASTC Encoder

Preset: Medium

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: MediumAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.24080120160200SE +/- 0.27, N = 3SE +/- 0.21, N = 3SE +/- 0.92, N = 3SE +/- 0.51, N = 3SE +/- 0.11, N = 3160.96155.09132.59135.19156.451. (CXX) g++ options: -O3 -march=native -flto -pthread

ASTC Encoder

Preset: Thorough

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ThoroughAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2510152025SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 319.9119.2819.4519.7719.431. (CXX) g++ options: -O3 -march=native -flto -pthread

ASTC Encoder

Preset: Exhaustive

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ExhaustiveAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.45620.91241.36861.82482.281SE +/- 0.0024, N = 3SE +/- 0.0029, N = 3SE +/- 0.0035, N = 3SE +/- 0.0024, N = 3SE +/- 0.0022, N = 32.01601.98142.00712.02761.98861. (CXX) g++ options: -O3 -march=native -flto -pthread

LeelaChessZero

Backend: BLAS

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: BLASAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.2400800120016002000SE +/- 24.06, N = 3SE +/- 14.33, N = 3SE +/- 18.37, N = 4SE +/- 18.88, N = 417481702169716861. (CXX) g++ options: -flto -O3 -march=native -pthread

LeelaChessZero

Backend: Eigen

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: EigenAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.2400800120016002000SE +/- 19.60, N = 3SE +/- 17.46, N = 3SE +/- 19.08, N = 3SE +/- 11.93, N = 319451861172518631. (CXX) g++ options: -flto -O3 -march=native -pthread

TSCP

AI Chess Performance

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2600K1200K1800K2400K3000KSE +/- 18536.62, N = 5SE +/- 17050.36, N = 5SE +/- 7641.62, N = 5SE +/- 3566.28, N = 5SE +/- 14422.21, N = 5247706329425792496821249222828570221. (CC) gcc options: -O3 -march=native -flto

LAMMPS Molecular Dynamics Simulator

Model: Rhodopsin Protein

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: Rhodopsin ProteinAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.248121620SE +/- 0.06, N = 3SE +/- 0.13, N = 15SE +/- 0.17, N = 3SE +/- 0.23, N = 3SE +/- 0.14, N = 1517.9117.6917.2617.0417.391. (CXX) g++ options: -O3 -march=native -flto -lm -ldl

Dragonflydb

Clients: 50 - Set To Get Ratio: 1:5

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 0.6Clients: 50 - Set To Get Ratio: 1:5AOCC 4.0GCC 12.2GCC 13.0 14 Nov1.2M2.4M3.6M4.8M6MSE +/- 24619.72, N = 3SE +/- 28018.78, N = 3SE +/- 37756.01, N = 35728724.375707956.745757620.861. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Dragonflydb

Clients: 50 - Set To Get Ratio: 5:1

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 0.6Clients: 50 - Set To Get Ratio: 5:1AOCC 4.0GCC 12.2GCC 13.0 14 Nov1.1M2.2M3.3M4.4M5.5MSE +/- 18465.52, N = 3SE +/- 11820.30, N = 3SE +/- 10081.64, N = 35242954.595275879.835271140.491. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Redis

Test: SET - Parallel Connections: 50

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 50AOCC 4.0GCC 12.2GCC 13.0 14 Nov1000K2000K3000K4000K5000KSE +/- 43555.06, N = 15SE +/- 56367.98, N = 15SE +/- 63650.32, N = 154701871.504498344.354675697.001. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native -flto

PJSIP

Method: INVITE

OpenBenchmarking.orgResponses Per Second, More Is BetterPJSIP 2.11Method: INVITEAOCC 4.0GCC 12.2GCC 13.0 14 Nov11002200330044005500SE +/- 64.01, N = 3SE +/- 5.24, N = 3SE +/- 57.10, N = 55344527953381. (CC) gcc options: -lSDL2 -lavformat -lavcodec -lswscale -lavutil -lstdc++ -lopus -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O3 -march=native -flto

PJSIP

Method: OPTIONS, Stateful

OpenBenchmarking.orgResponses Per Second, More Is BetterPJSIP 2.11Method: OPTIONS, StatefulAOCC 4.0GCC 12.2GCC 13.0 14 Nov2K4K6K8K10KSE +/- 19.14, N = 3SE +/- 17.01, N = 3SE +/- 37.24, N = 39370933093891. (CC) gcc options: -lSDL2 -lavformat -lavcodec -lswscale -lavutil -lstdc++ -lopus -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O3 -march=native -flto

PJSIP

Method: OPTIONS, Stateless

OpenBenchmarking.orgResponses Per Second, More Is BetterPJSIP 2.11Method: OPTIONS, StatelessAOCC 4.0GCC 12.2GCC 13.0 14 Nov30K60K90K120K150KSE +/- 515.14, N = 3SE +/- 794.35, N = 3SE +/- 236.11, N = 31245231258251240281. (CC) gcc options: -lSDL2 -lavformat -lavcodec -lswscale -lavutil -lstdc++ -lopus -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O3 -march=native -flto

