RTX 4070 SUPER Intel Core i9-13900K testing with a ASUS TUF GAMING Z790-PRO WIFI (1630 BIOS) and ASUS NVIDIA GeForce RTX 4070 Ti SUPER 16GB on EndeavourOS rolling via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2402174-SADD-240211636&sro&grr .
RTX 4070 SUPER Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Compiler File-System Screen Resolution NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 NVIDIA RTX 4070 TI NVIDIA RTX 3090 NVIDIA RTX 4070 TI SUPER Intel Core i9-13900K @ 5.50GHz (24 Cores / 32 Threads) ASUS TUF GAMING Z790-PRO WIFI (1401 BIOS) Intel Device 7a27 32GB 4001GB Seagate ZP4000GP304001 ASUS NVIDIA GeForce RTX 4070 SUPER 12GB Realtek ALC1220 ARZOPA Intel I226-V + Intel Device 7a70 EndeavourOS rolling 6.7.1-arch1-1 (x86_64) KDE Plasma 5.27.10 X Server 1.21.1.11 NVIDIA 550.40.07 4.6.0 OpenCL 3.0 CUDA 12.4.74 GCC 13.2.1 20230801 ext4 1920x1080 MSI NVIDIA GeForce RTX 4070 12GB GCC 13.2.1 20230801 + CUDA 12.3 NVIDIA GeForce RTX 4070 Ti 12GB NVIDIA GeForce RTX 3090 24GB PI-KVM Video 6.7.4-arch1-1 (x86_64) ASUS TUF GAMING Z790-PRO WIFI (1630 BIOS) Intel Raptor Lake-S PCH 4001GB Seagate ZP4000GP304001 + 0GB CD-ROM Drive ASUS NVIDIA GeForce RTX 4070 Ti SUPER 16GB Intel I226-V + Intel Raptor Lake-S PCH CNVi WiFi OpenCL 2.1 AMD-APP (3602.0) + OpenCL 3.0 CUDA 12.4.74 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: always Compiler Details - NVIDIA RTX 4070 SUPER: --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 - NVIDIA RTX 4070: --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 - NVIDIA RTX 4070 TI: --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 - NVIDIA RTX 3090: --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,m2,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 - NVIDIA RTX 4070 TI SUPER: --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,m2,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 - NVIDIA RTX 4070 SUPER: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x11d - NVIDIA RTX 4070: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x11d - NVIDIA RTX 4070 TI: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x11d - NVIDIA RTX 3090: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x11d - NVIDIA RTX 4070 TI SUPER: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x11f Graphics 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: 95.04.31.00.36 - NVIDIA RTX 3090: BAR1 / Visible vRAM Size: 256 MiB - vBIOS Version: 94.02.26.08.ba - NVIDIA RTX 4070 TI SUPER: BAR1 / Visible vRAM Size: 256 MiB - vBIOS Version: 95.03.45.00.c5 Security 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, NVIDIA RTX 3090, NVIDIA RTX 4070 TI SUPER: NVCC_PREPEND_FLAGS="-ccbin /opt/cuda/bin" Python Details - NVIDIA RTX 4070: Python 3.11.6 - NVIDIA RTX 4070 TI: Python 3.11.6 - NVIDIA RTX 3090: Python 3.11.6 - NVIDIA RTX 4070 TI SUPER: Python 3.11.7
RTX 4070 SUPER tensorflow: GPU - 256 - VGG-16 tensorflow: GPU - 64 - VGG-16 tensorflow: GPU - 32 - VGG-16 tensorflow: GPU - 512 - AlexNet tensorflow: GPU - 64 - ResNet-50 tensorflow: GPU - 16 - VGG-16 tensorflow: GPU - 256 - AlexNet tensorflow: GPU - 32 - ResNet-50 ncnn: Vulkan GPU - FastestDet ncnn: Vulkan GPU - vision_transformer ncnn: Vulkan GPU - regnety_400m ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU - yolov4-tiny ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - vgg16 ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU - mobilenet ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 tensorflow: GPU - 64 - GoogLeNet tensorflow: GPU - 16 - ResNet-50 vkpeak: int16-vec4 vkpeak: int16-scalar vkpeak: int32-vec4 vkpeak: int32-scalar vkpeak: fp64-vec4 vkpeak: fp64-scalar vkpeak: fp16-vec4 vkpeak: fp16-scalar vkpeak: fp32-vec4 vkpeak: fp32-scalar tensorflow: GPU - 32 - GoogLeNet tensorflow: GPU - 64 - AlexNet gpuowl: 77936867 gpuowl: 332220523 octanebench: Total Score gpuowl: 57885161 tensorflow: GPU - 16 - GoogLeNet vkfft: FFT + iFFT C2C multidimensional in single precision vkfft: FFT + iFFT C2C Bluestein benchmark in double precision luxcorerender: DLSC - GPU tensorflow: GPU - 32 - AlexNet fahbench: vkresample: 2x - Double indigobench: OpenCL GPU - Bedroom vkfft: FFT + iFFT C2C 1D batched in double precision indigobench: OpenCL GPU - Supercar luxcorerender: Orange Juice - GPU tensorflow: GPU - 1 - VGG-16 luxcorerender: LuxCore Benchmark - GPU vkfft: FFT + iFFT C2C Bluestein in single precision luxcorerender: Danish Mood - GPU vkfft: FFT + iFFT R2C / C2R blender: Barbershop - NVIDIA OptiX vkfft: FFT + iFFT C2C 1D batched in single precision vkfft: FFT + iFFT C2C 1D batched in single precision, no reshuffling tensorflow: GPU - 16 - AlexNet vkfft: FFT + iFFT C2C 1D batched in half precision libplacebo: av1_grain_lap libplacebo: hdr_lut libplacebo: hdr_peakdetect libplacebo: polar_nocompute libplacebo: deband_heavy realsr-ncnn: 4x - Yes blender: Fishy Cat - NVIDIA OptiX tensorflow: GPU - 1 - AlexNet pytorch: NVIDIA CUDA GPU - 32 - Efficientnet_v2_l namd-cuda: ATPase Simulation - 327,506 Atoms tensorflow: GPU - 1 - ResNet-50 pytorch: NVIDIA CUDA GPU - 64 - Efficientnet_v2_l pytorch: NVIDIA CUDA GPU - 512 - Efficientnet_v2_l viennacl: CPU BLAS - dGEMM-TT viennacl: CPU BLAS - dGEMM-TN viennacl: CPU BLAS - dGEMM-NT viennacl: CPU BLAS - dGEMM-NN viennacl: CPU BLAS - dGEMV-T viennacl: CPU BLAS - dGEMV-N viennacl: CPU BLAS - dDOT viennacl: CPU BLAS - dAXPY viennacl: CPU BLAS - dCOPY viennacl: CPU BLAS - sDOT viennacl: CPU BLAS - sAXPY viennacl: CPU BLAS - sCOPY pytorch: NVIDIA CUDA GPU - 256 - Efficientnet_v2_l viennacl: OpenCL BLAS - dGEMM-TT viennacl: OpenCL BLAS - dGEMM-TN viennacl: OpenCL BLAS - dGEMM-NT viennacl: OpenCL BLAS - dGEMM-NN viennacl: OpenCL BLAS - dGEMV-T viennacl: OpenCL BLAS - dGEMV-N viennacl: OpenCL BLAS - dDOT viennacl: OpenCL BLAS - dAXPY viennacl: OpenCL BLAS - dCOPY viennacl: OpenCL BLAS - sDOT viennacl: OpenCL BLAS - sAXPY viennacl: OpenCL BLAS - sCOPY blender: BMW27 - NVIDIA OptiX pytorch: NVIDIA CUDA GPU - 16 - Efficientnet_v2_l blender: Pabellon Barcelona - NVIDIA OptiX blender: Classroom - NVIDIA OptiX opencl-benchmark: Memory Bandwidth Coalesced Write opencl-benchmark: Memory Bandwidth Coalesced Read opencl-benchmark: INT8 Compute opencl-benchmark: INT16 Compute opencl-benchmark: INT32 Compute opencl-benchmark: INT64 Compute opencl-benchmark: FP32 Compute opencl-benchmark: FP64 Compute pytorch: NVIDIA CUDA GPU - 512 - ResNet-152 pytorch: NVIDIA CUDA GPU - 64 - ResNet-152 pytorch: NVIDIA CUDA GPU - 256 - ResNet-152 realsr-ncnn: 4x - No pytorch: NVIDIA CUDA GPU - 32 - ResNet-152 pytorch: NVIDIA CUDA GPU - 1 - Efficientnet_v2_l tensorflow: GPU - 1 - GoogLeNet pytorch: NVIDIA CUDA GPU - 16 - ResNet-152 vkresample: 2x - Single clpeak: Double-Precision Double luxcorerender: Rainbow Colors and Prism - GPU pytorch: NVIDIA CUDA GPU - 64 - ResNet-50 pytorch: NVIDIA CUDA GPU - 1 - ResNet-50 hashcat: MD5 hashcat: SHA1 hashcat: SHA-512 pytorch: NVIDIA CUDA GPU - 1 - ResNet-152 pytorch: NVIDIA CUDA GPU - 256 - ResNet-50 rodinia: OpenCL Particle Filter pytorch: NVIDIA CUDA GPU - 16 - ResNet-50 pytorch: NVIDIA CUDA GPU - 512 - ResNet-50 pytorch: NVIDIA CUDA GPU - 32 - ResNet-50 hashcat: TrueCrypt RIPEMD160 + XTS cl-mem: Copy cl-mem: Write cl-mem: Read hashcat: 7-Zip waifu2x-ncnn: 2x - 3 - Yes clpeak: Global Memory Bandwidth mandelgpu: GPU financebench: Black-Scholes OpenCL neatbench: GPU clpeak: Integer Compute INT clpeak: Single-Precision Float arrayfire: Conjugate Gradient OpenCL NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 NVIDIA RTX 4070 TI NVIDIA RTX 3090 NVIDIA RTX 4070 TI SUPER 1.50 35.10 5.55 1.48 34.16 5.51 2.86 844.61 11.11 6.86 63.82 46.26 