RTX 4070 SUPER

Intel Core i9-13900K testing with a ASUS TUF GAMING Z790-PRO WIFI (1401 BIOS) and NVIDIA GeForce RTX 4070 Ti 12GB on EndeavourOS rolling via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2402070-SADD-240129900&grs&sro.

RTX 4070 SUPERProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLCompilerFile-SystemScreen ResolutionNVIDIA RTX 4070 SUPERNVIDIA RTX 4070NVIDIA RTX 4070 TIIntel Core i9-13900K @ 5.50GHz (24 Cores / 32 Threads)ASUS TUF GAMING Z790-PRO WIFI (1401 BIOS)Intel Device 7a2732GB4001GB Seagate ZP4000GP304001ASUS NVIDIA GeForce RTX 4070 SUPER 12GBRealtek ALC1220ARZOPAIntel I226-V + Intel Device 7a70EndeavourOS rolling6.7.1-arch1-1 (x86_64)KDE Plasma 5.27.10X Server 1.21.1.11NVIDIA 550.40.074.6.0OpenCL 3.0 CUDA 12.4.74GCC 13.2.1 20230801ext41920x1080MSI NVIDIA GeForce RTX 4070 12GBGCC 13.2.1 20230801 + CUDA 12.3NVIDIA GeForce RTX 4070 Ti 12GBOpenBenchmarking.orgKernel Details- Transparent Huge Pages: alwaysCompiler Details- --disable-libssp --disable-libstdcxx-pch --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=ada,c,c++,d,fortran,go,lto,objc,obj-c++ --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-build-config=bootstrap-lto --with-linker-hash-style=gnu Processor Details- Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x11dGraphics Details- NVIDIA RTX 4070 SUPER: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.04.69.00.c1- NVIDIA RTX 4070: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.04.3e.40.2a- NVIDIA RTX 4070 TI: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.04.31.00.36Security Details- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected Environment Details- NVIDIA RTX 4070, NVIDIA RTX 4070 TI: NVCC_PREPEND_FLAGS="-ccbin /opt/cuda/bin"Python Details- NVIDIA RTX 4070, NVIDIA RTX 4070 TI: Python 3.11.6