Liquid-DSP

Threads: 8 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 8 - Buffer Length: 256 - Filter Length: 57AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2200M400M600M800M1000MSE +/- 6969075.34, N = 3SE +/- 475966.85, N = 3SE +/- 1506567.11, N = 3SE +/- 2781883.85, N = 3SE +/- 84936093.08, N = 128962433338098233338345066676508766675663527501. (CC) gcc options: -O3 -march=native -flto -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 16 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 16 - Buffer Length: 256 - Filter Length: 57AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2400M800M1200M1600M2000MSE +/- 5356097.25, N = 3SE +/- 1993600.87, N = 3SE +/- 6222093.25, N = 3SE +/- 2273274.68, N = 3SE +/- 883804.91, N = 3175483333315840666671627233333127443333315442666671. (CC) gcc options: -O3 -march=native -flto -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 32 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 32 - Buffer Length: 256 - Filter Length: 57AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2400M800M1200M1600M2000MSE +/- 2450170.06, N = 3SE +/- 721110.26, N = 3SE +/- 1289702.81, N = 3SE +/- 4147824.06, N = 3SE +/- 983756.97, N = 3188660000017236000001680600000163316666716549333331. (CC) gcc options: -O3 -march=native -flto -pthread -lm -lc -lliquid

OpenSSL

Algorithm: RSA4096

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.213002600390052006500SE +/- 4.01, N = 3SE +/- 10.70, N = 3SE +/- 1.50, N = 3SE +/- 0.27, N = 3SE +/- 0.55, N = 36026.26016.66014.66029.16030.9-Qunused-arguments-Qunused-arguments-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=native -flto -lssl -lcrypto -ldl

CLOMP

Static OMP Speedup

OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 1.2Static OMP SpeedupAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2612182430SE +/- 0.27, N = 5SE +/- 0.23, N = 6SE +/- 0.27, N = 3SE +/- 0.03, N = 3SE +/- 0.15, N = 325.023.722.822.623.61. (CC) gcc options: -fopenmp -O3 -march=native -flto -lm

Kripke

OpenBenchmarking.orgThroughput FoM, More Is BetterKripke 1.2.4AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.230M60M90M120M150MSE +/- 1766612.42, N = 3SE +/- 1260500.21, N = 4SE +/- 1385510.65, N = 15SE +/- 1504986.40, N = 4SE +/- 1079837.67, N = 3125045767109794900133327173132057600108977267-fopenmp=libomp-fopenmp=libomp-fopenmp-fopenmp-fopenmp=libomp1. (CXX) g++ options: -O3 -march=native -flto

OpenSSL

Algorithm: RSA4096

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.280K160K240K320K400KSE +/- 12.58, N = 3SE +/- 38.98, N = 3SE +/- 54.65, N = 3SE +/- 44.62, N = 3SE +/- 41.04, N = 3394139.1395258.1393865.8394339.8395636.4-Qunused-arguments-Qunused-arguments-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=native -flto -lssl -lcrypto -ldl

Caffe

Model: AlexNet - Acceleration: CPU - Iterations: 100

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 100AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.210K20K30K40K50KSE +/- 59.47, N = 3SE +/- 157.80, N = 3SE +/- 77.62, N = 3SE +/- 57.54, N = 3SE +/- 113.58, N = 327653469762368523696468001. (CXX) g++ options: -O3 -march=native -flto -fPIC -rdynamic -lglog -lgflags -lprotobuf -lcrypto -lcurl -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

Caffe

Model: GoogleNet - Acceleration: CPU - Iterations: 100

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 100AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.220K40K60K80K100KSE +/- 160.54, N = 3SE +/- 77.99, N = 3SE +/- 206.69, N = 3SE +/- 221.71, N = 3SE +/- 326.67, N = 37393410494265742649871074141. (CXX) g++ options: -O3 -march=native -flto -fPIC -rdynamic -lglog -lgflags -lprotobuf -lcrypto -lcurl -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

