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.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2401307-NE-2401299NE85
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

BLAS (Basic Linear Algebra Sub-Routine) Tests 3 Tests
C++ Boost Tests 2 Tests
CPU Massive 5 Tests
Creator Workloads 4 Tests
HPC - High Performance Computing 8 Tests
Machine Learning 6 Tests
Multi-Core 6 Tests
NVIDIA GPU Compute 25 Tests
OpenCL 5 Tests
Python Tests 5 Tests
Renderers 3 Tests
Server CPU Tests 2 Tests
Vulkan Compute 7 Tests
Common Workstation Benchmarks 2 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
NVIDIA RTX 4070 SUPER
January 25
  23 Hours, 51 Minutes
NVIDIA RTX 4070
January 28
  22 Hours, 26 Minutes
NVIDIA RTX 4070 TI
January 29
  1 Day, 7 Hours, 18 Minutes
Invert Hiding All Results Option
  1 Day, 1 Hour, 52 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

RTX 4070 SUPER Suite 1.0.0 System Test suite extracted from RTX 4070 SUPER. pts/clpeak-1.1.0 --compute-integer OpenCL Test: Integer Compute INT pts/clpeak-1.1.0 --compute-sp OpenCL Test: Single-Precision Float pts/hashcat-1.1.1 -m 0 Benchmark: MD5 pts/hashcat-1.1.1 -m 6211 Benchmark: TrueCrypt RIPEMD160 + XTS pts/opencl-benchmark-1.0.0 Operation: INT8 Compute pts/hashcat-1.1.1 -m 1700 Benchmark: SHA-512 pts/gpuowl-1.0.0 -iters 20000 -prp 332220523 Exponent: 332220523 pts/clpeak-1.1.0 --compute-dp OpenCL Test: Double-Precision Double pts/opencl-benchmark-1.0.0 Operation: FP64 Compute pts/hashcat-1.1.1 -m 100 Benchmark: SHA1 pts/hashcat-1.1.1 -m 11600 Benchmark: 7-Zip pts/viennacl-1.1.0 dense_blas-bench-opencl Test: OpenCL BLAS - dGEMM-TT pts/vkresample-1.0.2 -u 2 -p 1 Upscale: 2x - Precision: Double pts/opencl-benchmark-1.0.0 Operation: FP32 Compute pts/gpuowl-1.0.0 -iters 100000 -prp 57885161 Exponent: 57885161 pts/opencl-benchmark-1.0.0 Operation: INT32 Compute pts/opencl-benchmark-1.0.0 Operation: INT64 Compute pts/viennacl-1.1.0 dense_blas-bench-opencl Test: OpenCL BLAS - dGEMM-TN pts/viennacl-1.1.0 dense_blas-bench-opencl Test: OpenCL BLAS - dGEMM-NT pts/opencl-benchmark-1.0.0 Operation: INT16 Compute pts/viennacl-1.1.0 dense_blas-bench-opencl Test: OpenCL BLAS - dGEMM-NN pts/gpuowl-1.0.0 -iters 100000 -prp 77936867 Exponent: 77936867 pts/realsr-ncnn-1.0.0 -s 4 -x Scale: 4x - TAA: Yes pts/libplacebo-1.1.0 Test: deband_heavy pts/libplacebo-1.1.0 Test: polar_nocompute pts/rodinia-1.3.2 OCL_PARTICLEFILTER Test: OpenCL Particle Filter pts/luxcorerender-1.4.0 DanishMood/LuxCoreScene/render.cfg -D renderengine.type PATHOCL -D opencl.native.threads.count 0 -D context.cuda.optix.enable 0 Scene: Danish Mood - Acceleration: GPU pts/blender-4.0.0 -b ../fishy_cat_gpu.blend -o output.test -x 1 -F JPEG -f 1 -- --cycles-device OPTIX Blend File: Fishy Cat - Compute: NVIDIA OptiX pts/luxcorerender-1.4.0 LuxCore2.1Benchmark/LuxCoreScene/render.cfg -D renderengine.type PATHOCL -D opencl.native.threads.count 0 -D context.cuda.optix.enable 0 Scene: LuxCore Benchmark - Acceleration: GPU pts/blender-4.0.0 -b ../classroom_gpu.blend -o output.test -x 1 -F JPEG -f 1 -- --cycles-device OPTIX Blend File: Classroom - Compute: NVIDIA OptiX pts/fahbench-1.0.2 pts/mandelgpu-1.3.1 0 1 OpenCL Device: GPU pts/vkfft-1.2.0 -vkfft 8 Test: FFT + iFFT C2C Bluestein benchmark in double precision pts/luxcorerender-1.4.0 RainbowColorsAndPrism/LuxCoreScene/render.cfg -D renderengine.type PATHOCL -D opencl.native.threads.count 0 -D context.cuda.optix.enable 0 Scene: Rainbow Colors and Prism - Acceleration: GPU pts/luxcorerender-1.4.0 DLSC/LuxCoreScene/render.cfg -D renderengine.type PATHOCL -D opencl.native.threads.count 0 -D context.cuda.optix.enable 0 Scene: DLSC - Acceleration: GPU pts/blender-4.0.0 -b ../pavillon_barcelone_gpu.blend -o output.test -x 1 -F JPEG -f 1 -- --cycles-device OPTIX Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX pts/vkfft-1.2.0 -vkfft 6 Test: FFT + iFFT R2C / C2R pts/blender-4.0.0 -b ../barbershop_interior_gpu.blend -o output.test -x 1 -F JPEG -f 1 -- --cycles-device OPTIX Blend File: Barbershop - Compute: NVIDIA OptiX pts/blender-4.0.0 -b ../bmw27_gpu.blend -o output.test -x 1 -F JPEG -f 1 -- --cycles-device OPTIX Blend File: BMW27 - Compute: NVIDIA OptiX pts/luxcorerender-1.4.0 OrangeJuice/LuxCoreScene/render.cfg -D renderengine.type PATHOCL -D opencl.native.threads.count 0 -D context.cuda.optix.enable 0 Scene: Orange Juice - Acceleration: GPU pts/vkfft-1.2.0 -vkfft 1 Test: FFT + iFFT C2C 1D batched in double precision pts/octanebench-1.3.0 Total Score pts/indigobench-1.1.0 --gpuonly --scenes bedroom Acceleration: OpenCL GPU - Scene: Bedroom pts/pytorch-1.0.1 cuda 16 resnet50 Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-50 pts/waifu2x-ncnn-1.0.0 -s 2 -n 3 -x Scale: 2x - Denoise: 3 - TAA: Yes pts/pytorch-1.0.1 cuda 64 resnet50 Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-50 pts/vkfft-1.2.0 -vkfft 7 Test: FFT + iFFT C2C Bluestein in single precision pts/namd-cuda-1.1.1 ATPase Simulation - 327,506 Atoms pts/indigobench-1.1.0 --gpuonly --scenes supercar Acceleration: OpenCL GPU - Scene: Supercar pts/pytorch-1.0.1 cuda 32 resnet50 Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-50 pts/pytorch-1.0.1 cuda 512 resnet50 Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-50 pts/pytorch-1.0.1 cuda 256 resnet50 Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-50 pts/vkfft-1.2.0 -vkfft 3 Test: FFT + iFFT C2C multidimensional in single precision pts/viennacl-1.1.0 dense_blas-bench-cpu Test: CPU BLAS - dGEMM-TN pts/libplacebo-1.1.0 Test: hdr_peakdetect pts/tensorflow-2.1.1 --device gpu --batch_size=1 --model=alexnet Device: GPU - Batch Size: 1 - Model: AlexNet pts/pytorch-1.0.1 cuda 32 resnet152 Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-152 pts/pytorch-1.0.1 cuda 64 resnet152 Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-152 pts/vkfft-1.2.0 -vkfft 5 Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling pts/vkfft-1.2.0 -vkfft 0 Test: FFT + iFFT C2C 1D batched in single precision pts/viennacl-1.1.0 dense_blas-bench-cpu Test: CPU BLAS - dGEMM-TT pts/vkfft-1.2.0 -vkfft 2 Test: FFT + iFFT C2C 1D batched in half precision pts/pytorch-1.0.1 cuda 256 resnet152 Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-152 pts/pytorch-1.0.1 cuda 16 resnet152 Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-152 pts/viennacl-1.1.0 dense_blas-bench-cpu Test: CPU BLAS - dGEMM-NT pts/viennacl-1.1.0 dense_blas-bench-cpu Test: CPU BLAS - dGEMM-NN pts/pytorch-1.0.1 cuda 512 resnet152 Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-152 pts/viennacl-1.1.0 dense_blas-bench-opencl Test: OpenCL BLAS - dAXPY pts/vkresample-1.0.2 -u 2 -p 0 Upscale: 2x - Precision: Single pts/tensorflow-2.1.1 --device gpu --batch_size=1 --model=vgg16 Device: GPU - Batch Size: 1 - Model: VGG-16 pts/viennacl-1.1.0 dense_blas-bench-opencl Test: OpenCL BLAS - sDOT pts/pytorch-1.0.1 cuda 512 efficientnet_v2_l Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: Efficientnet_v2_l