16.17 8.97 117.81 5.07 3.85 2.31 3.03 8.62 11.04 0.84 2.25 15.52 5.46 15.61 33.97 646.41 137.44 720.973789 869.07 15.67 50299 4451 13.59 33.4 366.0576 339.593 19.801 24317 52.813 11.72 1.35 12.82 15166 10.56 54794 51.30 73929 75078 31.59 131705 4171.00 3905.98 3292.37 2327.55 2186.70 34.885 9.45 13.92 102.60 0.06791 4.35 102.60 103.57 122 115 117 119 109 102 96.8 87.2 70.8 165 156 132 103.17 613 599 584 577 389 210 458 437 423 370 392 334 5.57 14.29 12.60 455.01 464.86 14.307 17.170 19.889 4.214 38.594 0.621 195.30 196.07 194.58 6.323 195.39 106.37 12.62 195.40 18.489 630.11 27.67 507.45 557.73 67583033333 22132600000 3232733333 201.94 504.67 3.480 509.45 504.27 501.50 802967 331.8 407.5 446.2 1176467 2.855 437.65 587219538.2 5.912 4070 18170.54 35492.69 1.50 1.5 35.21 5.55 1.50 5.55 2.67 382.82 6.21 5.18 20.74 8.72 5.78 5.11 45.52 3.59 2.24 2.08 2.48 7.20 6.06 0.84 2.15 15.54 5.49 15.63 33.93 530.32 112.61 647.997867 714.80 15.66 47212 3886 11.74 33.32 317.1952 415.160 18.203 22390 48.517 10.40 1.36 10.92 13714 8.89 47097 58.44 77774 79057 31.45 137762 4152.41 3946.90 3329.26 1968.37 1843.26 42.852 11.03 14.04 102.90 0.07498 4.34 101.55 101.43 118 121 122 122 109 103 96.7 86.8 71.0 166 153 131 101.24 502 494 477 473 387 209 456 455 423 362 389 330 6.21 103.68 16.55 14.86 459.43 465.18 12.116 14.284 16.377 3.443 31.768 0.510 187.51 186.63 187.27 7.092 187.69 107.59 12.78 187.26 18.016 515.17 23.26 458.36 546.76 56147866667 18202466667 2673300000 198.18 459.93 4.098 458.39 459.27 459.94 660967 330.3 406.7 446.3 976967 3.168 437.21 516770131.2 6.906 4070 14555.19 28479.39 1.5 1.5 1.5 35.44 5.53 1.49 34.61 5.50 3.04 497.66 5.89 6.13 16.37 12.25 6.07 7.74 34.49 3.46 4.14 2.01 2.54 7.45 7.37 0.82 2.09 15.50 5.46 15.81 34.06 676.59 145.84 735.940593 919.13 15.69 51528 4647 13.95 33.29 382.1637 322.064 20.256 25431 53.589 11.89 1.38 13.23 15125 10.99 55446 50.73 73942 75141 31.70 136210 4143.96 3976.04 3475.06 2459.03 2306.56 33.626 9.02 14.79 96.50 0.06788 4.32 103.20 103.50 124 125 118 117 102.7 103 96.4 87.3 71.3 168 156 132 103.24 648 634 612 604 391 211 457 437 424 365 393 336 5.43 103.45 13.97 12.30 457.17 465.07 15.731 18.281 21.047 4.420 40.914 0.660 194.87 197.02 195.86 5.962 198.82 108.59 12.79 194.29 18.456 667.05 27.71 505.62 535.39 73312233333 23532400000 3462500000 201.19 3.291 502.92 504.66 505.55 858600 333.3 412.2 446.3 1262633 2.854 437.63 619106132.5 5.226 4070 19821.10 38691.73 1.51 1.51 1.5 35.58 5.57 1.49 34.46 5.57 2.65 354.57 6.73 4.90 11.29 12.70 3.60 4.12 17.88 3.34 2.16 2.04 2.34 7.27 6.14 0.87 2.21 15.63 5.49 16329.72 13264.91 20009.73 20295.27 638.74 638.84 39860.80 20151.44 26699.66 20353.95 15.67 33.93 645.99 137.32 674.250912 866.31 15.68 50856 4195 12.99 33.53 343.0199 333.639 20.959 30912 52.014 12.14 1.38 13.12 14205 10.20 48418 54.30 141876 144311 31.98 273221 4100.36 3369.88 5055.88 2116.79 2020.16 30.313 10.64 14.45 99.05 0.10822 4.35 99.84 99.25 113 121 119 113 110 103 95.2 86.2 70.2 132.1 154 132 99.43 593 594 595 592 374 187 659 724 605 376 498 363 6.31 98.11 17.30 15.26 887.31 864.11 13.727 17.001 20.027 3.135 39.395 0.637 164.35 164.14 161.01 5.556 163.74 105.55 12.82 164.14 10.323 642.23 33.29 419.03 525.12 67177300000 21323733333 3081866667 197.12 416.89 3.844 419.76 416.20 420.29 797833 360.8 753.8 825.8 1056000 3.202 816.55 484098913.8 5.741 3090 17923.33 34906.79 1.47 1.46 1.46 35.02 5.33 1.45 33.95 5.35 2.55 312.10 6.59 5.19 17.20 8.79 4.41 7.58 24.85 3.48 2.26 2.13 2.70 7.48 6.46 0.88 2.16 15.00 5.32 21156.99 15901.32 23768.27 23888.02 750.68 750.49 47340.52 23894.70 31635.47 23920.67 15.11 33.55 761.61 163.41 876.436994 1025.99 15.29 59790 5047 16.23 32.88 394.7356 285.988 24.570 27947 61.338 13.64 1.32 14.61 16141 12.42 59378 44.49 104003 105549 31.10 143992 4044.72 3822.16 3913.34 2653.03 2495.92 30.724 8.32 12.26 102.83 0.07715 4.14 103.49 103.53 117 120 119 122 82.6 78.5 70.8 64.3 52.7 129 120 107 102.83 731 714 689 681 424 218 575 585 512 410 469 373 5.04 103.66 12.56 11.20 608.94 619.03 17.615 20.503 23.660 4.414 45.950 0.743 198.01 196.50 198.70 5.633 197.82 105.86 12.24 198.58 13.363 750.36 31.86 527.82 558.82 82004966667 26388600000 3887033333 200.46 529.14 2.973 531.96 529.49 532.77 961733 370.7 551.9 595.2 1420700 2.660 582.84 656484783.7 0.501 2084.1 22171.25 43244.79 OpenBenchmarking.org
TensorFlow Device: GPU - Batch Size: 256 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: GPU - Batch Size: 256 - Model: VGG-16 NVIDIA RTX 3090 NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 0.3398 0.6796 1.0194 1.3592 1.699 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.51 1.50 1.47
TensorFlow Device: GPU - Batch Size: 64 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: GPU - Batch Size: 64 - Model: VGG-16 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 0.3398 0.6796 1.0194 1.3592 1.699 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.51 1.50 1.50 1.46
TensorFlow Device: GPU - Batch Size: 32 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: GPU - Batch Size: 32 - Model: VGG-16 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 0.3375 0.675 1.0125 1.35 1.6875 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 2 SE +/- 0.00, N = 3 1.50 1.50 1.50 1.50 1.46
TensorFlow Device: GPU - Batch Size: 512 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: GPU - Batch Size: 512 - Model: AlexNet NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 8 16 24 32 40 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 2 SE +/- 0.09, N = 2 SE +/- 0.01, N = 3 35.58 35.21 35.10 35.44 35.02
TensorFlow Device: GPU - Batch Size: 64 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: GPU - Batch Size: 64 - Model: ResNet-50 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 1.2533 2.5066 3.7599 5.0132 6.2665 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 2 SE +/- 0.01, N = 2 SE +/- 0.02, N = 3 5.57 5.55 5.55 5.53 5.33
TensorFlow Device: GPU - Batch Size: 16 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: GPU - Batch Size: 16 - Model: VGG-16 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 0.3375 0.675 1.0125 1.35 1.6875 SE +/- 0.00, N = 3 SE +/- 0.01, N = 2 SE +/- 0.00, N = 2 SE +/- 0.00, N = 3 1.49 1.50 1.48 1.49 1.45
TensorFlow Device: GPU - Batch Size: 256 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: GPU - Batch Size: 256 - Model: AlexNet NVIDIA RTX 3090 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 8 16 24 32 40 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 2 SE +/- 0.05, N = 3 34.46 34.16 34.61 33.95
TensorFlow Device: GPU - Batch Size: 32 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: GPU - Batch Size: 32 - Model: ResNet-50 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 1.2533 2.5066 3.7599 5.0132 6.2665 SE +/- 0.01, N = 3 SE +/- 0.01, N = 2 SE +/- 0.01, N = 2 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 5.57 5.55 5.51 5.50 5.35