RTX 4070 SUPERclpeak: Integer Compute INTclpeak: Single-Precision Floathashcat: MD5hashcat: TrueCrypt RIPEMD160 + XTSopencl-benchmark: INT8 Computehashcat: SHA-512gpuowl: 332220523clpeak: Double-Precision Doubleopencl-benchmark: FP64 Computehashcat: SHA1hashcat: 7-Zipviennacl: OpenCL BLAS - dGEMM-TTvkresample: 2x - Doubleopencl-benchmark: FP32 Computegpuowl: 57885161opencl-benchmark: INT32 Computeopencl-benchmark: INT64 Computeviennacl: OpenCL BLAS - dGEMM-TNviennacl: OpenCL BLAS - dGEMM-NTopencl-benchmark: INT16 Computeviennacl: OpenCL BLAS - dGEMM-NNgpuowl: 77936867realsr-ncnn: 4x - Yeslibplacebo: deband_heavylibplacebo: polar_nocomputerodinia: OpenCL Particle Filterluxcorerender: Danish Mood - GPUblender: Fishy Cat - NVIDIA OptiXluxcorerender: LuxCore Benchmark - GPUblender: Classroom - NVIDIA OptiXfahbench: mandelgpu: GPUvkfft: FFT + iFFT C2C Bluestein benchmark in double precisionluxcorerender: Rainbow Colors and Prism - GPUluxcorerender: DLSC - GPUblender: Pabellon Barcelona - NVIDIA OptiXvkfft: FFT + iFFT R2C / C2Rblender: Barbershop - NVIDIA OptiXblender: BMW27 - NVIDIA OptiXluxcorerender: Orange Juice - GPUvkfft: FFT + iFFT C2C 1D batched in double precisionoctanebench: Total Scoreindigobench: OpenCL GPU - Bedroompytorch: NVIDIA CUDA GPU - 16 - ResNet-50waifu2x-ncnn: 2x - 3 - Yespytorch: NVIDIA CUDA GPU - 64 - ResNet-50vkfft: FFT + iFFT C2C Bluestein in single precisionnamd-cuda: ATPase Simulation - 327,506 Atomsindigobench: OpenCL GPU - Supercarpytorch: NVIDIA CUDA GPU - 32 - ResNet-50pytorch: NVIDIA CUDA GPU - 512 - ResNet-50pytorch: NVIDIA CUDA GPU - 256 - ResNet-50vkfft: FFT + iFFT C2C multidimensional in single precisionviennacl: CPU BLAS - dGEMM-TNlibplacebo: hdr_peakdetecttensorflow: GPU - 1 - AlexNetpytorch: NVIDIA CUDA GPU - 32 - ResNet-152pytorch: NVIDIA CUDA GPU - 64 - ResNet-152vkfft: FFT + iFFT C2C 1D batched in single precision, no reshufflingvkfft: FFT + iFFT C2C 1D batched in single precisionviennacl: CPU BLAS - dGEMM-TTvkfft: FFT + iFFT C2C 1D batched in half precisionpytorch: NVIDIA CUDA GPU - 256 - ResNet-152pytorch: NVIDIA CUDA GPU - 16 - ResNet-152viennacl: CPU BLAS - dGEMM-NTviennacl: CPU BLAS - dGEMM-NNpytorch: NVIDIA CUDA GPU - 512 - ResNet-152viennacl: OpenCL BLAS - dAXPYvkresample: 2x - Singletensorflow: GPU - 1 - VGG-16viennacl: OpenCL BLAS - sDOTpytorch: NVIDIA CUDA GPU - 512 - Efficientnet_v2_lpytorch: NVIDIA CUDA GPU - 1 - Efficientnet_v2_lpytorch: NVIDIA CUDA GPU - 256 - Efficientnet_v2_lviennacl: CPU BLAS - sAXPYpytorch: NVIDIA CUDA GPU - 1 - ResNet-152viennacl: OpenCL BLAS - sCOPYviennacl: CPU BLAS - sDOTlibplacebo: hdr_lutlibplacebo: av1_grain_lappytorch: NVIDIA CUDA GPU - 64 - Efficientnet_v2_lcl-mem: Writetensorflow: GPU - 16 - VGG-16tensorflow: GPU - 1 - GoogLeNettensorflow: GPU - 256 - AlexNettensorflow: GPU - 32 - GoogLeNetviennacl: OpenCL BLAS - dGEMV-Tviennacl: OpenCL BLAS - sAXPYviennacl: CPU BLAS - dGEMV-Nopencl-benchmark: Memory Bandwidth Coalesced Writetensorflow: GPU - 512 - AlexNetviennacl: OpenCL BLAS - dGEMV-Ntensorflow: GPU - 32 - ResNet-50cl-mem: Copytensorflow: GPU - 16 - AlexNetviennacl: CPU BLAS - sCOPYviennacl: CPU BLAS - dCOPYtensorflow: GPU - 1 - ResNet-50viennacl: CPU BLAS - dAXPYtensorflow: GPU - 16 - ResNet-50viennacl: OpenCL BLAS - dDOTviennacl: CPU BLAS - dDOTtensorflow: GPU - 64 - AlexNettensorflow: GPU - 64 - ResNet-50tensorflow: GPU - 32 - AlexNettensorflow: GPU - 64 - GoogLeNetviennacl: OpenCL BLAS - dCOPYpytorch: NVIDIA CUDA GPU - 16 - Efficientnet_v2_ltensorflow: GPU - 16 - GoogLeNetclpeak: Global Memory Bandwidthopencl-benchmark: Memory Bandwidth Coalesced Readcl-mem: Readtensorflow: GPU - 256 - VGG-16tensorflow: GPU - 64 - VGG-16tensorflow: GPU - 32 - VGG-16neatbench: GPUncnn: Vulkan GPU - FastestDetncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - mobilenetviennacl: CPU BLAS - dGEMV-Tfinancebench: Black-Scholes OpenCLrealsr-ncnn: 4x - Nopytorch: NVIDIA CUDA GPU - 32 - Efficientnet_v2_lpytorch: NVIDIA CUDA GPU - 1 - ResNet-50NVIDIA RTX 4070 SUPERNVIDIA RTX 4070NVIDIA RTX 4070 TI18170.5435492.696758303333380296714.3073232733333137.44630.110.621221326000001176467613339.59338.594869.0719.8894.21459958417.170577646.4134.8852186.702327.553.48010.569.4512.8212.60366.0576587219538.2445127.6713.5914.295479451.305.5711.7224317720.97378919.801509.452.855507.45151660.0679152.813501.50504.27504.67502991153292.3713.92195.39196.077507873929122131705194.58195.40117119195.3043718.4891.35370103.57106.37103.17156201.943341653905.984171.00102.60407.51.4812.6234.1615.61389392102455.0135.102105.51331.831.5913270.84.3587.25.4645896.833.975.5533.415.5242315.67437.65464.86446.21.5040702.86844.6111.116.8663.8246.2616.178.97117.8111.040.845.073.852.312.253.038.621095.9126.323102.60557.7314555.1928479.395614786666766096712.1162673300000112.61515.170.51018202466667976967502415.16031.768714.8016.3773.44349447714.284473530.3242.8521843.261968.374.0988.8911.0310.9214.86317.1952516770131.2388623.2611.7416.554709758.446.2110.4022390647.99786718.203458.393.168458.36137140.0749848.517459.94459.27459.93472121213329.2614.04187.69186.637905777774118137762187.27187.26122122187.5145518.0161.36362101.43107.59101.24153198.183301663946.904152.41101.55406.71.5012.7815.63387389103459.4335.212095.55330.331.4513171.04.3486.85.4945696.733.935.5533.3215.54423103.6815.66437.21465.18446.31.501.540702.67382.826.215.1820.748.725.785.1145.526.060.843.592.242.082.152.487.201096.9067.092102.90546.7619821.1038691.737331223333385860015.7313462500000145.84667.050.660235324000001262633648322.06440.914919.1321.0474.42063461218.281604676.5933.6262306.562459.033.29110.999.0213.2312.30382.1637619106132.5464727.7113.9513.975544650.735.4311.8925431735.94059320.256502.922.854505.62151250.0678853.589505.55504.66515281253475.0614.79198.82197.027514173942124136210195.86194.29118117194.8743718.4561.38365103.50108.59103.24156201.193361683976.044143.96103.20412.21.4912.7934.6115.81391393103457.1735.442115.50333.331.7013271.34.3287.35.4645796.434.065.5333.2915.50424103.4515.69437.63465.07446.31.51.51.540703.04497.665.896.1316.3712.256.077.7434.497.370.823.464.142.012.092.547.45102.75.2265.96296.50535.39OpenBenchmarking.org

clpeak

OpenCL Test: Integer Compute INT

OpenBenchmarking.orgGIOPS, More Is Betterclpeak 1.1.2OpenCL Test: Integer Compute INTNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI4K8K12K16K20KSE +/- 15.26, N = 3SE +/- 3.14, N = 3SE +/- 2.50, N = 314555.1918170.5419821.101. (CXX) g++ options: -O3

clpeak

OpenCL Test: Single-Precision Float

OpenBenchmarking.orgGFLOPS, More Is Betterclpeak 1.1.2OpenCL Test: Single-Precision FloatNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI8K16K24K32K40KSE +/- 5.46, N = 3SE +/- 0.99, N = 3SE +/- 11.67, N = 328479.3935492.6938691.731. (CXX) g++ options: -O3