oneDNN

Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.1180.2360.3540.4720.59SE +/- 0.000214, N = 3SE +/- 0.000115, N = 3SE +/- 0.002131, N = 3SE +/- 0.029304, N = 15SE +/- 0.000600, N = 30.3385810.3435950.4799060.5242830.343749-fopenmp=libomp - MIN: 0.33-fopenmp=libomp - MIN: 0.33-fopenmp - MIN: 0.38-fopenmp -lpthread - MIN: 0.35-fopenmp=libomp - MIN: 0.331. (CXX) g++ options: -O3 -march=native -flto -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.08150.1630.24450.3260.4075SE +/- 0.002915, N = 3SE +/- 0.004019, N = 3SE +/- 0.003679, N = 15SE +/- 0.003020, N = 15SE +/- 0.001605, N = 30.3470170.3377600.3565460.3564070.362285-fopenmp=libomp - MIN: 0.31-fopenmp=libomp - MIN: 0.31-fopenmp - MIN: 0.3-fopenmp -lpthread - MIN: 0.3-fopenmp=libomp - MIN: 0.321. (CXX) g++ options: -O3 -march=native -flto -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPUAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.16330.32660.48990.65320.8165SE +/- 0.000272, N = 3SE +/- 0.000668, N = 3SE +/- 0.034180, N = 12SE +/- 0.016807, N = 15SE +/- 0.000306, N = 30.5778340.5833770.7259780.6629050.582381-fopenmp=libomp - MIN: 0.56-fopenmp=libomp - MIN: 0.57-fopenmp - MIN: 0.58-fopenmp -lpthread - MIN: 0.58-fopenmp=libomp - MIN: 0.571. (CXX) g++ options: -O3 -march=native -flto -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPUAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.34740.69481.04221.38961.737SE +/- 0.00757, N = 3SE +/- 0.01741, N = 3SE +/- 0.00876, N = 3SE +/- 0.00799, N = 3SE +/- 0.01491, N = 31.500161.511761.543791.533051.51369-fopenmp=libomp - MIN: 1.45-fopenmp=libomp - MIN: 1.45-fopenmp - MIN: 1.46-fopenmp -lpthread - MIN: 1.46-fopenmp=libomp - MIN: 1.451. (CXX) g++ options: -O3 -march=native -flto -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.21.19882.39763.59644.79525.994SE +/- 0.00469, N = 3SE +/- 0.01758, N = 3SE +/- 0.00364, N = 3SE +/- 0.00740, N = 3SE +/- 0.01647, N = 35.287855.319305.327805.305015.30337-fopenmp=libomp - MIN: 5.23-fopenmp=libomp - MIN: 5.24-fopenmp - MIN: 5.25-fopenmp -lpthread - MIN: 5.23-fopenmp=libomp - MIN: 5.241. (CXX) g++ options: -O3 -march=native -flto -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.09480.18960.28440.37920.474SE +/- 0.000864, N = 3SE +/- 0.000027, N = 3SE +/- 0.000200, N = 3SE +/- 0.000894, N = 3SE +/- 0.000120, N = 30.4050970.4084320.4214190.4188600.408594-fopenmp=libomp - MIN: 0.39-fopenmp=libomp - MIN: 0.39-fopenmp - MIN: 0.41-fopenmp -lpthread - MIN: 0.4-fopenmp=libomp - MIN: 0.41. (CXX) g++ options: -O3 -march=native -flto -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.22004006008001000SE +/- 0.74, N = 3SE +/- 0.92, N = 3SE +/- 2.28, N = 3SE +/- 1.14, N = 3SE +/- 0.82, N = 31138.831138.261140.341139.641137.49-fopenmp=libomp - MIN: 1134.32-fopenmp=libomp - MIN: 1134.02-fopenmp - MIN: 1132.99-fopenmp -lpthread - MIN: 1133.46-fopenmp=libomp - MIN: 1132.691. (CXX) g++ options: -O3 -march=native -flto -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.77951.5592.33853.1183.8975SE +/- 0.01463, N = 3SE +/- 0.00364, N = 3SE +/- 0.00041, N = 3SE +/- 0.00889, N = 3SE +/- 0.03887, N = 33.273673.395813.364123.426863.46444-fopenmp=libomp - MIN: 3.13-fopenmp=libomp - MIN: 3.3-fopenmp - MIN: 3.21-fopenmp -lpthread - MIN: 3.24-fopenmp=libomp - MIN: 3.261. (CXX) g++ options: -O3 -march=native -flto -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPUAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.31670.63340.95011.26681.5835SE +/- 0.00291, N = 3SE +/- 0.00660, N = 3SE +/- 0.00253, N = 3SE +/- 0.01473, N = 13SE +/- 0.00184, N = 31.384551.407661.386961.405031.39579-fopenmp=libomp - MIN: 1.33-fopenmp=libomp - MIN: 1.35-fopenmp - MIN: 1.35-fopenmp -lpthread - MIN: 1.34-fopenmp=libomp - MIN: 1.351. (CXX) g++ options: -O3 -march=native -flto -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2130260390520650SE +/- 0.21, N = 3SE +/- 0.44, N = 3SE +/- 2.60, N = 3SE +/- 1.15, N = 3SE +/- 0.73, N = 3574.01575.60580.33582.00575.13-fopenmp=libomp - MIN: 571.16-fopenmp=libomp - MIN: 571.93-fopenmp - MIN: 573.07-fopenmp -lpthread - MIN: 575.92-fopenmp=libomp - MIN: 571.751. (CXX) g++ options: -O3 -march=native -flto -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.22004006008001000SE +/- 1.07, N = 3SE +/- 1.57, N = 3SE +/- 0.51, N = 3SE +/- 0.77, N = 3SE +/- 1.59, N = 31139.441142.951139.551142.221142.00-fopenmp=libomp - MIN: 1134.21-fopenmp=libomp - MIN: 1136.51-fopenmp - MIN: 1134.18-fopenmp -lpthread - MIN: 1135.79-fopenmp=libomp - MIN: 1135.131. (CXX) g++ options: -O3 -march=native -flto -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2130260390520650SE +/- 0.14, N = 3SE +/- 0.11, N = 3SE +/- 1.50, N = 3SE +/- 2.68, N = 3SE +/- 0.79, N = 3574.91575.94578.82578.96576.22-fopenmp=libomp - MIN: 572.07-fopenmp=libomp - MIN: 573.26-fopenmp - MIN: 572.91-fopenmp -lpthread - MIN: 571.53-fopenmp=libomp - MIN: 572.911. (CXX) g++ options: -O3 -march=native -flto -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.03160.06320.09480.12640.158SE +/- 0.000006, N = 3SE +/- 0.000110, N = 3SE +/- 0.000173, N = 3SE +/- 0.000031, N = 3SE +/- 0.000185, N = 30.1331690.1363430.1398620.1403490.136310-fopenmp=libomp - MIN: 0.13-fopenmp=libomp - MIN: 0.13-fopenmp - MIN: 0.13-fopenmp -lpthread - MIN: 0.13-fopenmp=libomp - MIN: 0.131. (CXX) g++ options: -O3 -march=native -flto -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPUAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.05140.10280.15420.20560.257SE +/- 0.000436, N = 3SE +/- 0.000409, N = 3SE +/- 0.000273, N = 3SE +/- 0.000270, N = 3SE +/- 0.000141, N = 30.2223780.2241010.2285140.2279180.224449-fopenmp=libomp - MIN: 0.21-fopenmp=libomp - MIN: 0.22-fopenmp - MIN: 0.21-fopenmp -lpthread - MIN: 0.22-fopenmp=libomp - MIN: 0.221. (CXX) g++ options: -O3 -march=native -flto -msse4.1 -fPIC -pie -ldl