NCNN Target: Vulkan GPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: FastestDet NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 2 4 6 8 10 SE +/- 0.08, N = 8 SE +/- 0.10, N = 9 SE +/- 0.29, N = 9 SE +/- 0.12, N = 8 SE +/- 0.26, N = 3 2.50 2.34 2.86 2.84 2.54 MIN: 2.1 / MAX: 32.36 MIN: 2 / MAX: 3.86 MIN: 2.17 / MAX: 577.17 MIN: 2.4 / MAX: 5.07 MIN: 2.14 / MAX: 4.21 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vision_transformer NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 200 400 600 800 1000 SE +/- 52.80, N = 9 SE +/- 61.31, N = 9 SE +/- 87.53, N = 9 SE +/- 25.65, N = 9 SE +/- 57.46, N = 12 327.82 281.56 844.61 390.18 312.10 MIN: 46.48 / MAX: 1816.93 MIN: 46.48 / MAX: 1913.33 MIN: 46.34 / MAX: 1866.93 MIN: 46.49 / MAX: 1816.77 MIN: 47.85 / MAX: 1850.09 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: regnety_400m NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 3 6 9 12 15 SE +/- 0.32, N = 8 SE +/- 0.24, N = 12 SE +/- 3.28, N = 9 SE +/- 0.18, N = 12 SE +/- 0.26, N = 12 6.47 6.21 11.11 5.89 6.59 MIN: 5.44 / MAX: 9.3 MIN: 5.53 / MAX: 8.99 MIN: 5.49 / MAX: 4942.19 MIN: 5.42 / MAX: 7.57 MIN: 5.45 / MAX: 9.09 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: squeezenet_ssd NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 2 4 6 8 10 SE +/- 0.19, N = 3 SE +/- 0.12, N = 12 SE +/- 1.76, N = 9 SE +/- 0.29, N = 9 SE +/- 0.54, N = 3 4.90 5.18 6.86 5.36 5.11 MIN: 4.47 / MAX: 5.27 MIN: 4.67 / MAX: 6.88 MIN: 4.34 / MAX: 1630.01 MIN: 4.55 / MAX: 496.3 MIN: 4.43 / MAX: 8.4 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: yolov4-tiny NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 14 28 42 56 70 SE +/- 0.21, N = 3 SE +/- 5.37, N = 12 SE +/- 10.56, N = 9 SE +/- 3.10, N = 12 SE +/- 3.14, N = 3 11.29 20.74 63.82 16.37 14.26 MIN: 10.82 / MAX: 11.93 MIN: 10.3 / MAX: 854.36 MIN: 10.28 / MAX: 858.44 MIN: 10.57 / MAX: 855.36 MIN: 10.89 / MAX: 673.37 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet50 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 10 20 30 40 50 SE +/- 0.12, N = 9 SE +/- 0.10, N = 9 SE +/- 14.70, N = 9 SE +/- 4.00, N = 12 SE +/- 0.22, N = 3 8.20 8.24 46.26 12.25 8.58 MIN: 7.69 / MAX: 11.69 MIN: 7.87 / MAX: 9.87 MIN: 7.71 / MAX: 1829.99 MIN: 8 / MAX: 1777.17 MIN: 8.2 / MAX: 11.07 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: alexnet NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 4 8 12 16 20 SE +/- 0.09, N = 3 SE +/- 1.70, N = 12 SE +/- 5.86, N = 9 SE +/- 0.03, N = 9 SE +/- 0.03, N = 3 3.60 5.78 16.17 3.74 4.38 MIN: 3.44 / MAX: 3.79 MIN: 3.6 / MAX: 397.75 MIN: 3.52 / MAX: 436.52 MIN: 3.61 / MAX: 3.98 MIN: 4.29 / MAX: 6.18 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet18 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 4 8 12 16 20 SE +/- 0.07, N = 3 SE +/- 0.73, N = 12 SE +/- 3.49, N = 9 SE +/- 1.33, N = 9 SE +/- 0.08, N = 3 4.12 5.11 8.97 5.47 4.64 MIN: 3.97 / MAX: 4.51 MIN: 3.99 / MAX: 916.69 MIN: 3.94 / MAX: 922.04 MIN: 3.95 / MAX: 726.67 MIN: 4.46 / MAX: 7.98 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vgg16 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 30 60 90 120 150 SE +/- 0.25, N = 3 SE +/- 13.24, N = 12 SE +/- 29.60, N = 9 SE +/- 11.81, N = 9 SE +/- 0.19, N = 3 17.88 45.52 117.81 32.05 21.76 MIN: 17.3 / MAX: 18.57 MIN: 17.49 / MAX: 643.35 MIN: 17.16 / MAX: 647.67 MIN: 17.34 / MAX: 644.35 MIN: 21.34 / MAX: 23.45 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: efficientnet-b0 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 4 8 12 16 20 SE +/- 0.17, N = 3 SE +/- 0.09, N = 9 SE +/- 0.97, N = 9 SE +/- 0.07, N = 12 SE +/- 0.07, N = 3 3.34 3.46 5.07 3.46 3.36 MIN: 3.14 / MAX: 4 MIN: 2.91 / MAX: 3.79 MIN: 3.22 / MAX: 1124.2 MIN: 3.13 / MAX: 7.03 MIN: 3.21 / MAX: 3.57 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mnasnet NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 0.9315 1.863 2.7945 3.726 4.6575 SE +/- 0.14, N = 3 SE +/- 0.08, N = 8 SE +/- 1.31, N = 9 SE +/- 0.05, N = 9 SE +/- 0.13, N = 3 2.16 2.22 3.85 2.30 2.21 MIN: 2.01 / MAX: 2.55 MIN: 1.83 / MAX: 2.54 MIN: 1.89 / MAX: 1093.29 MIN: 2.15 / MAX: 2.58 MIN: 2.01 / MAX: 3.93 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: shufflenet-v2 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 0.9383 1.8766 2.8149 3.7532 4.6915 SE +/- 0.21, N = 3 SE +/- 0.09, N = 11 SE +/- 0.34, N = 8 SE +/- 0.08, N = 12 SE +/- 0.19, N = 3 2.04 2.08 2.31 2.01 2.05 MIN: 1.8 / MAX: 5.8 MIN: 1.82 / MAX: 2.59 MIN: 1.76 / MAX: 421.42 MIN: 1.73 / MAX: 3.86 MIN: 1.83 / MAX: 6.6 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 1.0553 2.1106 3.1659 4.2212 5.2765 SE +/- 0.15, N = 3 SE +/- 0.07, N = 12 SE +/- 0.44, N = 9 SE +/- 0.07, N = 9 SE +/- 0.09, N = 3 2.34 2.48 3.03 2.43 2.42 MIN: 2.04 / MAX: 2.63 MIN: 2.02 / MAX: 5.82 MIN: 2.38 / MAX: 970.87 MIN: 2.09 / MAX: 5.8 MIN: 2.24 / MAX: 9.23 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mobilenet NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 3 6 9 12 15 SE +/- 0.22, N = 9 SE +/- 0.21, N = 12 SE +/- 0.47, N = 9 SE +/- 0.25, N = 12 SE +/- 0.05, N = 3 6.92 7.20 8.62 7.45 6.28 MIN: 6.06 / MAX: 8.65 MIN: 6.2 / MAX: 11.13 MIN: 6.42 / MAX: 1101.3 MIN: 6.87 / MAX: 734.65 MIN: 6.16 / MAX: 8.09 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: googlenet NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 3 6 9 12 15 SE +/- 0.18, N = 9 SE +/- 0.14, N = 9 SE +/- 1.21, N = 9 SE +/- 0.14, N = 9 SE +/- 0.24, N = 3 6.11 6.06 11.04 5.87 6.25 MIN: 5.25 / MAX: 9.16 MIN: 5.33 / MAX: 8.36 MIN: 5.28 / MAX: 1769.19 MIN: 5.2 / MAX: 6.88 MIN: 5.84 / MAX: 6.86 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: blazeface NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 0.198 0.396 0.594 0.792 0.99 SE +/- 0.03, N = 9 SE +/- 0.03, N = 9 SE +/- 0.04, N = 9 SE +/- 0.03, N = 9 SE +/- 0.05, N = 3 0.84 0.84 0.84 0.81 0.86 MIN: 0.63 / MAX: 1.13 MIN: 0.64 / MAX: 0.96 MIN: 0.65 / MAX: 4.63 MIN: 0.61 / MAX: 1.19 MIN: 0.75 / MAX: 2.68 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 2 4 6 8 10 SE +/- 0.09, N = 9 SE +/- 0.08, N = 12 SE +/- 0.16, N = 9 SE +/- 0.09, N = 9 SE +/- 0.02, N = 3 2.20 2.15 2.25 2.09 1.87 MIN: 1.91 / MAX: 2.71 MIN: 1.81 / MAX: 2.58 MIN: 1.75 / MAX: 343.7 MIN: 1.78 / MAX: 2.85 MIN: 1.81 / MAX: 5.21 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
TensorFlow Device: GPU - Batch Size: 64 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: GPU - Batch Size: 64 - Model: GoogLeNet NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 4 8 12 16 20 SE +/- 0.08, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 2 SE +/- 0.09, N = 3 15.63 15.54 15.52 15.50 15.00
TensorFlow Device: GPU - Batch Size: 16 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: GPU - Batch Size: 16 - Model: ResNet-50 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 1.2353 2.4706 3.7059 4.9412 6.1765 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 2 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 5.49 5.49 5.46 5.46 5.32
vkpeak int16-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20230730 int16-vec4 NVIDIA RTX 3090 NVIDIA RTX 4070 TI SUPER 5K 10K 15K 20K 25K SE +/- 28.77, N = 3 SE +/- 3.02, N = 3 16302.58 21124.09
vkpeak int16-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20230730 int16-scalar NVIDIA RTX 3090 NVIDIA RTX 4070 TI SUPER 3K 6K 9K 12K 15K SE +/- 23.55, N = 3 SE +/- 22.68, N = 3 13225.17 15859.37
vkpeak int32-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20230730 int32-vec4 NVIDIA RTX 3090 NVIDIA RTX 4070 TI SUPER 5K 10K 15K 20K 25K SE +/- 2.34, N = 3 SE +/- 34.76, N = 3 19996.92 23733.30
vkpeak int32-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20230730 int32-scalar NVIDIA RTX 3090 NVIDIA RTX 4070 TI SUPER 5K 10K 15K 20K 25K SE +/- 3.21, N = 3 SE +/- 0.36, N = 3 20280.33 23874.85
vkpeak fp64-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp64-vec4 NVIDIA RTX 3090 NVIDIA RTX 4070 TI SUPER 160 320 480 640 800 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 638.72 749.76
vkpeak fp64-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp64-scalar NVIDIA RTX 3090 NVIDIA RTX 4070 TI SUPER 160 320 480 640 800 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 638.70 750.47
vkpeak fp16-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp16-vec4 NVIDIA RTX 3090 NVIDIA RTX 4070 TI SUPER 10K 20K 30K 40K 50K SE +/- 75.11, N = 3 SE +/- 76.15, N = 3 39746.91 47192.56