Hashcat

Benchmark: MD5

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: MD5NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI16000M32000M48000M64000M80000MSE +/- 33772046.30, N = 3SE +/- 22430807.19, N = 3SE +/- 11283665.68, N = 3561478666676758303333373312233333

Hashcat

Benchmark: TrueCrypt RIPEMD160 + XTS

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: TrueCrypt RIPEMD160 + XTSNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI200K400K600K800K1000KSE +/- 176.38, N = 3SE +/- 633.33, N = 3SE +/- 888.82, N = 3660967802967858600

ProjectPhysX OpenCL-Benchmark

Operation: INT8 Compute

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT8 ComputeNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI48121620SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 312.1214.3115.731. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

Hashcat

Benchmark: SHA-512

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: SHA-512NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI700M1400M2100M2800M3500MSE +/- 1059874.21, N = 3SE +/- 1530068.99, N = 3SE +/- 721110.26, N = 3267330000032327333333462500000

GpuOwl

Exponent: 332220523

OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.2.1Exponent: 332220523NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI306090120150SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3112.61137.44145.84

clpeak

OpenCL Test: Double-Precision Double

OpenBenchmarking.orgGFLOPS, More Is Betterclpeak 1.1.2OpenCL Test: Double-Precision DoubleNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI140280420560700SE +/- 0.21, N = 3SE +/- 0.98, N = 3SE +/- 1.33, N = 3515.17630.11667.051. (CXX) g++ options: -O3

ProjectPhysX OpenCL-Benchmark

Operation: FP64 Compute

OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: FP64 ComputeNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI0.14850.2970.44550.5940.7425SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 30.5100.6210.6601. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

Hashcat

Benchmark: SHA1

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: SHA1NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI5000M10000M15000M20000M25000MSE +/- 6318315.53, N = 3SE +/- 5140363.15, N = 3SE +/- 15926811.78, N = 3182024666672213260000023532400000

Hashcat

Benchmark: 7-Zip

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: 7-ZipNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI300K600K900K1200K1500KSE +/- 2062.63, N = 3SE +/- 1991.93, N = 3SE +/- 2339.04, N = 397696711764671262633

ViennaCL

Test: OpenCL BLAS - dGEMM-TT

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TTNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI140280420560700SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 35026136481. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

VkResample

Upscale: 2x - Precision: Double

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: DoubleNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI90180270360450SE +/- 0.77, N = 3SE +/- 0.30, N = 3SE +/- 0.35, N = 3415.16339.59322.061. (CXX) g++ options: -O3

ProjectPhysX OpenCL-Benchmark

Operation: FP32 Compute

OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: FP32 ComputeNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI918273645SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 331.7738.5940.911. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

GpuOwl

Exponent: 57885161

OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.2.1Exponent: 57885161NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI2004006008001000SE +/- 0.00, N = 3SE +/- 1.26, N = 3SE +/- 2.53, N = 3714.80869.07919.13

ProjectPhysX OpenCL-Benchmark

Operation: INT32 Compute

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT32 ComputeNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI510152025SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 316.3819.8921.051. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

ProjectPhysX OpenCL-Benchmark

Operation: INT64 Compute

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT64 ComputeNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI0.99451.9892.98353.9784.9725SE +/- 0.004, N = 3SE +/- 0.015, N = 3SE +/- 0.016, N = 33.4434.2144.4201. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

ViennaCL

Test: OpenCL BLAS - dGEMM-TN

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TNNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI140280420560700SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.67, N = 34945996341. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: OpenCL BLAS - dGEMM-NT

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NTNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI130260390520650SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 34775846121. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ProjectPhysX OpenCL-Benchmark

Operation: INT16 Compute

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT16 ComputeNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI48121620SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 314.2817.1718.281. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

ViennaCL

Test: OpenCL BLAS - dGEMM-NN

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NNNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI130260390520650SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 34735776041. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

GpuOwl

Exponent: 77936867

OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.2.1Exponent: 77936867NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI150300450600750SE +/- 0.09, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3530.32646.41676.59

RealSR-NCNN

Scale: 4x - TAA: Yes

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI1020304050SE +/- 0.23, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 342.8534.8933.63

Libplacebo

Test: deband_heavy

OpenBenchmarking.orgFPS, More Is BetterLibplacebo 5.229.1Test: deband_heavyNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI5001000150020002500SE +/- 0.12, N = 3SE +/- 2.26, N = 3SE +/- 0.40, N = 31843.262186.702306.561. (CXX) g++ options: -lm -pthread -ldl -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -MD -MQ -MF

Libplacebo

Test: polar_nocompute

OpenBenchmarking.orgFPS, More Is BetterLibplacebo 5.229.1Test: polar_nocomputeNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI5001000150020002500SE +/- 0.01, N = 3SE +/- 0.24, N = 3SE +/- 1.70, N = 31968.372327.552459.031. (CXX) g++ options: -lm -pthread -ldl -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -MD -MQ -MF