OpenJPEG

Encode: NASA Curiosity Panorama M34

OpenBenchmarking.orgms, Fewer Is BetterOpenJPEG 2.4Encode: NASA Curiosity Panorama M34AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.216K32K48K64K80KSE +/- 115.52, N = 3SE +/- 566.51, N = 7SE +/- 575.75, N = 15SE +/- 357.45, N = 3SE +/- 79.04, N = 373991644167122269608626891. (CXX) g++ options: -O3 -march=native -flto -rdynamic

Google Draco

Model: Lion

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: LionAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.28001600240032004000SE +/- 5.51, N = 3SE +/- 52.92, N = 3SE +/- 30.51, N = 3SE +/- 22.07, N = 333733763348637001. (CXX) g++ options: -O3 -march=native -flto

Google Draco

Model: Church Facade

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: Church FacadeAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.210002000300040005000SE +/- 7.54, N = 3SE +/- 8.51, N = 3SE +/- 1.00, N = 3SE +/- 47.16, N = 643244782442446491. (CXX) g++ options: -O3 -march=native -flto

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.23691215SE +/- 0.11, N = 3SE +/- 0.09, N = 6SE +/- 0.08, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 58.579.098.688.689.24-lomp - MIN: 8.29 / MAX: 9.54MIN: 8.74 / MAX: 10.31-lgomp - MIN: 8.53 / MAX: 9.96-lgomp - MIN: 8.49 / MAX: 11.83MIN: 8.92 / MAX: 30.181. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.8371.6742.5113.3484.185SE +/- 0.07, N = 3SE +/- 0.02, N = 6SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 53.173.443.713.723.53-lomp - MIN: 3.04 / MAX: 4.89MIN: 3.31 / MAX: 4.22-lgomp - MIN: 3.64 / MAX: 5.07-lgomp - MIN: 3.64 / MAX: 4.37MIN: 3.4 / MAX: 4.361. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v3-v3 - Model: mobilenet-v3AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.73351.4672.20052.9343.6675SE +/- 0.02, N = 3SE +/- 0.02, N = 6SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 52.692.993.243.262.99-lomp - MIN: 2.6 / MAX: 3.34MIN: 2.9 / MAX: 3.96-lgomp - MIN: 3.18 / MAX: 4.64-lgomp - MIN: 3.19 / MAX: 3.89MIN: 2.85 / MAX: 4.221. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.8461.6922.5383.3844.23SE +/- 0.07, N = 3SE +/- 0.05, N = 6SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 52.963.253.763.743.31-lomp - MIN: 2.81 / MAX: 3.55MIN: 3.05 / MAX: 3.95-lgomp - MIN: 3.69 / MAX: 4.45-lgomp - MIN: 3.68 / MAX: 12.3MIN: 3.2 / MAX: 4.881. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.7471.4942.2412.9883.735SE +/- 0.04, N = 3SE +/- 0.03, N = 6SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 52.723.023.303.323.07-lomp - MIN: 2.65 / MAX: 5.37MIN: 2.88 / MAX: 3.77-lgomp - MIN: 3.26 / MAX: 3.92-lgomp - MIN: 3.26 / MAX: 4.03MIN: 2.98 / MAX: 3.821. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.21.0442.0883.1324.1765.22SE +/- 0.07, N = 3SE +/- 0.03, N = 6SE +/- 0.11, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 53.854.254.644.574.35-lomp - MIN: 3.73 / MAX: 4.7MIN: 4.09 / MAX: 5.43-lgomp - MIN: 4.46 / MAX: 16.81-lgomp - MIN: 4.45 / MAX: 5.39MIN: 4.17 / MAX: 17.271. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.35780.71561.07341.43121.789SE +/- 0.01, N = 3SE +/- 0.01, N = 6SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 51.211.371.591.581.41-lomp - MIN: 1.18 / MAX: 1.94MIN: 1.32 / MAX: 2.09-lgomp - MIN: 1.55 / MAX: 2.26-lgomp - MIN: 1.55 / MAX: 2.27MIN: 1.33 / MAX: 1.841. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2246810SE +/- 0.15, N = 3SE +/- 0.08, N = 6SE +/- 0.13, N = 3SE +/- 0.14, N = 3SE +/- 0.15, N = 57.858.548.668.658.63-lomp - MIN: 7.47 / MAX: 9.41MIN: 8.23 / MAX: 15.46-lgomp - MIN: 8.41 / MAX: 9.8-lgomp - MIN: 8.39 / MAX: 10.25MIN: 8.24 / MAX: 9.921. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2612182430SE +/- 0.31, N = 3SE +/- 0.42, N = 6SE +/- 0.26, N = 3SE +/- 0.36, N = 3SE +/- 0.34, N = 524.8325.9624.5624.3925.52-lomp - MIN: 24.13 / MAX: 31.13MIN: 24.5 / MAX: 34.87-lgomp - MIN: 24.02 / MAX: 31.29-lgomp - MIN: 23.8 / MAX: 30.07MIN: 24.44 / MAX: 33.711. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2246810SE +/- 0.05, N = 3SE +/- 0.08, N = 6SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.20, N = 57.187.367.497.497.41-lomp - MIN: 6.98 / MAX: 8.34MIN: 7.12 / MAX: 8.7-lgomp - MIN: 7.3 / MAX: 8.43-lgomp - MIN: 7.32 / MAX: 8.85MIN: 7.08 / MAX: 10.221. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.21.16782.33563.50344.67125.839SE +/- 0.08, N = 3SE +/- 0.01, N = 6SE +/- 0.15, N = 3SE +/- 0.13, N = 3SE +/- 0.04, N = 54.795.194.994.985.16-lomp - MIN: 4.59 / MAX: 5.88MIN: 5.05 / MAX: 6.8-lgomp - MIN: 4.76 / MAX: 12.84-lgomp - MIN: 4.76 / MAX: 5.88MIN: 4.97 / MAX: 7.151. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.23691215SE +/- 0.11, N = 3SE +/- 0.18, N = 6SE +/- 0.19, N = 3SE +/- 0.23, N = 3SE +/- 0.24, N = 511.6212.3212.2512.2612.32-lomp - MIN: 11.29 / MAX: 13.29MIN: 11.77 / MAX: 22.76-lgomp - MIN: 11.82 / MAX: 13.43-lgomp - MIN: 11.85 / MAX: 14.07MIN: 11.77 / MAX: 14.071. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.248121620SE +/- 0.06, N = 3SE +/- 0.08, N = 6SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.22, N = 514.3814.6814.0314.1214.94-lomp - MIN: 14.16 / MAX: 15.32MIN: 14.35 / MAX: 24.68-lgomp - MIN: 13.79 / MAX: 15.31-lgomp - MIN: 13.91 / MAX: 15.48MIN: 14.52 / MAX: 17.61. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.23691215SE +/- 0.21, N = 3SE +/- 0.10, N = 6SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.11, N = 511.2711.8012.4312.2711.97-lomp - MIN: 10.85 / MAX: 12.53MIN: 11.31 / MAX: 28.92-lgomp - MIN: 12.2 / MAX: 13.43-lgomp - MIN: 12.11 / MAX: 13.52MIN: 11.52 / MAX: 21.231. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.23691215SE +/- 0.13, N = 3SE +/- 0.09, N = 6SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.12, N = 57.559.4112.0111.849.62-lomp - MIN: 7.32 / MAX: 8.83MIN: 9.11 / MAX: 27.31-lgomp - MIN: 11.85 / MAX: 18.93-lgomp - MIN: 11.71 / MAX: 18.24MIN: 9.1 / MAX: 10.591. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

TNN

Target: CPU - Model: DenseNet

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNetAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.210002000300040005000SE +/- 0.57, N = 3SE +/- 1.92, N = 3SE +/- 50.48, N = 3SE +/- 6.75, N = 32455.643634.334513.712499.82-fopenmp=libomp - MIN: 2405.98 / MAX: 2515.95-fopenmp=libomp - MIN: 3566.47 / MAX: 3716.42-fopenmp - MIN: 4338.8 / MAX: 4643.28-fopenmp=libomp - MIN: 2420.99 / MAX: 2590.771. (CXX) g++ options: -O3 -march=native -flto -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