vkpeak fp16-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp16-scalar NVIDIA RTX 3090 NVIDIA RTX 4070 TI SUPER 5K 10K 15K 20K 25K SE +/- 34.71, N = 3 SE +/- 34.93, N = 3 20080.47 23825.05
vkpeak fp32-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp32-vec4 NVIDIA RTX 3090 NVIDIA RTX 4070 TI SUPER 7K 14K 21K 28K 35K SE +/- 1.51, N = 3 SE +/- 43.84, N = 3 26563.72 31591.71
vkpeak fp32-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp32-scalar NVIDIA RTX 3090 NVIDIA RTX 4070 TI SUPER 5K 10K 15K 20K 25K SE +/- 36.15, N = 3 SE +/- 38.13, N = 3 20263.13 23883.53
TensorFlow Device: GPU - Batch Size: 32 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: GPU - Batch Size: 32 - Model: GoogLeNet NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 2 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 15.67 15.63 15.61 15.81 15.11
TensorFlow Device: GPU - Batch Size: 64 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: GPU - Batch Size: 64 - Model: AlexNet NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 8 16 24 32 40 SE +/- 0.08, N = 3 SE +/- 0.14, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 33.93 33.93 33.97 34.06 33.55
GpuOwl Exponent: 77936867 OpenBenchmarking.org Iterations / Second, More Is Better GpuOwl 7.2.1 Exponent: 77936867 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 160 320 480 640 800 SE +/- 0.00, N = 3 SE +/- 0.09, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 645.99 530.32 646.41 676.59 761.61
GpuOwl Exponent: 332220523 OpenBenchmarking.org Iterations / Second, More Is Better GpuOwl 7.2.1 Exponent: 332220523 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 40 80 120 160 200 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 137.32 112.61 137.44 145.84 163.41
OctaneBench Total Score OpenBenchmarking.org Score, More Is Better OctaneBench 2020.1 Total Score NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 200 400 600 800 1000 674.25 648.00 720.97 735.94 876.44
GpuOwl Exponent: 57885161 OpenBenchmarking.org Iterations / Second, More Is Better GpuOwl 7.2.1 Exponent: 57885161 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 200 400 600 800 1000 SE +/- 2.01, N = 3 SE +/- 0.00, N = 3 SE +/- 1.26, N = 3 SE +/- 2.53, N = 3 SE +/- 0.35, N = 3 866.31 714.80 869.07 919.13 1025.99
TensorFlow Device: GPU - Batch Size: 16 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: GPU - Batch Size: 16 - Model: GoogLeNet NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 15.68 15.66 15.67 15.69 15.29
VkFFT Test: FFT + iFFT C2C multidimensional in single precision OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C multidimensional in single precision NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 13K 26K 39K 52K 65K SE +/- 407.28, N = 15 SE +/- 476.57, N = 5 SE +/- 407.19, N = 15 SE +/- 417.77, N = 15 SE +/- 251.10, N = 3 50856 47212 50299 51528 59790 1. (CXX) g++ options: -O3 -lrt
VkFFT Test: FFT + iFFT C2C Bluestein benchmark in double precision OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C Bluestein benchmark in double precision NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 1100 2200 3300 4400 5500 SE +/- 9.84, N = 3 SE +/- 4.51, N = 3 SE +/- 12.55, N = 3 SE +/- 11.35, N = 3 SE +/- 11.37, N = 3 4195 3886 4451 4647 5047 1. (CXX) g++ options: -O3 -lrt
LuxCoreRender Scene: DLSC - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: DLSC - Acceleration: GPU NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 4 8 12 16 20 SE +/- 1.13, N = 12 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 12.99 11.74 13.59 13.95 16.23 MIN: 0.52 / MAX: 14.69 MIN: 11.35 / MAX: 11.83 MIN: 12.52 / MAX: 13.84 MIN: 13.67 / MAX: 14.14 MIN: 15.91 / MAX: 16.36
TensorFlow Device: GPU - Batch Size: 32 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: GPU - Batch Size: 32 - Model: AlexNet NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 8 16 24 32 40 SE +/- 0.05, N = 3 SE +/- 0.18, N = 3 SE +/- 0.15, N = 2 SE +/- 0.04, N = 3 SE +/- 0.19, N = 3 33.53 33.32 33.40 33.29 32.88
FAHBench OpenBenchmarking.org Ns Per Day, More Is Better FAHBench 2.3.2 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 90 180 270 360 450 SE +/- 0.26, N = 3 SE +/- 0.12, N = 3 SE +/- 0.39, N = 3 SE +/- 0.26, N = 3 SE +/- 0.22, N = 3 343.02 317.20 366.06 382.16 394.74
VkResample Upscale: 2x - Precision: Double OpenBenchmarking.org ms, Fewer Is Better VkResample 1.0 Upscale: 2x - Precision: Double NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 90 180 270 360 450 SE +/- 0.30, N = 3 SE +/- 0.77, N = 3 SE +/- 0.30, N = 3 SE +/- 0.35, N = 3 SE +/- 0.02, N = 3 333.64 415.16 339.59 322.06 285.99 1. (CXX) g++ options: -O3
IndigoBench Acceleration: OpenCL GPU - Scene: Bedroom OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Bedroom NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 6 12 18 24 30 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 20.96 18.20 19.80 20.26 24.57
VkFFT Test: FFT + iFFT C2C 1D batched in double precision OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C 1D batched in double precision NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 7K 14K 21K 28K 35K SE +/- 50.66, N = 3 SE +/- 125.94, N = 3 SE +/- 146.69, N = 3 SE +/- 302.46, N = 3 SE +/- 325.03, N = 3 30912 22390 24317 25431 27947 1. (CXX) g++ options: -O3 -lrt
IndigoBench Acceleration: OpenCL GPU - Scene: Supercar OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Supercar NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 14 28 42 56 70 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 52.01 48.52 52.81 53.59 61.34
LuxCoreRender Scene: Orange Juice - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Orange Juice - Acceleration: GPU NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.00, N = 3 SE +/- 0.15, N = 4 12.14 10.40 11.72 11.89 13.64 MIN: 10.24 / MAX: 16.71 MIN: 8.31 / MAX: 13.9 MIN: 9.6 / MAX: 15.44 MIN: 9.85 / MAX: 15.88 MIN: 11.16 / MAX: 18.46
TensorFlow Device: GPU - Batch Size: 1 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: GPU - Batch Size: 1 - Model: VGG-16 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 0.3105 0.621 0.9315 1.242 1.5525 SE +/- 0.01, N = 3 SE +/- 0.01, N = 2 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 1.38 1.36 1.35 1.38 1.32
LuxCoreRender Scene: LuxCore Benchmark - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: LuxCore Benchmark - Acceleration: GPU NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 4 8 12 16 20 SE +/- 0.03, N = 2 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 13.12 10.92 12.82 13.23 14.61 MIN: 4.85 / MAX: 15.21 MIN: 4.45 / MAX: 12.42 MIN: 4.84 / MAX: 14.62 MIN: 5.41 / MAX: 15.13 MIN: 5.91 / MAX: 16.88
VkFFT Test: FFT + iFFT C2C Bluestein in single precision OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C Bluestein in single precision NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 3K 6K 9K 12K 15K SE +/- 115.62, N = 3 SE +/- 52.09, N = 3 SE +/- 102.52, N = 3 SE +/- 118.41, N = 3 SE +/- 73.00, N = 3 14205 13714 15166 15125 16141 1. (CXX) g++ options: -O3 -lrt
LuxCoreRender Scene: Danish Mood - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Danish Mood - Acceleration: GPU NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 SE +/- 0.11, N = 3 SE +/- 0.03, N = 3 10.20 8.89 10.56 10.99 12.42 MIN: 4.07 / MAX: 11.93 MIN: 3.32 / MAX: 10.26 MIN: 3.7 / MAX: 12.17 MIN: 4.17 / MAX: 12.71 MIN: 4.35 / MAX: 14.32