Rodinia

Test: OpenCL Particle Filter

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenCL Particle FilterNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI0.92211.84422.76633.68844.6105SE +/- 0.008, N = 3SE +/- 0.039, N = 4SE +/- 0.002, N = 34.0983.4803.2911. (CXX) g++ options: -O2 -lOpenCL

LuxCoreRender

Scene: Danish Mood - Acceleration: GPU

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Danish Mood - Acceleration: GPUNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI3691215SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.11, N = 38.8910.5610.99MIN: 3.32 / MAX: 10.26MIN: 3.7 / MAX: 12.17MIN: 4.17 / MAX: 12.71

Blender

Blend File: Fishy Cat - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Fishy Cat - Compute: NVIDIA OptiXNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI3691215SE +/- 0.03, N = 3SE +/- 0.06, N = 13SE +/- 0.01, N = 311.039.459.02

LuxCoreRender

Scene: LuxCore Benchmark - Acceleration: GPU

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: LuxCore Benchmark - Acceleration: GPUNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI3691215SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 310.9212.8213.23MIN: 4.45 / MAX: 12.42MIN: 4.84 / MAX: 14.62MIN: 5.41 / MAX: 15.13

Blender

Blend File: Classroom - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Classroom - Compute: NVIDIA OptiXNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI48121620SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 314.8612.6012.30

FAHBench

OpenBenchmarking.orgNs Per Day, More Is BetterFAHBench 2.3.2NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI80160240320400SE +/- 0.12, N = 3SE +/- 0.39, N = 3SE +/- 0.26, N = 3317.20366.06382.16

MandelGPU

OpenCL Device: GPU

OpenBenchmarking.orgSamples/sec, More Is BetterMandelGPU 1.3pts1OpenCL Device: GPUNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI130M260M390M520M650MSE +/- 1783157.89, N = 3SE +/- 467034.80, N = 3SE +/- 1202791.77, N = 3516770131.2587219538.2619106132.51. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

VkFFT

Test: FFT + iFFT C2C Bluestein benchmark in double precision

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C Bluestein benchmark in double precisionNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI10002000300040005000SE +/- 4.51, N = 3SE +/- 12.55, N = 3SE +/- 11.35, N = 33886445146471. (CXX) g++ options: -O3 -lrt

LuxCoreRender

Scene: Rainbow Colors and Prism - Acceleration: GPU

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Rainbow Colors and Prism - Acceleration: GPUNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI714212835SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 323.2627.6727.71MIN: 20.92 / MAX: 24.3MIN: 24.87 / MAX: 29.03MIN: 25.01 / MAX: 29.15

LuxCoreRender

Scene: DLSC - Acceleration: GPU

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: GPUNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI48121620SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 311.7413.5913.95MIN: 11.35 / MAX: 11.83MIN: 12.52 / MAX: 13.84MIN: 13.67 / MAX: 14.14

Blender

Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI48121620SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 316.5514.2913.97

VkFFT

Test: FFT + iFFT R2C / C2R

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT R2C / C2RNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI12K24K36K48K60KSE +/- 745.02, N = 13SE +/- 702.53, N = 15SE +/- 520.37, N = 34709754794554461. (CXX) g++ options: -O3 -lrt

Blender

Blend File: Barbershop - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Barbershop - Compute: NVIDIA OptiXNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI1326395265SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.05, N = 358.4451.3050.73

Blender

Blend File: BMW27 - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: BMW27 - Compute: NVIDIA OptiXNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI246810SE +/- 0.01, N = 3SE +/- 0.06, N = 13SE +/- 0.02, N = 36.215.575.43

LuxCoreRender

Scene: Orange Juice - Acceleration: GPU

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: GPUNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI3691215SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.00, N = 310.4011.7211.89MIN: 8.31 / MAX: 13.9MIN: 9.6 / MAX: 15.44MIN: 9.85 / MAX: 15.88

VkFFT

Test: FFT + iFFT C2C 1D batched in double precision

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C 1D batched in double precisionNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI5K10K15K20K25KSE +/- 125.94, N = 3SE +/- 146.69, N = 3SE +/- 302.46, N = 32239024317254311. (CXX) g++ options: -O3 -lrt

OctaneBench

Total Score

OpenBenchmarking.orgScore, More Is BetterOctaneBench 2020.1Total ScoreNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI160320480640800648.00720.97735.94

IndigoBench

Acceleration: OpenCL GPU - Scene: Bedroom

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: BedroomNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI510152025SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 318.2019.8020.26

PyTorch

Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-50

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-50NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI110220330440550SE +/- 0.26, N = 3SE +/- 2.23, N = 3458.39509.45502.92MIN: 404.5 / MAX: 461.01MIN: 430.1 / MAX: 516.48MIN: 415.65 / MAX: 520.39

Waifu2x-NCNN Vulkan

Scale: 2x - Denoise: 3 - TAA: Yes

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: YesNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI0.71281.42562.13842.85123.564SE +/- 0.028, N = 3SE +/- 0.014, N = 3SE +/- 0.009, N = 33.1682.8552.854

PyTorch

Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-50

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-50NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI110220330440550SE +/- 0.27, N = 3SE +/- 0.92, N = 3SE +/- 1.92, N = 3458.36507.45505.62MIN: 404.89 / MAX: 461.01MIN: 423.41 / MAX: 512.88MIN: 426.6 / MAX: 513.25

VkFFT

Test: FFT + iFFT C2C Bluestein in single precision

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C Bluestein in single precisionNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI3K6K9K12K15KSE +/- 52.09, N = 3SE +/- 102.52, N = 3SE +/- 118.41, N = 31371415166151251. (CXX) g++ options: -O3 -lrt