TNN

Target: CPU - Model: MobileNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v2AOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.290180270360450SE +/- 0.24, N = 3SE +/- 1.19, N = 3SE +/- 0.97, N = 3SE +/- 0.07, N = 3244.05431.56412.94337.48-fopenmp=libomp - MIN: 243.09 / MAX: 248.96-fopenmp=libomp - MIN: 428.32 / MAX: 434.62-fopenmp - MIN: 410.59 / MAX: 431.69-fopenmp=libomp - MIN: 336.45 / MAX: 345.731. (CXX) g++ options: -O3 -march=native -flto -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

TNN

Target: CPU - Model: SqueezeNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2AOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.21632486480SE +/- 0.41, N = 12SE +/- 0.37, N = 15SE +/- 0.89, N = 3SE +/- 0.31, N = 1544.5961.1169.9249.43-fopenmp=libomp - MIN: 40.15 / MAX: 45.73-fopenmp=libomp - MIN: 56.49 / MAX: 63.12-fopenmp - MIN: 68.11 / MAX: 71.55-fopenmp=libomp - MIN: 45.34 / MAX: 50.651. (CXX) g++ options: -O3 -march=native -flto -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

TNN

Target: CPU - Model: SqueezeNet v1.1

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.1AOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.280160240320400SE +/- 1.12, N = 3SE +/- 0.06, N = 3SE +/- 0.23, N = 3SE +/- 1.42, N = 3217.84302.02388.44232.44-fopenmp=libomp - MIN: 215.42 / MAX: 219.12-fopenmp=libomp - MIN: 301.67 / MAX: 304.24-fopenmp - MIN: 387.68 / MAX: 389.12-fopenmp=libomp - MIN: 230.61 / MAX: 241.131. (CXX) g++ options: -O3 -march=native -flto -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Face Detection FP16 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.2120240360480600SE +/- 1.12, N = 3SE +/- 2.19, N = 3SE +/- 1.81, N = 3SE +/- 2.14, N = 3557.01555.00557.36555.05MIN: 283.75 / MAX: 603.22MIN: 537.69 / MAX: 616.06-fno-strict-overflow -fwrapv - MIN: 527.31 / MAX: 601MIN: 522.63 / MAX: 589.631. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Person Detection FP16 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.22004006008001000SE +/- 2.64, N = 3SE +/- 0.94, N = 3SE +/- 1.87, N = 3SE +/- 4.13, N = 31055.291066.071060.871065.31MIN: 875.98 / MAX: 1296.48MIN: 718.92 / MAX: 1326.23-fno-strict-overflow -fwrapv - MIN: 672.13 / MAX: 1319.18MIN: 636.05 / MAX: 1337.861. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Person Detection FP32 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.22004006008001000SE +/- 3.44, N = 3SE +/- 5.67, N = 3SE +/- 7.82, N = 3SE +/- 5.64, N = 31081.011092.871085.331071.50MIN: 580.39 / MAX: 1284.59MIN: 753 / MAX: 1274.14-fno-strict-overflow -fwrapv - MIN: 731.35 / MAX: 1302.96MIN: 726.76 / MAX: 1318.281. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.23691215SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 310.6210.6210.5510.76MIN: 4 / MAX: 26.8MIN: 3.86 / MAX: 26.67-fno-strict-overflow -fwrapv - MIN: 4.88 / MAX: 26.32MIN: 5.08 / MAX: 25.941. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Face Detection FP16-INT8 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.260120180240300SE +/- 0.22, N = 3SE +/- 0.93, N = 3SE +/- 0.11, N = 3SE +/- 1.08, N = 3283.07283.72284.35282.59MIN: 145.95 / MAX: 325.14MIN: 146.73 / MAX: 325.51-fno-strict-overflow -fwrapv - MIN: 250.18 / MAX: 318.64MIN: 216.72 / MAX: 375.591. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.20.97881.95762.93643.91524.894SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 34.324.324.354.33MIN: 2.62 / MAX: 13.23MIN: 2.61 / MAX: 13.39-fno-strict-overflow -fwrapv - MIN: 2.69 / MAX: 14.15MIN: 2.65 / MAX: 13.041. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.21.25782.51563.77345.03126.289SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 35.555.575.595.56MIN: 2.87 / MAX: 13.9MIN: 2.89 / MAX: 15.21-fno-strict-overflow -fwrapv - MIN: 2.91 / MAX: 14.45MIN: 2.88 / MAX: 14.861. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Machine Translation EN To DE FP16 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.21326395265SE +/- 0.40, N = 3SE +/- 0.34, N = 3SE +/- 0.64, N = 3SE +/- 0.27, N = 359.9559.8359.4759.20MIN: 28.33 / MAX: 87.44MIN: 27.32 / MAX: 85.28-fno-strict-overflow -fwrapv - MIN: 27.89 / MAX: 86.56MIN: 30.14 / MAX: 87.471. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.21.24882.49763.74644.99526.244SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 35.525.545.555.52MIN: 2.93 / MAX: 12.86MIN: 2.86 / MAX: 13.37-fno-strict-overflow -fwrapv - MIN: 2.9 / MAX: 18.91MIN: 2.86 / MAX: 14.51. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.21.09132.18263.27394.36525.4565SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 44.804.834.824.85MIN: 3.12 / MAX: 13.53MIN: 3.7 / MAX: 13.95-fno-strict-overflow -fwrapv - MIN: 3.66 / MAX: 14.3MIN: 3.25 / MAX: 15.021. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.20.0810.1620.2430.3240.405SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.360.360.360.36MIN: 0.21 / MAX: 7.72MIN: 0.21 / MAX: 8.45-fno-strict-overflow -fwrapv - MIN: 0.21 / MAX: 9.03MIN: 0.21 / MAX: 8.851. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.20.05630.11260.16890.22520.2815SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.250.250.250.25MIN: 0.15 / MAX: 7.46MIN: 0.15 / MAX: 8.4-fno-strict-overflow -fwrapv - MIN: 0.15 / MAX: 8.94MIN: 0.15 / MAX: 21.41. (CXX) g++ options: -fPIC -O3 -march=native -flto -fsigned-char -ffunction-sections -fdata-sections -shared