VkFFT Test: FFT + iFFT R2C / C2R OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.2.31 Test: FFT + iFFT R2C / C2R NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 13K 26K 39K 52K 65K SE +/- 320.62, N = 3 SE +/- 745.02, N = 13 SE +/- 702.53, N = 15 SE +/- 520.37, N = 3 SE +/- 772.47, N = 15 48418 47097 54794 55446 59378 1. (CXX) g++ options: -O3 -lrt
Blender Blend File: Barbershop - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.0 Blend File: Barbershop - Compute: NVIDIA OptiX NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 13 26 39 52 65 SE +/- 0.02, N = 2 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 54.30 58.44 51.30 50.73 44.49
VkFFT Test: FFT + iFFT C2C 1D batched in single precision OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C 1D batched in single precision NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 30K 60K 90K 120K 150K SE +/- 9.64, N = 3 SE +/- 13.72, N = 3 SE +/- 7.94, N = 3 SE +/- 0.88, N = 3 SE +/- 33.60, N = 3 141876 77774 73929 73942 104003 1. (CXX) g++ options: -O3 -lrt
VkFFT Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 30K 60K 90K 120K 150K SE +/- 37.44, N = 3 SE +/- 5.84, N = 3 SE +/- 37.77, N = 3 SE +/- 28.54, N = 3 SE +/- 20.80, N = 3 144311 79057 75078 75141 105549 1. (CXX) g++ options: -O3 -lrt
TensorFlow Device: GPU - Batch Size: 16 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: GPU - Batch Size: 16 - Model: AlexNet NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 7 14 21 28 35 SE +/- 0.07, N = 3 SE +/- 0.17, N = 3 SE +/- 0.08, N = 3 SE +/- 0.07, N = 3 31.98 31.45 31.59 31.70 31.10
VkFFT Test: FFT + iFFT C2C 1D batched in half precision OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C 1D batched in half precision NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 60K 120K 180K 240K 300K SE +/- 160.60, N = 3 SE +/- 1301.92, N = 3 SE +/- 159.17, N = 3 SE +/- 1708.38, N = 3 SE +/- 3524.05, N = 12 273221 137762 131705 136210 143992 1. (CXX) g++ options: -O3 -lrt
Libplacebo Test: av1_grain_lap OpenBenchmarking.org FPS, More Is Better Libplacebo 5.229.1 Test: av1_grain_lap NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 900 1800 2700 3600 4500 SE +/- 42.82, N = 3 SE +/- 66.69, N = 3 SE +/- 5.52, N = 3 SE +/- 21.66, N = 3 SE +/- 48.74, N = 3 4096.48 4103.40 4171.00 4140.87 4044.72 1. (CXX) g++ options: -lm -pthread -ldl -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -MD -MQ -MF
Libplacebo Test: hdr_lut OpenBenchmarking.org FPS, More Is Better Libplacebo 5.229.1 Test: hdr_lut NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 900 1800 2700 3600 4500 SE +/- 13.62, N = 3 SE +/- 10.06, N = 3 SE +/- 12.09, N = 3 SE +/- 5.47, N = 3 SE +/- 16.37, N = 3 3313.26 3927.11 3905.98 3971.61 3822.16 1. (CXX) g++ options: -lm -pthread -ldl -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -MD -MQ -MF
Libplacebo Test: hdr_peakdetect OpenBenchmarking.org FPS, More Is Better Libplacebo 5.229.1 Test: hdr_peakdetect NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 1100 2200 3300 4400 5500 SE +/- 75.68, N = 3 SE +/- 11.75, N = 3 SE +/- 3.65, N = 3 SE +/- 165.74, N = 3 SE +/- 13.83, N = 3 4969.74 3310.02 3292.37 3475.06 3913.34 1. (CXX) g++ options: -lm -pthread -ldl -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -MD -MQ -MF
Libplacebo Test: polar_nocompute OpenBenchmarking.org FPS, More Is Better Libplacebo 5.229.1 Test: polar_nocompute NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 600 1200 1800 2400 3000 SE +/- 3.16, N = 3 SE +/- 0.01, N = 3 SE +/- 0.24, N = 3 SE +/- 1.70, N = 3 SE +/- 0.38, N = 3 2116.50 1968.37 2327.55 2459.03 2646.70 1. (CXX) g++ options: -lm -pthread -ldl -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -MD -MQ -MF
Libplacebo Test: deband_heavy OpenBenchmarking.org FPS, More Is Better Libplacebo 5.229.1 Test: deband_heavy NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 500 1000 1500 2000 2500 SE +/- 2.90, N = 3 SE +/- 0.12, N = 3 SE +/- 2.26, N = 3 SE +/- 0.40, N = 3 SE +/- 2.22, N = 3 2015.93 1843.26 2186.70 2306.56 2493.29 1. (CXX) g++ options: -lm -pthread -ldl -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -MD -MQ -MF
RealSR-NCNN Scale: 4x - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: Yes NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 10 20 30 40 50 SE +/- 0.06, N = 3 SE +/- 0.23, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 30.31 42.85 34.89 33.63 30.72
Blender Blend File: Fishy Cat - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.0 Blend File: Fishy Cat - Compute: NVIDIA OptiX NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 3 6 9 12 15 SE +/- 0.08, N = 9 SE +/- 0.03, N = 3 SE +/- 0.06, N = 13 SE +/- 0.01, N = 3 SE +/- 0.06, N = 13 10.64 11.03 9.45 9.02 8.32
TensorFlow Device: GPU - Batch Size: 1 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: GPU - Batch Size: 1 - Model: AlexNet NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 4 8 12 16 20 SE +/- 0.20, N = 15 SE +/- 0.16, N = 3 SE +/- 0.22, N = 2 SE +/- 0.06, N = 2 SE +/- 0.13, N = 15 14.45 14.04 13.92 14.79 12.26
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: Efficientnet_v2_l NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 20 40 60 80 100 SE +/- 0.13, N = 3 SE +/- 6.65, N = 5 SE +/- 0.62, N = 3 99.05 102.90 102.60 96.50 102.83 MIN: 91.8 / MAX: 100.69 MIN: 95.98 / MAX: 104.54 MIN: 94.84 / MAX: 104.25 MIN: 64.35 / MAX: 104.79 MIN: 92.44 / MAX: 105.47
NAMD CUDA ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD CUDA 2.14 ATPase Simulation - 327,506 Atoms NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 0.0243 0.0486 0.0729 0.0972 0.1215 SE +/- 0.00042, N = 3 SE +/- 0.00021, N = 3 SE +/- 0.00031, N = 3 SE +/- 0.00061, N = 3 SE +/- 0.00018, N = 3 0.10822 0.07498 0.06791 0.06788 0.07715
TensorFlow Device: GPU - Batch Size: 1 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: GPU - Batch Size: 1 - Model: ResNet-50 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 0.9788 1.9576 2.9364 3.9152 4.894 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 2 SE +/- 0.02, N = 3 4.35 4.34 4.35 4.32 4.14
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: Efficientnet_v2_l NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 20 40 60 80 100 SE +/- 0.14, N = 3 SE +/- 0.45, N = 3 SE +/- 1.49, N = 2 SE +/- 0.39, N = 2 SE +/- 0.13, N = 3 99.84 101.55 102.60 103.20 103.49 MIN: 92.73 / MAX: 101.46 MIN: 93.44 / MAX: 103.08 MIN: 79.69 / MAX: 105.28 MIN: 95.31 / MAX: 105.27 MIN: 93.23 / MAX: 105.43
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: Efficientnet_v2_l NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 20 40 60 80 100 SE +/- 0.19, N = 3 SE +/- 0.39, N = 3 SE +/- 0.36, N = 2 99.25 101.43 103.57 103.50 103.53 MIN: 91.16 / MAX: 101.18 MIN: 93.27 / MAX: 103.58 MIN: 95.95 / MAX: 105.54 MIN: 94.95 / MAX: 105.61 MIN: 88.81 / MAX: 104.8