NAMD CUDA

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD CUDA 2.14ATPase Simulation - 327,506 AtomsNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI0.01690.03380.05070.06760.0845SE +/- 0.00021, N = 3SE +/- 0.00031, N = 3SE +/- 0.00061, N = 30.074980.067910.06788

IndigoBench

Acceleration: OpenCL GPU - Scene: Supercar

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: SupercarNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI1224364860SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 348.5252.8153.59

PyTorch

Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-50

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-50NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI110220330440550SE +/- 0.13, N = 2SE +/- 2.17, N = 2SE +/- 1.69, N = 3459.94501.50505.55MIN: 403.65 / MAX: 462.59MIN: 415.94 / MAX: 510.69MIN: 419.93 / MAX: 512.69

PyTorch

Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-50

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-50NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI110220330440550SE +/- 0.43, N = 2SE +/- 4.43, N = 2SE +/- 0.83, N = 2459.27504.27504.66MIN: 405.48 / MAX: 461.88MIN: 418.22 / MAX: 512.44MIN: 424.27 / MAX: 509.08

PyTorch

Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-50

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-50NVIDIA RTX 4070NVIDIA RTX 4070 SUPER110220330440550SE +/- 0.34, N = 3SE +/- 1.39, N = 3459.93504.67MIN: 403.65 / MAX: 462.74MIN: 412.34 / MAX: 514.07

VkFFT

Test: FFT + iFFT C2C multidimensional in single precision

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C multidimensional in single precisionNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI11K22K33K44K55KSE +/- 476.57, N = 5SE +/- 407.19, N = 15SE +/- 417.77, N = 154721250299515281. (CXX) g++ options: -O3 -lrt

ViennaCL

Test: CPU BLAS - dGEMM-TN

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TNNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI306090120150SE +/- 2.31, N = 3SE +/- 1.00, N = 2SE +/- 2.08, N = 31211151251. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Libplacebo

Test: hdr_peakdetect

OpenBenchmarking.orgFPS, More Is BetterLibplacebo 5.229.1Test: hdr_peakdetectNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI8001600240032004000SE +/- 11.75, N = 3SE +/- 3.65, N = 3SE +/- 165.74, N = 33310.023292.373475.061. (CXX) g++ options: -lm -pthread -ldl -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -MD -MQ -MF

TensorFlow

Device: GPU - Batch Size: 1 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 1 - Model: AlexNetNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI48121620SE +/- 0.16, N = 3SE +/- 0.22, N = 2SE +/- 0.06, N = 214.0413.9214.79

PyTorch

Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-152NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI4080120160200187.69195.39198.82MIN: 182.03 / MAX: 188.31MIN: 183.94 / MAX: 198.7MIN: 188.33 / MAX: 201.47

PyTorch

Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-152NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI4080120160200SE +/- 0.34, N = 3SE +/- 0.51, N = 3SE +/- 0.78, N = 2186.63196.07197.02MIN: 180.51 / MAX: 187.79MIN: 171.95 / MAX: 199.96MIN: 183.92 / MAX: 200.54

VkFFT

Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C 1D batched in single precision, no reshufflingNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI20K40K60K80K100KSE +/- 5.84, N = 3SE +/- 37.77, N = 3SE +/- 28.54, N = 37905775078751411. (CXX) g++ options: -O3 -lrt

VkFFT

Test: FFT + iFFT C2C 1D batched in single precision

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C 1D batched in single precisionNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI17K34K51K68K85KSE +/- 13.72, N = 3SE +/- 7.94, N = 3SE +/- 0.88, N = 37777473929739421. (CXX) g++ options: -O3 -lrt

ViennaCL

Test: CPU BLAS - dGEMM-TT

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TTNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI306090120150SE +/- 1.20, N = 3SE +/- 2.08, N = 3SE +/- 2.08, N = 31181221241. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

VkFFT

Test: FFT + iFFT C2C 1D batched in half precision

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C 1D batched in half precisionNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI30K60K90K120K150KSE +/- 1301.92, N = 3SE +/- 159.17, N = 3SE +/- 1708.38, N = 31377621317051362101. (CXX) g++ options: -O3 -lrt

PyTorch

Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-152NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI4080120160200SE +/- 0.17, N = 3SE +/- 1.14, N = 2SE +/- 0.19, N = 2187.27194.58195.86MIN: 179.9 / MAX: 188.08MIN: 183.74 / MAX: 198.52MIN: 181.64 / MAX: 199.2

PyTorch

Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-152NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI4080120160200SE +/- 0.29, N = 3187.26195.40194.29MIN: 179.81 / MAX: 188.21MIN: 186.09 / MAX: 197.7MIN: 182.25 / MAX: 197.39

ViennaCL

Test: CPU BLAS - dGEMM-NT

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NTNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI306090120150SE +/- 1.76, N = 3SE +/- 2.08, N = 3SE +/- 1.20, N = 31221171181. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - dGEMM-NN

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NNNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI306090120150SE +/- 1.86, N = 3SE +/- 4.04, N = 3SE +/- 1.15, N = 31221191171. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

PyTorch

Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-152NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI4080120160200SE +/- 0.05, N = 3SE +/- 1.38, N = 2187.51195.30194.87MIN: 181.57 / MAX: 188.05MIN: 182 / MAX: 199.43MIN: 180.8 / MAX: 198

ViennaCL

Test: OpenCL BLAS - dAXPY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dAXPYNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI100200300400500SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 34554374371. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