Dolfyn

Computational Fluid Dynamics

OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid DynamicsAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.23691215SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 310.7710.7710.7910.5110.82

Monte Carlo Simulations of Ionised Nebulae

Input: Dust 2D tau100.0

OpenBenchmarking.orgSeconds, Fewer Is BetterMonte Carlo Simulations of Ionised Nebulae 2019-03-24Input: Dust 2D tau100.0AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.21530456075SE +/- 0.58, N = 3SE +/- 0.71, N = 4SE +/- 0.88, N = 3SE +/- 0.33, N = 3SE +/- 0.88, N = 364656463641. (F9X) gfortran options: -cpp -Jsource/ -ffree-line-length-0 -lm -std=legacy -O3 -O2 -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lz

libavif avifenc

Encoder Speed: 0

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 0AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.21530456075SE +/- 0.18, N = 3SE +/- 0.45, N = 3SE +/- 0.11, N = 3SE +/- 0.17, N = 3SE +/- 0.23, N = 363.1165.2368.5266.2765.151. (CXX) g++ options: -O3 -fPIC -march=native -flto -lm

libavif avifenc

Encoder Speed: 2

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 2AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2816243240SE +/- 0.08, N = 3SE +/- 0.12, N = 3SE +/- 0.24, N = 3SE +/- 0.16, N = 3SE +/- 0.04, N = 331.3832.3834.8533.7532.311. (CXX) g++ options: -O3 -fPIC -march=native -flto -lm

libavif avifenc

Encoder Speed: 6

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 6AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.72051.4412.16152.8823.6025SE +/- 0.022, N = 3SE +/- 0.018, N = 3SE +/- 0.011, N = 3SE +/- 0.006, N = 3SE +/- 0.005, N = 32.9433.0793.2023.1053.0441. (CXX) g++ options: -O3 -fPIC -march=native -flto -lm

libavif avifenc

Encoder Speed: 6, Lossless

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 6, LosslessAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.21.13132.26263.39394.52525.6565SE +/- 0.019, N = 3SE +/- 0.002, N = 3SE +/- 0.027, N = 3SE +/- 0.002, N = 3SE +/- 0.024, N = 34.2294.3775.0284.6754.3631. (CXX) g++ options: -O3 -fPIC -march=native -flto -lm

libavif avifenc

Encoder Speed: 10, Lossless

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 10, LosslessAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.20.69231.38462.07692.76923.4615SE +/- 0.033, N = 3SE +/- 0.009, N = 3SE +/- 0.021, N = 3SE +/- 0.004, N = 3SE +/- 0.018, N = 32.7732.7613.0772.9472.7251. (CXX) g++ options: -O3 -fPIC -march=native -flto -lm

C-Ray

Total Time - 4K, 16 Rays Per Pixel

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2612182430SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 327.4520.1318.9919.3320.151. (CC) gcc options: -lm -lpthread -O3 -march=native -flto

POV-Ray

Trace Time

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace TimeAOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.248121620SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 316.1016.5715.9614.83-R/usr/lib1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -flto -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

Primesieve

Length: 1e12

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 8.0Length: 1e12AOCC 4.0LLVM Clang 14GCC 12.2LLVM Clang 15.0.2246810SE +/- 0.011, N = 3SE +/- 0.008, N = 3SE +/- 0.010, N = 3SE +/- 0.016, N = 36.2456.1726.1876.2431. (CXX) g++ options: -O3 -march=native -flto

AOBench

Size: 2048 x 2048 - Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total TimeAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2510152025SE +/- 0.03, N = 3SE +/- 0.28, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 321.5821.7019.7619.9021.391. (CC) gcc options: -lm -O3 -march=native -flto