ViennaCL Test: CPU BLAS - dGEMM-TT OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TT NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 30 60 90 120 150 SE +/- 0.88, N = 3 SE +/- 1.20, N = 3 SE +/- 2.08, N = 3 SE +/- 2.08, N = 3 SE +/- 2.91, N = 3 113 118 122 124 117 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dGEMM-TN OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TN NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 30 60 90 120 150 SE +/- 2.08, N = 3 SE +/- 2.31, N = 3 SE +/- 1.00, N = 2 SE +/- 2.08, N = 3 SE +/- 3.00, N = 2 121 121 115 125 120 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dGEMM-NT OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NT NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 30 60 90 120 150 SE +/- 3.28, N = 3 SE +/- 1.76, N = 3 SE +/- 2.08, N = 3 SE +/- 1.20, N = 3 SE +/- 3.50, N = 2 119 122 117 118 119 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dGEMM-NN OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NN NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 30 60 90 120 150 SE +/- 1.86, N = 3 SE +/- 1.86, N = 3 SE +/- 4.04, N = 3 SE +/- 1.15, N = 3 SE +/- 1.50, N = 2 113 122 119 117 122 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dGEMV-T OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-T NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 20 40 60 80 100 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 6.30, N = 3 SE +/- 0.47, N = 3 110.0 109.0 109.0 102.7 82.6 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dGEMV-N OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-N NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 20 40 60 80 100 SE +/- 0.88, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.46, N = 3 103.0 103.0 102.0 103.0 78.5 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dDOT OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dDOT NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 20 40 60 80 100 SE +/- 0.84, N = 3 SE +/- 0.22, N = 3 SE +/- 0.09, N = 3 SE +/- 0.58, N = 3 SE +/- 0.19, N = 3 95.2 96.7 96.8 96.4 70.8 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dAXPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dAXPY NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 20 40 60 80 100 SE +/- 0.94, N = 3 SE +/- 0.44, N = 3 SE +/- 0.12, N = 3 SE +/- 0.57, N = 3 SE +/- 0.12, N = 3 86.2 86.8 87.2 87.3 64.3 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dCOPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dCOPY NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 16 32 48 64 80 SE +/- 0.72, N = 3 SE +/- 0.25, N = 3 SE +/- 0.32, N = 3 SE +/- 0.74, N = 3 SE +/- 0.18, N = 3 70.2 71.0 70.8 71.3 52.7 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - sDOT OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sDOT NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 40 80 120 160 200 SE +/- 35.40, N = 3 SE +/- 3.76, N = 3 SE +/- 2.73, N = 3 SE +/- 2.40, N = 3 SE +/- 0.58, N = 3 132.1 166.0 165.0 168.0 129.0 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - sAXPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sAXPY NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 30 60 90 120 150 SE +/- 0.33, N = 3 SE +/- 4.81, N = 3 SE +/- 2.19, N = 3 SE +/- 2.00, N = 3 SE +/- 0.33, N = 3 154 153 156 156 120 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - sCOPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sCOPY NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 30 60 90 120 150 SE +/- 1.20, N = 3 SE +/- 1.20, N = 3 SE +/- 1.20, N = 3 SE +/- 0.88, N = 3 SE +/- 0.67, N = 3 132 131 132 132 107 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: Efficientnet_v2_l NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 20 40 60 80 100 SE +/- 0.57, N = 3 SE +/- 0.05, N = 2 SE +/- 0.18, N = 3 99.43 101.24 103.17 103.24 102.83 MIN: 90.49 / MAX: 101.97 MIN: 93.33 / MAX: 102.92 MIN: 95.79 / MAX: 105.15 MIN: 95.41 / MAX: 104.9 MIN: 93.16 / MAX: 105.07
ViennaCL Test: OpenCL BLAS - dGEMM-TT OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TT NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 160 320 480 640 800 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 1.33, N = 3 593 502 613 648 731 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - dGEMM-TN OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TN NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 150 300 450 600 750 SE +/- 2.03, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.67, N = 3 SE +/- 1.00, N = 3 594 494 599 634 714 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - dGEMM-NT OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NT NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 150 300 450 600 750 SE +/- 2.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 1.00, N = 3 595 477 584 612 689 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - dGEMM-NN OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NN NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 150 300 450 600 750 SE +/- 2.31, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 1.33, N = 3 592 473 577 604 681 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - dGEMV-T OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-T NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 90 180 270 360 450 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 374 387 389 391 424 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - dGEMV-N OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-N NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 50 100 150 200 250 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 187 209 210 211 218 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - dDOT OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dDOT NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 140 280 420 560 700 SE +/- 0.88, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 1.33, N = 3 659 456 458 457 575 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - dAXPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dAXPY NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 160 320 480 640 800 SE +/- 0.58, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 724 455 437 437 585 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - dCOPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dCOPY NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 130 260 390 520 650 SE +/- 0.58, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 4.00, N = 3 605 423 423 424 512 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - sDOT OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - sDOT NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 90 180 270 360 450 SE +/- 0.58, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 1.00, N = 3 376 362 370 365 410 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - sAXPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - sAXPY NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 110 220 330 440 550 SE +/- 0.58, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 1.20, N = 3 498 389 392 393 469 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - sCOPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - sCOPY NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 80 160 240 320 400 SE +/- 1.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 363 330 334 336 373 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
Blender Blend File: BMW27 - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.0 Blend File: BMW27 - Compute: NVIDIA OptiX NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 2 4 6 8 10 SE +/- 0.06, N = 14 SE +/- 0.01, N = 3 SE +/- 0.06, N = 13 SE +/- 0.02, N = 3 SE +/- 0.06, N = 14 6.31 6.21 5.57 5.43 5.04
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: Efficientnet_v2_l NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 20 40 60 80 100 SE +/- 0.53, N = 2 SE +/- 0.52, N = 2 SE +/- 0.33, N = 3 98.11 103.68 103.45 103.66 MIN: 89.88 / MAX: 100.25 MIN: 96.86 / MAX: 105.56 MIN: 95.22 / MAX: 105.88 MIN: 93.46 / MAX: 105.95
Blender Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.0 Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 17.30 16.55 14.29 13.97 12.56
Blender Blend File: Classroom - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.0 Blend File: Classroom - Compute: NVIDIA OptiX NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 15.26 14.86 12.60 12.30 11.20