VkResample

Upscale: 2x - Precision: Single

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: SingleNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI510152025SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 318.0218.4918.461. (CXX) g++ options: -O3

TensorFlow

Device: GPU - Batch Size: 1 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 1 - Model: VGG-16NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI0.31050.6210.93151.2421.5525SE +/- 0.01, N = 2SE +/- 0.01, N = 31.361.351.38

ViennaCL

Test: OpenCL BLAS - sDOT

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sDOTNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI80160240320400SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33623703651. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

PyTorch

Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: Efficientnet_v2_lNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI20406080100SE +/- 0.39, N = 3SE +/- 0.36, N = 2101.43103.57103.50MIN: 93.27 / MAX: 103.58MIN: 95.95 / MAX: 105.54MIN: 94.95 / MAX: 105.61

PyTorch

Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: Efficientnet_v2_lNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI20406080100SE +/- 0.55, N = 3107.59106.37108.59MIN: 98.77 / MAX: 109.43MIN: 97.91 / MAX: 108.16MIN: 99.04 / MAX: 110.68

PyTorch

Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: Efficientnet_v2_lNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI20406080100SE +/- 0.05, N = 2101.24103.17103.24MIN: 93.33 / MAX: 102.92MIN: 95.79 / MAX: 105.15MIN: 95.41 / MAX: 104.9

ViennaCL

Test: CPU BLAS - sAXPY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sAXPYNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI306090120150SE +/- 4.81, N = 3SE +/- 2.19, N = 3SE +/- 2.00, N = 31531561561. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

PyTorch

Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-152NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI4080120160200SE +/- 0.36, N = 3SE +/- 0.73, N = 3198.18201.94201.19MIN: 181.27 / MAX: 200.06MIN: 183.53 / MAX: 206.5MIN: 180.79 / MAX: 203.92

ViennaCL

Test: OpenCL BLAS - sCOPY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sCOPYNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI70140210280350SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 33303343361. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - sDOT

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sDOTNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI4080120160200SE +/- 3.76, N = 3SE +/- 2.73, N = 3SE +/- 2.40, N = 31661651681. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Libplacebo

Test: hdr_lut

OpenBenchmarking.orgFPS, More Is BetterLibplacebo 5.229.1Test: hdr_lutNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI9001800270036004500SE +/- 10.06, N = 3SE +/- 12.09, N = 3SE +/- 5.47, N = 33927.113905.983971.611. (CXX) g++ options: -lm -pthread -ldl -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -MD -MQ -MF

Libplacebo

Test: av1_grain_lap

OpenBenchmarking.orgFPS, More Is BetterLibplacebo 5.229.1Test: av1_grain_lapNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI9001800270036004500SE +/- 66.69, N = 3SE +/- 5.52, N = 3SE +/- 21.66, N = 34103.404171.004140.871. (CXX) g++ options: -lm -pthread -ldl -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -MD -MQ -MF

PyTorch

Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: Efficientnet_v2_lNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI20406080100SE +/- 0.45, N = 3SE +/- 1.49, N = 2SE +/- 0.39, N = 2101.55102.60103.20MIN: 93.44 / MAX: 103.08MIN: 79.69 / MAX: 105.28MIN: 95.31 / MAX: 105.27

cl-mem

Benchmark: Write

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI90180270360450SE +/- 0.55, N = 3SE +/- 1.11, N = 3SE +/- 0.12, N = 3406.7407.5412.21. (CC) gcc options: -O2 -flto -lOpenCL

TensorFlow

Device: GPU - Batch Size: 16 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 16 - Model: VGG-16NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI0.33750.6751.01251.351.6875SE +/- 0.01, N = 2SE +/- 0.00, N = 21.501.481.49

TensorFlow

Device: GPU - Batch Size: 1 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 1 - Model: GoogLeNetNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI3691215SE +/- 0.10, N = 3SE +/- 0.17, N = 2SE +/- 0.30, N = 212.7812.6212.79

TensorFlow

Device: GPU - Batch Size: 256 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 256 - Model: AlexNetNVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI816243240SE +/- 0.01, N = 3SE +/- 0.07, N = 234.1634.61

TensorFlow

Device: GPU - Batch Size: 32 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 32 - Model: GoogLeNetNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI48121620SE +/- 0.03, N = 3SE +/- 0.01, N = 2SE +/- 0.03, N = 315.6315.6115.81

ViennaCL

Test: OpenCL BLAS - dGEMV-T

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-TNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI80160240320400SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 33873893911. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: OpenCL BLAS - sAXPY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sAXPYNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI90180270360450SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33893923931. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - dGEMV-N

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-NNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI20406080100SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 31031021031. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ProjectPhysX OpenCL-Benchmark

Operation: Memory Bandwidth Coalesced Write

OpenBenchmarking.orgGB/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: Memory Bandwidth Coalesced WriteNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI100200300400500SE +/- 0.16, N = 3SE +/- 0.14, N = 3SE +/- 0.11, N = 3459.43455.01457.171. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

TensorFlow

Device: GPU - Batch Size: 512 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 512 - Model: AlexNetNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI816243240SE +/- 0.03, N = 3SE +/- 0.02, N = 2SE +/- 0.09, N = 235.2135.1035.44

ViennaCL

Test: OpenCL BLAS - dGEMV-N

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-NNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI50100150200250SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 32092102111. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

TensorFlow

Device: GPU - Batch Size: 32 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 32 - Model: ResNet-50NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI1.24882.49763.74644.99526.244SE +/- 0.01, N = 2SE +/- 0.01, N = 2SE +/- 0.02, N = 35.555.515.50

cl-mem

Benchmark: Copy

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI70140210280350SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3330.3331.8333.31. (CC) gcc options: -O2 -flto -lOpenCL