pts/pytorch-1.0.1 cuda 1 efficientnet_v2_l Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: Efficientnet_v2_l pts/pytorch-1.0.1 cuda 256 efficientnet_v2_l Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: Efficientnet_v2_l pts/viennacl-1.1.0 dense_blas-bench-cpu Test: CPU BLAS - sAXPY pts/pytorch-1.0.1 cuda 1 resnet152 Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-152 pts/viennacl-1.1.0 dense_blas-bench-opencl Test: OpenCL BLAS - sCOPY pts/viennacl-1.1.0 dense_blas-bench-cpu Test: CPU BLAS - sDOT pts/libplacebo-1.1.0 Test: hdr_lut pts/libplacebo-1.1.0 Test: av1_grain_lap pts/pytorch-1.0.1 cuda 64 efficientnet_v2_l Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: Efficientnet_v2_l pts/cl-mem-1.0.1 WRITE Benchmark: Write pts/tensorflow-2.1.1 --device gpu --batch_size=16 --model=vgg16 Device: GPU - Batch Size: 16 - Model: VGG-16 pts/tensorflow-2.1.1 --device gpu --batch_size=1 --model=googlenet Device: GPU - Batch Size: 1 - Model: GoogLeNet pts/tensorflow-2.1.1 --device gpu --batch_size=256 --model=alexnet Device: GPU - Batch Size: 256 - Model: AlexNet pts/tensorflow-2.1.1 --device gpu --batch_size=32 --model=googlenet Device: GPU - Batch Size: 32 - Model: GoogLeNet pts/viennacl-1.1.0 dense_blas-bench-opencl Test: OpenCL BLAS - dGEMV-T pts/viennacl-1.1.0 dense_blas-bench-opencl Test: OpenCL BLAS - sAXPY pts/viennacl-1.1.0 dense_blas-bench-cpu Test: CPU BLAS - dGEMV-N pts/opencl-benchmark-1.0.0 Operation: Memory Bandwidth Coalesced Write pts/tensorflow-2.1.1 --device gpu --batch_size=512 --model=alexnet Device: GPU - Batch Size: 512 - Model: AlexNet pts/viennacl-1.1.0 dense_blas-bench-opencl Test: OpenCL BLAS - dGEMV-N pts/tensorflow-2.1.1 --device gpu --batch_size=32 --model=resnet50 Device: GPU - Batch Size: 32 - Model: ResNet-50 pts/cl-mem-1.0.1 COPY Benchmark: Copy pts/tensorflow-2.1.1 --device gpu --batch_size=16 --model=alexnet Device: GPU - Batch Size: 16 - Model: AlexNet pts/viennacl-1.1.0 dense_blas-bench-cpu Test: CPU BLAS - sCOPY pts/viennacl-1.1.0 dense_blas-bench-cpu Test: CPU BLAS - dCOPY pts/tensorflow-2.1.1 --device gpu --batch_size=1 --model=resnet50 Device: GPU - Batch Size: 1 - Model: ResNet-50 pts/viennacl-1.1.0 dense_blas-bench-cpu Test: CPU BLAS - dAXPY pts/tensorflow-2.1.1 --device gpu --batch_size=16 --model=resnet50 Device: GPU - Batch Size: 16 - Model: ResNet-50 pts/viennacl-1.1.0 dense_blas-bench-opencl Test: OpenCL BLAS - dDOT pts/viennacl-1.1.0 dense_blas-bench-cpu Test: CPU BLAS - dDOT pts/tensorflow-2.1.1 --device gpu --batch_size=64 --model=alexnet Device: GPU - Batch Size: 64 - Model: AlexNet pts/tensorflow-2.1.1 --device gpu --batch_size=64 --model=resnet50 Device: GPU - Batch Size: 64 - Model: ResNet-50 pts/tensorflow-2.1.1 --device gpu --batch_size=32 --model=alexnet Device: GPU - Batch Size: 32 - Model: AlexNet pts/tensorflow-2.1.1 --device gpu --batch_size=64 --model=googlenet Device: GPU - Batch Size: 64 - Model: GoogLeNet pts/viennacl-1.1.0 dense_blas-bench-opencl Test: OpenCL BLAS - dCOPY pts/pytorch-1.0.1 cuda 16 efficientnet_v2_l Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: Efficientnet_v2_l pts/tensorflow-2.1.1 --device gpu --batch_size=16 --model=googlenet Device: GPU - Batch Size: 16 - Model: GoogLeNet pts/clpeak-1.1.0 --global-bandwidth OpenCL Test: Global Memory Bandwidth pts/opencl-benchmark-1.0.0 Operation: Memory Bandwidth Coalesced Read pts/cl-mem-1.0.1 READ Benchmark: Read pts/tensorflow-2.1.1 --device gpu --batch_size=256 --model=vgg16 Device: GPU - Batch Size: 256 - Model: VGG-16 pts/tensorflow-2.1.1 --device gpu --batch_size=64 --model=vgg16 Device: GPU - Batch Size: 64 - Model: VGG-16 pts/tensorflow-2.1.1 --device gpu --batch_size=32 --model=vgg16 Device: GPU - Batch Size: 32 - Model: VGG-16 pts/neatbench-1.0.4 gpu Acceleration: GPU pts/ncnn-1.5.0 Target: Vulkan GPU - Model: FastestDet pts/ncnn-1.5.0 Target: Vulkan GPU - Model: vision_transformer pts/ncnn-1.5.0 Target: Vulkan GPU - Model: regnety_400m pts/ncnn-1.5.0 Target: Vulkan GPU - Model: squeezenet_ssd pts/ncnn-1.5.0 Target: Vulkan GPU - Model: yolov4-tiny pts/ncnn-1.5.0 Target: Vulkan GPU - Model: resnet50 pts/ncnn-1.5.0 Target: Vulkan GPU - Model: alexnet pts/ncnn-1.5.0 Target: Vulkan GPU - Model: resnet18 pts/ncnn-1.5.0 Target: Vulkan GPU - Model: vgg16 pts/ncnn-1.5.0 Target: Vulkan GPU - Model: googlenet pts/ncnn-1.5.0 Target: Vulkan GPU - Model: blazeface pts/ncnn-1.5.0 Target: Vulkan GPU - Model: efficientnet-b0 pts/ncnn-1.5.0 Target: Vulkan GPU - Model: mnasnet pts/ncnn-1.5.0 Target: Vulkan GPU - Model: shufflenet-v2 pts/ncnn-1.5.0 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 pts/ncnn-1.5.0 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 pts/ncnn-1.5.0 Target: Vulkan GPU - Model: mobilenet pts/tensorflow-2.1.1 --device gpu --batch_size=512 --model=vgg16 Device: GPU - Batch Size: 512 - Model: VGG-16 pts/plaidml-1.0.4 --no-fp16 --no-train densenet201 OPENCL FP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCL pts/plaidml-1.0.4 --fp16 --no-train mobilenet OPENCL FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL pts/plaidml-1.0.4 --no-fp16 --no-train mobilenet OPENCL FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL pts/plaidml-1.0.4 --no-fp16 --no-train imdb_lstm OPENCL FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL pts/plaidml-1.0.4 --no-fp16 --train mobilenet OPENCL FP16: No - Mode: Training - Network: Mobilenet - Device: OpenCL pts/ncnn-1.5.0 Target: Vulkan GPU pts/caffe-1.5.0 --model=../models/bvlc_googlenet/deploy.prototxt -gpu all -iterations 1000 Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 1000 pts/caffe-1.5.0 --model=../models/bvlc_googlenet/deploy.prototxt -gpu all -iterations 200 Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 200 pts/caffe-1.5.0 --model=../models/bvlc_googlenet/deploy.prototxt -gpu all -iterations 100 Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 100 pts/caffe-1.5.0 --model=../models/bvlc_alexnet/deploy.prototxt -gpu all -iterations 1000 Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 1000 pts/caffe-1.5.0 --model=../models/bvlc_alexnet/deploy.prototxt -gpu all -iterations 200 Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 200 pts/caffe-1.5.0 --model=../models/bvlc_alexnet/deploy.prototxt -gpu all -iterations 100 Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 100 pts/viennacl-1.1.0 dense_blas-bench-cpu Test: CPU BLAS - dGEMV-T pts/financebench-1.1.1 Black-Scholes/OpenCL/blackScholesAnalyticEngine.exe Benchmark: Black-Scholes OpenCL pts/arrayfire-1.2.0 cg_opencl Test: Conjugate Gradient OpenCL pts/lczero-1.7.0 -b opencl Backend: OpenCL pts/libplacebo-1.1.0 pts/waifu2x-ncnn-1.0.0 -s 2 -n 3 Scale: 2x - Denoise: 3 - TAA: No pts/realsr-ncnn-1.0.0 -s 4 Scale: 4x - TAA: No pts/vkpeak-1.1.0 pts/pytorch-1.0.1 cuda 32 efficientnet_v2_l Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: Efficientnet_v2_l pts/pytorch-1.0.1 cuda 1 resnet50 Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-50