ProjectPhysX OpenCL-Benchmark Operation: Memory Bandwidth Coalesced Write OpenBenchmarking.org GB/s, More Is Better ProjectPhysX OpenCL-Benchmark 1.2 Operation: Memory Bandwidth Coalesced Write NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 200 400 600 800 1000 SE +/- 0.06, N = 3 SE +/- 0.16, N = 3 SE +/- 0.14, N = 3 SE +/- 0.11, N = 3 SE +/- 0.57, N = 3 887.31 459.43 455.01 457.17 608.94 1. (CXX) g++ options: -std=c++17 -pthread -lOpenCL
ProjectPhysX OpenCL-Benchmark Operation: Memory Bandwidth Coalesced Read OpenBenchmarking.org GB/s, More Is Better ProjectPhysX OpenCL-Benchmark 1.2 Operation: Memory Bandwidth Coalesced Read NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 200 400 600 800 1000 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 864.11 465.18 464.86 465.07 619.03 1. (CXX) g++ options: -std=c++17 -pthread -lOpenCL
ProjectPhysX OpenCL-Benchmark Operation: INT8 Compute OpenBenchmarking.org TIOPs/s, More Is Better ProjectPhysX OpenCL-Benchmark 1.2 Operation: INT8 Compute NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 4 8 12 16 20 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 13.73 12.12 14.31 15.73 17.62 1. (CXX) g++ options: -std=c++17 -pthread -lOpenCL
ProjectPhysX OpenCL-Benchmark Operation: INT16 Compute OpenBenchmarking.org TIOPs/s, More Is Better ProjectPhysX OpenCL-Benchmark 1.2 Operation: INT16 Compute NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 5 10 15 20 25 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 17.00 14.28 17.17 18.28 20.50 1. (CXX) g++ options: -std=c++17 -pthread -lOpenCL
ProjectPhysX OpenCL-Benchmark Operation: INT32 Compute OpenBenchmarking.org TIOPs/s, More Is Better ProjectPhysX OpenCL-Benchmark 1.2 Operation: INT32 Compute NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 6 12 18 24 30 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 20.03 16.38 19.89 21.05 23.66 1. (CXX) g++ options: -std=c++17 -pthread -lOpenCL
ProjectPhysX OpenCL-Benchmark Operation: INT64 Compute OpenBenchmarking.org TIOPs/s, More Is Better ProjectPhysX OpenCL-Benchmark 1.2 Operation: INT64 Compute NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 0.9945 1.989 2.9835 3.978 4.9725 SE +/- 0.003, N = 3 SE +/- 0.004, N = 3 SE +/- 0.015, N = 3 SE +/- 0.016, N = 3 SE +/- 0.009, N = 3 3.135 3.443 4.214 4.420 4.414 1. (CXX) g++ options: -std=c++17 -pthread -lOpenCL
ProjectPhysX OpenCL-Benchmark Operation: FP32 Compute OpenBenchmarking.org TFLOPs/s, More Is Better ProjectPhysX OpenCL-Benchmark 1.2 Operation: FP32 Compute NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 10 20 30 40 50 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 39.40 31.77 38.59 40.91 45.95 1. (CXX) g++ options: -std=c++17 -pthread -lOpenCL
ProjectPhysX OpenCL-Benchmark Operation: FP64 Compute OpenBenchmarking.org TFLOPs/s, More Is Better ProjectPhysX OpenCL-Benchmark 1.2 Operation: FP64 Compute NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 0.1672 0.3344 0.5016 0.6688 0.836 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 0.637 0.510 0.621 0.660 0.743 1. (CXX) g++ options: -std=c++17 -pthread -lOpenCL
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-152 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 40 80 120 160 200 SE +/- 0.33, N = 2 SE +/- 0.05, N = 3 SE +/- 1.38, N = 2 SE +/- 0.81, N = 3 164.35 187.51 195.30 194.87 198.01 MIN: 149.91 / MAX: 166.09 MIN: 181.57 / MAX: 188.05 MIN: 182 / MAX: 199.43 MIN: 180.8 / MAX: 198 MIN: 185.3 / MAX: 202.59
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-152 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 40 80 120 160 200 SE +/- 0.34, N = 3 SE +/- 0.51, N = 3 SE +/- 0.78, N = 2 SE +/- 0.20, N = 3 164.14 186.63 196.07 197.02 196.50 MIN: 149 / MAX: 165 MIN: 180.51 / MAX: 187.79 MIN: 171.95 / MAX: 199.96 MIN: 183.92 / MAX: 200.54 MIN: 179.34 / MAX: 200
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-152 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 40 80 120 160 200 SE +/- 0.17, N = 3 SE +/- 1.14, N = 2 SE +/- 0.19, N = 2 SE +/- 0.95, N = 3 161.01 187.27 194.58 195.86 198.70 MIN: 138.12 / MAX: 165.16 MIN: 179.9 / MAX: 188.08 MIN: 183.74 / MAX: 198.52 MIN: 181.64 / MAX: 199.2 MIN: 185.21 / MAX: 203.36
RealSR-NCNN Scale: 4x - TAA: No OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: No NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 2 4 6 8 10 SE +/- 0.016, N = 3 SE +/- 0.006, N = 3 SE +/- 0.150, N = 15 SE +/- 0.039, N = 3 SE +/- 0.003, N = 3 5.556 7.092 6.323 5.962 5.633
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-152 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 40 80 120 160 200 SE +/- 0.29, N = 3 SE +/- 0.28, N = 3 163.74 187.69 195.39 198.82 197.82 MIN: 144.93 / MAX: 165.03 MIN: 182.03 / MAX: 188.31 MIN: 183.94 / MAX: 198.7 MIN: 188.33 / MAX: 201.47 MIN: 176.19 / MAX: 201.63
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: Efficientnet_v2_l NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 20 40 60 80 100 SE +/- 0.33, N = 3 SE +/- 0.55, N = 3 SE +/- 0.24, N = 2 105.55 107.59 106.37 108.59 105.86 MIN: 91.76 / MAX: 107.42 MIN: 98.77 / MAX: 109.43 MIN: 97.91 / MAX: 108.16 MIN: 99.04 / MAX: 110.68 MIN: 95.05 / MAX: 107.6
TensorFlow Device: GPU - Batch Size: 1 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: GPU - Batch Size: 1 - Model: GoogLeNet NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 3 6 9 12 15 SE +/- 0.07, N = 3 SE +/- 0.10, N = 3 SE +/- 0.17, N = 2 SE +/- 0.30, N = 2 SE +/- 0.05, N = 3 12.82 12.78 12.62 12.79 12.24
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-152 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 40 80 120 160 200 SE +/- 0.29, N = 3 SE +/- 0.33, N = 3 164.14 187.26 195.40 194.29 198.58 MIN: 145.67 / MAX: 165.38 MIN: 179.81 / MAX: 188.21 MIN: 186.09 / MAX: 197.7 MIN: 182.25 / MAX: 197.39 MIN: 183.91 / MAX: 201.98
VkResample Upscale: 2x - Precision: Single OpenBenchmarking.org ms, Fewer Is Better VkResample 1.0 Upscale: 2x - Precision: Single NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 5 10 15 20 25 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 10.32 18.02 18.49 18.46 13.36 1. (CXX) g++ options: -O3
clpeak OpenCL Test: Double-Precision Double OpenBenchmarking.org GFLOPS, More Is Better clpeak 1.1.2 OpenCL Test: Double-Precision Double NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 160 320 480 640 800 SE +/- 1.63, N = 3 SE +/- 0.21, N = 3 SE +/- 0.98, N = 3 SE +/- 1.33, N = 3 SE +/- 1.26, N = 3 642.23 515.17 630.11 667.05 750.36 1. (CXX) g++ options: -O3
LuxCoreRender Scene: Rainbow Colors and Prism - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Rainbow Colors and Prism - Acceleration: GPU NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 8 16 24 32 40 SE +/- 0.36, N = 5 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 33.29 23.26 27.67 27.71 31.86 MIN: 30.4 / MAX: 36.21 MIN: 20.92 / MAX: 24.3 MIN: 24.87 / MAX: 29.03 MIN: 25.01 / MAX: 29.15 MIN: 28.57 / MAX: 33.29
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-50 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 110 220 330 440 550 SE +/- 0.24, N = 3 SE +/- 0.27, N = 3 SE +/- 0.92, N = 3 SE +/- 1.92, N = 3 SE +/- 1.58, N = 3 419.03 458.36 507.45 505.62 527.82 MIN: 376 / MAX: 422 MIN: 404.89 / MAX: 461.01 MIN: 423.41 / MAX: 512.88 MIN: 426.6 / MAX: 513.25 MIN: 419.39 / MAX: 534.44
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-50 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 120 240 360 480 600 SE +/- 3.09, N = 3 SE +/- 11.16, N = 12 SE +/- 3.07, N = 3 525.12 546.76 557.73 535.39 558.82 MIN: 458.54 / MAX: 542.46 MIN: 195.25 / MAX: 556.94 MIN: 513.63 / MAX: 563.37 MIN: 428.43 / MAX: 572.99 MIN: 473.77 / MAX: 573.46