FLAC Audio Encoding

WAV To FLAC

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.4WAV To FLACAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.23691215SE +/- 0.018, N = 5SE +/- 0.025, N = 5SE +/- 0.073, N = 5SE +/- 0.021, N = 5SE +/- 0.007, N = 59.9289.28010.52010.8109.4351. (CXX) g++ options: -O3 -march=native -flto -fvisibility=hidden -logg -lm

LAME MP3 Encoding

WAV To MP3

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.21.06472.12943.19414.25885.3235SE +/- 0.014, N = 3SE +/- 0.005, N = 3SE +/- 0.012, N = 3SE +/- 0.007, N = 3SE +/- 0.010, N = 34.7324.6204.4094.3874.529-ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr-ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr1. (CC) gcc options: -O3 -pipe -march=native -flto -lncurses -lm

eSpeak-NG Speech Engine

Text-To-Speech Synthesis

OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak-NG Speech Engine 20200907Text-To-Speech SynthesisAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 Nov510152025SE +/- 0.11, N = 4SE +/- 0.11, N = 4SE +/- 0.11, N = 4SE +/- 0.14, N = 414.5420.5417.8317.771. (CC) gcc options: -O3 -march=native -flto -std=c99

Ngspice

Circuit: C2670

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C2670AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.21428425670SE +/- 0.47, N = 3SE +/- 0.14, N = 3SE +/- 0.14, N = 3SE +/- 0.41, N = 3SE +/- 0.46, N = 358.2657.7163.7562.6858.96-lstdc++-lstdc++-lstdc++-lstdc++1. (CC) gcc options: -O3 -march=native -flto -fopenmp -lm -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lSM -lICE

Ngspice

Circuit: C7552

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C7552AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.21326395265SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.17, N = 356.3156.2258.2860.2956.48-lstdc++-lstdc++-lstdc++-lstdc++1. (CC) gcc options: -O3 -march=native -flto -fopenmp -lm -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lSM -lICE

Tachyon

Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.99.2Total TimeAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.21224364860SE +/- 0.19, N = 3SE +/- 0.19, N = 3SE +/- 0.22, N = 3SE +/- 0.20, N = 3SE +/- 0.16, N = 355.4954.9755.4855.2855.081. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread

CppPerformanceBenchmarks

Test: Atol

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: AtolAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2612182430SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.29, N = 425.5225.4625.4325.5526.061. (CXX) g++ options: -O3 -march=native -flto -std=c++11

CppPerformanceBenchmarks

Test: Ctype

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: CtypeAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2816243240SE +/- 0.44, N = 3SE +/- 0.01, N = 3SE +/- 0.22, N = 3SE +/- 0.36, N = 3SE +/- 0.20, N = 331.3631.6332.2833.7731.781. (CXX) g++ options: -O3 -march=native -flto -std=c++11

CppPerformanceBenchmarks

Test: Math Library

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Math LibraryAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.24080120160200SE +/- 0.09, N = 3SE +/- 0.38, N = 3SE +/- 0.39, N = 3SE +/- 0.41, N = 3SE +/- 0.74, N = 3164.80164.39166.58169.48165.551. (CXX) g++ options: -O3 -march=native -flto -std=c++11

CppPerformanceBenchmarks

Test: Stepanov Vector

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Stepanov VectorAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2918273645SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 339.3840.1835.2035.5140.281. (CXX) g++ options: -O3 -march=native -flto -std=c++11

CppPerformanceBenchmarks

Test: Function Objects

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Function ObjectsAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.23691215SE +/- 0.031, N = 3SE +/- 0.014, N = 3SE +/- 0.086, N = 3SE +/- 0.094, N = 3SE +/- 0.006, N = 39.0239.2469.2519.2119.3331. (CXX) g++ options: -O3 -march=native -flto -std=c++11

CppPerformanceBenchmarks

Test: Stepanov Abstraction

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Stepanov AbstractionAOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.248121620SE +/- 0.15, N = 3SE +/- 0.10, N = 3SE +/- 0.14, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 316.9317.0315.7315.7317.181. (CXX) g++ options: -O3 -march=native -flto -std=c++11

SQLite Speedtest

Timed Time - Size 1,000

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.2816243240SE +/- 0.17, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 0.22, N = 3SE +/- 0.30, N = 334.7736.0734.2334.7336.021. (CC) gcc options: -O3 -march=native -flto -lz

KTX-Software toktx

Settings: UASTC 3

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.21.12122.24243.36364.48485.606SE +/- 0.004, N = 3SE +/- 0.025, N = 3SE +/- 0.005, N = 3SE +/- 0.006, N = 3SE +/- 0.005, N = 34.9574.9824.9584.9614.983

KTX-Software toktx

Settings: Zstd Compression 19

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 19AOCC 4.0LLVM Clang 14GCC 12.2GCC 13.0 14 NovLLVM Clang 15.0.23691215SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 311.3511.6411.6911.6211.46

Phoronix Test Suite v10.8.5