TensorFlow

Device: GPU - Batch Size: 16 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 16 - Model: AlexNetNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI714212835SE +/- 0.17, N = 3SE +/- 0.08, N = 331.4531.5931.70

ViennaCL

Test: CPU BLAS - sCOPY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sCOPYNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI306090120150SE +/- 1.20, N = 3SE +/- 1.20, N = 3SE +/- 0.88, N = 31311321321. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - dCOPY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dCOPYNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI1632486480SE +/- 0.25, N = 3SE +/- 0.32, N = 3SE +/- 0.74, N = 371.070.871.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

TensorFlow

Device: GPU - Batch Size: 1 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 1 - Model: ResNet-50NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI0.97881.95762.93643.91524.894SE +/- 0.01, N = 3SE +/- 0.02, N = 24.344.354.32

ViennaCL

Test: CPU BLAS - dAXPY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dAXPYNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI20406080100SE +/- 0.44, N = 3SE +/- 0.12, N = 3SE +/- 0.57, N = 386.887.287.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

TensorFlow

Device: GPU - Batch Size: 16 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 16 - Model: ResNet-50NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI1.23532.47063.70594.94126.1765SE +/- 0.02, N = 3SE +/- 0.00, N = 2SE +/- 0.01, N = 35.495.465.46

ViennaCL

Test: OpenCL BLAS - dDOT

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dDOTNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI100200300400500SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 34564584571. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - dDOT

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dDOTNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI20406080100SE +/- 0.22, N = 3SE +/- 0.09, N = 3SE +/- 0.58, N = 396.796.896.41. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

TensorFlow

Device: GPU - Batch Size: 64 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 64 - Model: AlexNetNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI816243240SE +/- 0.14, N = 3SE +/- 0.06, N = 333.9333.9734.06

TensorFlow

Device: GPU - Batch Size: 64 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 64 - Model: ResNet-50NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI1.24882.49763.74644.99526.244SE +/- 0.00, N = 3SE +/- 0.01, N = 2SE +/- 0.01, N = 25.555.555.53

TensorFlow

Device: GPU - Batch Size: 32 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 32 - Model: AlexNetNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI816243240SE +/- 0.18, N = 3SE +/- 0.15, N = 2SE +/- 0.04, N = 333.3233.4033.29

TensorFlow

Device: GPU - Batch Size: 64 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 64 - Model: GoogLeNetNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI48121620SE +/- 0.07, N = 3SE +/- 0.06, N = 215.5415.5215.50

ViennaCL

Test: OpenCL BLAS - dCOPY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dCOPYNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI90180270360450SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 34234234241. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

PyTorch

Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: Efficientnet_v2_lNVIDIA RTX 4070NVIDIA RTX 4070 TI20406080100SE +/- 0.52, N = 2103.68103.45MIN: 96.86 / MAX: 105.56MIN: 95.22 / MAX: 105.88

TensorFlow

Device: GPU - Batch Size: 16 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 16 - Model: GoogLeNetNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI48121620SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 315.6615.6715.69

clpeak

OpenCL Test: Global Memory Bandwidth

OpenBenchmarking.orgGBPS, More Is Betterclpeak 1.1.2OpenCL Test: Global Memory BandwidthNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI90180270360450SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3437.21437.65437.631. (CXX) g++ options: -O3

ProjectPhysX OpenCL-Benchmark

Operation: Memory Bandwidth Coalesced Read

OpenBenchmarking.orgGB/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: Memory Bandwidth Coalesced ReadNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI100200300400500SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3465.18464.86465.071. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

cl-mem

Benchmark: Read

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI100200300400500SE +/- 0.00, N = 3SE +/- 0.12, N = 3SE +/- 0.00, N = 3446.3446.2446.31. (CC) gcc options: -O2 -flto -lOpenCL

TensorFlow

Device: GPU - Batch Size: 256 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 256 - Model: VGG-16NVIDIA RTX 4070 TI0.33750.6751.01251.351.68751.5

TensorFlow

Device: GPU - Batch Size: 64 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 64 - Model: VGG-16NVIDIA RTX 4070NVIDIA RTX 4070 TI0.33750.6751.01251.351.6875SE +/- 0.00, N = 3SE +/- 0.00, N = 31.501.50

TensorFlow

Device: GPU - Batch Size: 32 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 32 - Model: VGG-16NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI0.33750.6751.01251.351.6875SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 21.501.501.50

NeatBench

Acceleration: GPU

OpenBenchmarking.orgFPS, More Is BetterNeatBench 5Acceleration: GPUNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI9001800270036004500SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3407040704070