Hashcat Benchmark: MD5 OpenBenchmarking.org H/s, More Is Better Hashcat 6.2.4 Benchmark: MD5 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 20000M 40000M 60000M 80000M 100000M SE +/- 53667246.37, N = 3 SE +/- 33772046.30, N = 3 SE +/- 22430807.19, N = 3 SE +/- 11283665.68, N = 3 SE +/- 97655010.68, N = 3 67177300000 56147866667 67583033333 73312233333 82004966667
Hashcat Benchmark: SHA1 OpenBenchmarking.org H/s, More Is Better Hashcat 6.2.4 Benchmark: SHA1 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 6000M 12000M 18000M 24000M 30000M SE +/- 26244639.66, N = 3 SE +/- 6318315.53, N = 3 SE +/- 5140363.15, N = 3 SE +/- 15926811.78, N = 3 SE +/- 29067564.97, N = 3 21323733333 18202466667 22132600000 23532400000 26388600000
Hashcat Benchmark: SHA-512 OpenBenchmarking.org H/s, More Is Better Hashcat 6.2.4 Benchmark: SHA-512 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 800M 1600M 2400M 3200M 4000M SE +/- 3288532.26, N = 3 SE +/- 1059874.21, N = 3 SE +/- 1530068.99, N = 3 SE +/- 721110.26, N = 3 SE +/- 1098989.43, N = 3 3081866667 2673300000 3232733333 3462500000 3887033333
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-152 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 40 80 120 160 200 SE +/- 0.09, N = 2 SE +/- 0.36, N = 3 SE +/- 0.73, N = 3 SE +/- 0.38, N = 3 197.12 198.18 201.94 201.19 200.46 MIN: 137.37 / MAX: 198.9 MIN: 181.27 / MAX: 200.06 MIN: 183.53 / MAX: 206.5 MIN: 180.79 / MAX: 203.92 MIN: 177.25 / MAX: 203.31
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-50 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI SUPER 110 220 330 440 550 SE +/- 0.14, N = 3 SE +/- 0.34, N = 3 SE +/- 1.39, N = 3 SE +/- 0.54, N = 3 416.89 459.93 504.67 529.14 MIN: 329.77 / MAX: 420.82 MIN: 403.65 / MAX: 462.74 MIN: 412.34 / MAX: 514.07 MIN: 414.54 / MAX: 534.65
Rodinia Test: OpenCL Particle Filter OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenCL Particle Filter NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 0.9221 1.8442 2.7663 3.6884 4.6105 SE +/- 0.030, N = 15 SE +/- 0.008, N = 3 SE +/- 0.039, N = 4 SE +/- 0.002, N = 3 SE +/- 0.004, N = 3 3.844 4.098 3.480 3.291 2.973 1. (CXX) g++ options: -O2 -lOpenCL
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-50 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 120 240 360 480 600 SE +/- 0.89, N = 2 SE +/- 0.26, N = 3 SE +/- 2.23, N = 3 SE +/- 1.33, N = 3 419.76 458.39 509.45 502.92 531.96 MIN: 376.2 / MAX: 422.17 MIN: 404.5 / MAX: 461.01 MIN: 430.1 / MAX: 516.48 MIN: 415.65 / MAX: 520.39 MIN: 422.98 / MAX: 539.81
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-50 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 110 220 330 440 550 SE +/- 0.40, N = 3 SE +/- 0.43, N = 2 SE +/- 4.43, N = 2 SE +/- 0.83, N = 2 SE +/- 1.16, N = 3 416.20 459.27 504.27 504.66 529.49 MIN: 355.45 / MAX: 419.05 MIN: 405.48 / MAX: 461.88 MIN: 418.22 / MAX: 512.44 MIN: 424.27 / MAX: 509.08 MIN: 410.12 / MAX: 537.25
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-50 NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 120 240 360 480 600 SE +/- 0.13, N = 2 SE +/- 2.17, N = 2 SE +/- 1.69, N = 3 SE +/- 0.70, N = 3 420.29 459.94 501.50 505.55 532.77 MIN: 376.81 / MAX: 421.58 MIN: 403.65 / MAX: 462.59 MIN: 415.94 / MAX: 510.69 MIN: 419.93 / MAX: 512.69 MIN: 420.31 / MAX: 538.98
Hashcat Benchmark: TrueCrypt RIPEMD160 + XTS OpenBenchmarking.org H/s, More Is Better Hashcat 6.2.4 Benchmark: TrueCrypt RIPEMD160 + XTS NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 200K 400K 600K 800K 1000K SE +/- 1757.21, N = 3 SE +/- 176.38, N = 3 SE +/- 633.33, N = 3 SE +/- 888.82, N = 3 SE +/- 392.99, N = 3 797833 660967 802967 858600 961733
cl-mem Benchmark: Copy OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Copy NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 80 160 240 320 400 SE +/- 0.22, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 360.8 330.3 331.8 333.3 370.7 1. (CC) gcc options: -O2 -flto -lOpenCL
cl-mem Benchmark: Write OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Write NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 160 320 480 640 800 SE +/- 0.83, N = 3 SE +/- 0.55, N = 3 SE +/- 1.11, N = 3 SE +/- 0.12, N = 3 SE +/- 0.25, N = 3 753.8 406.7 407.5 412.2 551.9 1. (CC) gcc options: -O2 -flto -lOpenCL
cl-mem Benchmark: Read OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Read NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 200 400 600 800 1000 SE +/- 0.32, N = 3 SE +/- 0.00, N = 3 SE +/- 0.12, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 825.8 446.3 446.2 446.3 595.2 1. (CC) gcc options: -O2 -flto -lOpenCL
Hashcat Benchmark: 7-Zip OpenBenchmarking.org H/s, More Is Better Hashcat 6.2.4 Benchmark: 7-Zip NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 300K 600K 900K 1200K 1500K SE +/- 1587.45, N = 3 SE +/- 2062.63, N = 3 SE +/- 1991.93, N = 3 SE +/- 2339.04, N = 3 SE +/- 1628.91, N = 3 1056000 976967 1176467 1262633 1420700
Waifu2x-NCNN Vulkan Scale: 2x - Denoise: 3 - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better Waifu2x-NCNN Vulkan 20200818 Scale: 2x - Denoise: 3 - TAA: Yes NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 0.7205 1.441 2.1615 2.882 3.6025 SE +/- 0.011, N = 3 SE +/- 0.028, N = 3 SE +/- 0.014, N = 3 SE +/- 0.009, N = 3 SE +/- 0.028, N = 3 3.202 3.168 2.855 2.854 2.660
clpeak OpenCL Test: Global Memory Bandwidth OpenBenchmarking.org GBPS, More Is Better clpeak 1.1.2 OpenCL Test: Global Memory Bandwidth NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 200 400 600 800 1000 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 816.55 437.21 437.65 437.63 582.84 1. (CXX) g++ options: -O3
MandelGPU OpenCL Device: GPU OpenBenchmarking.org Samples/sec, More Is Better MandelGPU 1.3pts1 OpenCL Device: GPU NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 140M 280M 420M 560M 700M SE +/- 794770.01, N = 3 SE +/- 1783157.89, N = 3 SE +/- 467034.80, N = 3 SE +/- 1202791.77, N = 3 SE +/- 1096202.13, N = 3 484098913.8 516770131.2 587219538.2 619106132.5 656484783.7 1. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL
FinanceBench Benchmark: Black-Scholes OpenCL OpenBenchmarking.org ms, Fewer Is Better FinanceBench 2016-07-25 Benchmark: Black-Scholes OpenCL NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 2 4 6 8 10 SE +/- 0.006, N = 3 SE +/- 0.003, N = 3 SE +/- 0.114, N = 15 SE +/- 0.003, N = 3 SE +/- 0.000, N = 3 5.741 6.906 5.912 5.226 0.501 1. (CXX) g++ options: -O3 -march=native -fopenmp
NeatBench Acceleration: GPU OpenBenchmarking.org FPS, More Is Better NeatBench 5 Acceleration: GPU NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 900 1800 2700 3600 4500 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 512.75, N = 16 3090.0 4070.0 4070.0 4070.0 2084.1
clpeak OpenCL Test: Integer Compute INT OpenBenchmarking.org GIOPS, More Is Better clpeak 1.1.2 OpenCL Test: Integer Compute INT NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 5K 10K 15K 20K 25K SE +/- 16.49, N = 3 SE +/- 15.26, N = 3 SE +/- 3.14, N = 3 SE +/- 2.50, N = 3 SE +/- 28.14, N = 3 17923.33 14555.19 18170.54 19821.10 22171.25 1. (CXX) g++ options: -O3
clpeak OpenCL Test: Single-Precision Float OpenBenchmarking.org GFLOPS, More Is Better clpeak 1.1.2 OpenCL Test: Single-Precision Float NVIDIA RTX 3090 NVIDIA RTX 4070 NVIDIA RTX 4070 SUPER NVIDIA RTX 4070 TI NVIDIA RTX 4070 TI SUPER 9K 18K 27K 36K 45K SE +/- 113.39, N = 3 SE +/- 5.46, N = 3 SE +/- 0.99, N = 3 SE +/- 11.67, N = 3 SE +/- 50.25, N = 3 34906.79 28479.39 35492.69 38691.73 43244.79 1. (CXX) g++ options: -O3
Phoronix Test Suite v10.8.5