NCNN

Target: Vulkan GPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: FastestDetNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI0.6841.3682.0522.7363.42SE +/- 0.10, N = 9SE +/- 0.29, N = 9SE +/- 0.12, N = 82.342.862.84MIN: 2 / MAX: 3.86MIN: 2.17 / MAX: 577.17MIN: 2.4 / MAX: 5.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vision_transformerNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI2004006008001000SE +/- 61.31, N = 9SE +/- 87.53, N = 9SE +/- 25.65, N = 9281.56844.61390.18MIN: 46.48 / MAX: 1913.33MIN: 46.34 / MAX: 1866.93MIN: 46.49 / MAX: 1816.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: regnety_400mNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI3691215SE +/- 0.24, N = 12SE +/- 3.28, N = 9SE +/- 0.18, N = 126.2111.115.89MIN: 5.53 / MAX: 8.99MIN: 5.49 / MAX: 4942.19MIN: 5.42 / MAX: 7.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: squeezenet_ssdNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI246810SE +/- 0.12, N = 12SE +/- 1.76, N = 9SE +/- 0.29, N = 95.186.865.36MIN: 4.67 / MAX: 6.88MIN: 4.34 / MAX: 1630.01MIN: 4.55 / MAX: 496.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: yolov4-tinyNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI1428425670SE +/- 5.37, N = 12SE +/- 10.56, N = 9SE +/- 3.10, N = 1220.7463.8216.37MIN: 10.3 / MAX: 854.36MIN: 10.28 / MAX: 858.44MIN: 10.57 / MAX: 855.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet50NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI1020304050SE +/- 0.10, N = 9SE +/- 14.70, N = 9SE +/- 4.00, N = 128.2446.2612.25MIN: 7.87 / MAX: 9.87MIN: 7.71 / MAX: 1829.99MIN: 8 / MAX: 1777.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: alexnetNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI48121620SE +/- 1.70, N = 12SE +/- 5.86, N = 9SE +/- 0.03, N = 95.7816.173.74MIN: 3.6 / MAX: 397.75MIN: 3.52 / MAX: 436.52MIN: 3.61 / MAX: 3.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet18NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI3691215SE +/- 0.73, N = 12SE +/- 3.49, N = 9SE +/- 1.33, N = 95.118.975.47MIN: 3.99 / MAX: 916.69MIN: 3.94 / MAX: 922.04MIN: 3.95 / MAX: 726.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vgg16NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI306090120150SE +/- 13.24, N = 12SE +/- 29.60, N = 9SE +/- 11.81, N = 945.52117.8132.05MIN: 17.49 / MAX: 643.35MIN: 17.16 / MAX: 647.67MIN: 17.34 / MAX: 644.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: googlenetNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI3691215SE +/- 0.14, N = 9SE +/- 1.21, N = 9SE +/- 0.14, N = 96.0611.045.87MIN: 5.33 / MAX: 8.36MIN: 5.28 / MAX: 1769.19MIN: 5.2 / MAX: 6.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: blazefaceNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI0.1890.3780.5670.7560.945SE +/- 0.03, N = 9SE +/- 0.04, N = 9SE +/- 0.03, N = 90.840.840.81MIN: 0.64 / MAX: 0.96MIN: 0.65 / MAX: 4.63MIN: 0.61 / MAX: 1.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: efficientnet-b0NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI1.14082.28163.42244.56325.704SE +/- 0.09, N = 9SE +/- 0.97, N = 9SE +/- 0.07, N = 123.465.073.46MIN: 2.91 / MAX: 3.79MIN: 3.22 / MAX: 1124.2MIN: 3.13 / MAX: 7.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mnasnetNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI0.93151.8632.79453.7264.6575SE +/- 0.08, N = 8SE +/- 1.31, N = 9SE +/- 0.05, N = 92.223.852.30MIN: 1.83 / MAX: 2.54MIN: 1.89 / MAX: 1093.29MIN: 2.15 / MAX: 2.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: shufflenet-v2NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI0.51981.03961.55942.07922.599SE +/- 0.09, N = 11SE +/- 0.34, N = 8SE +/- 0.08, N = 122.082.312.01MIN: 1.82 / MAX: 2.59MIN: 1.76 / MAX: 421.42MIN: 1.73 / MAX: 3.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI246810SE +/- 0.08, N = 12SE +/- 0.16, N = 9SE +/- 0.09, N = 92.152.252.09MIN: 1.81 / MAX: 2.58MIN: 1.75 / MAX: 343.7MIN: 1.78 / MAX: 2.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI1.05532.11063.16594.22125.2765SE +/- 0.07, N = 12SE +/- 0.44, N = 9SE +/- 0.07, N = 92.483.032.43MIN: 2.02 / MAX: 5.82MIN: 2.38 / MAX: 970.87MIN: 2.09 / MAX: 5.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mobilenetNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI3691215SE +/- 0.21, N = 12SE +/- 0.47, N = 9SE +/- 0.25, N = 127.208.627.45MIN: 6.2 / MAX: 11.13MIN: 6.42 / MAX: 1101.3MIN: 6.87 / MAX: 734.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

ViennaCL

Test: CPU BLAS - dGEMV-T

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-TNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI20406080100SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 6.30, N = 3109.0109.0102.71. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

FinanceBench

Benchmark: Black-Scholes OpenCL

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Black-Scholes OpenCLNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI246810SE +/- 0.003, N = 3SE +/- 0.114, N = 15SE +/- 0.003, N = 36.9065.9125.2261. (CXX) g++ options: -O3 -march=native -fopenmp

RealSR-NCNN

Scale: 4x - TAA: No

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI246810SE +/- 0.006, N = 3SE +/- 0.150, N = 15SE +/- 0.039, N = 37.0926.3235.962

PyTorch

Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: Efficientnet_v2_lNVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI20406080100SE +/- 6.65, N = 5102.90102.6096.50MIN: 95.98 / MAX: 104.54MIN: 94.84 / MAX: 104.25MIN: 64.35 / MAX: 104.79

PyTorch

Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-50

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-50NVIDIA RTX 4070NVIDIA RTX 4070 SUPERNVIDIA RTX 4070 TI120240360480600SE +/- 3.09, N = 3SE +/- 11.16, N = 12546.76557.73535.39MIN: 195.25 / MAX: 556.94MIN: 513.63 / MAX: 563.37MIN: 428.43 / MAX: 572.99


Phoronix Test Suite v10.8.5