RTX 4070 SUPER
sudo apt install vulkan-headers vulkan-tools libvulkan-dev
HTML result view exported from: https://openbenchmarking.org/result/2412092-NE-INTELGPU196&grs&sor.
NCNN
Target: Vulkan GPU - Model: googlenet
NCNN
Target: Vulkan GPU - Model: mobilenet
NCNN
Target: Vulkan GPU - Model: vision_transformer
NCNN
Target: Vulkan GPU - Model: resnet18
NCNN
Target: Vulkan GPU - Model: regnety_400m
Hashcat
Benchmark: 7-Zip
ViennaCL
Test: OpenCL BLAS - sAXPY
Hashcat
Benchmark: SHA1
ProjectPhysX OpenCL-Benchmark
Operation: INT32 Compute
ProjectPhysX OpenCL-Benchmark
Operation: FP32 Compute
clpeak
OpenCL Test: Integer Compute INT
Hashcat
Benchmark: SHA-512
ViennaCL
Test: OpenCL BLAS - sCOPY
clpeak
OpenCL Test: Single-Precision Float
Unigine Valley
Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL
cl-mem
Benchmark: Read
ViennaCL
Test: OpenCL BLAS - sDOT
VkFFT
Test: FFT + iFFT C2C Bluestein in single precision
IndigoBench
Acceleration: OpenCL GPU - Scene: Supercar
Hashcat
Benchmark: TrueCrypt RIPEMD160 + XTS
ProjectPhysX OpenCL-Benchmark
Operation: Memory Bandwidth Coalesced Read
Hashcat
Benchmark: MD5
IndigoBench
Acceleration: OpenCL GPU - Scene: Bedroom
ViennaCL
Test: CPU BLAS - sDOT
NCNN
Target: Vulkan GPU - Model: resnet50
NCNN
Target: Vulkan GPU - Model: squeezenet_ssd
OpenArena
Resolution: 1920 x 1080 - Total Frame Time
RealSR-NCNN
Scale: 4x - TAA: Yes
Waifu2x-NCNN Vulkan
Scale: 2x - Denoise: 3 - TAA: Yes
VkFFT
Test: FFT + iFFT R2C / C2R
ViennaCL
Test: CPU BLAS - sCOPY
VkFFT
Test: FFT + iFFT C2C multidimensional in single precision
ProjectPhysX OpenCL-Benchmark
Operation: INT8 Compute
NCNN
Target: Vulkan GPU - Model: alexnet
cl-mem
Benchmark: Write
VkFFT
Test: FFT + iFFT C2C 1D batched in half precision
NCNN
Target: Vulkan GPU - Model: yolov4-tiny
ViennaCL
Test: CPU BLAS - sAXPY
ViennaCL
Test: CPU BLAS - dDOT
VkFFT
Test: FFT + iFFT C2C 1D batched in single precision
ViennaCL
Test: CPU BLAS - dCOPY
cl-mem
Benchmark: Copy
ViennaCL
Test: CPU BLAS - dGEMM-TN
VkFFT
Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling
vkpeak
int32-scalar
vkpeak
int32-vec4
vkpeak
fp32-vec4
ProjectPhysX OpenCL-Benchmark
Operation: Memory Bandwidth Coalesced Write
vkpeak
fp16-scalar
vkpeak
int16-scalar
vkpeak
fp16-vec4
vkpeak
int16-vec4
vkpeak
fp32-scalar
ViennaCL
Test: CPU BLAS - dGEMM-NN
ViennaCL
Test: CPU BLAS - dAXPY
clpeak
OpenCL Test: Global Memory Bandwidth
ViennaCL
Test: CPU BLAS - dGEMM-TT
ViennaCL
Test: CPU BLAS - dGEMM-NT
NCNN
Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3
VkResample
Upscale: 2x - Precision: Single
ViennaCL
Test: CPU BLAS - dGEMV-T
ViennaCL
Test: CPU BLAS - dGEMV-N
ProjectPhysX OpenCL-Benchmark
Operation: FP16 Compute
SHOC Scalable HeterOgeneous Computing
Target: OpenCL - Benchmark: Texture Read Bandwidth
SHOC Scalable HeterOgeneous Computing
Target: OpenCL - Benchmark: Bus Speed Readback
SHOC Scalable HeterOgeneous Computing
Target: OpenCL - Benchmark: Bus Speed Download
SHOC Scalable HeterOgeneous Computing
Target: OpenCL - Benchmark: GEMM SGEMM_N
SHOC Scalable HeterOgeneous Computing
Target: OpenCL - Benchmark: Reduction
SHOC Scalable HeterOgeneous Computing
Target: OpenCL - Benchmark: MD5 Hash
SHOC Scalable HeterOgeneous Computing
Target: OpenCL - Benchmark: FFT SP
SHOC Scalable HeterOgeneous Computing
Target: OpenCL - Benchmark: Triad
SHOC Scalable HeterOgeneous Computing
Target: OpenCL - Benchmark: S3D
Darktable
Test: Server Room - Acceleration: CPU-only
Darktable
Test: Server Rack - Acceleration: CPU-only
Darktable
Test: Server Room - Acceleration: OpenCL
Darktable
Test: Server Rack - Acceleration: OpenCL
Darktable
Test: Masskrug - Acceleration: CPU-only
Darktable
Test: Masskrug - Acceleration: OpenCL
Darktable
Test: Boat - Acceleration: CPU-only
Darktable
Test: Boat - Acceleration: OpenCL
SPECViewPerf 2020
Resolution: 1920 x 1080 - Viewset: SOLIDWORKS-07
SPECViewPerf 2020
Resolution: 1920 x 1080 - Viewset: MEDICAL-O3
SPECViewPerf 2020
Resolution: 1920 x 1080 - Viewset: ENERGY-03
SPECViewPerf 2020
Resolution: 1920 x 1080 - Viewset: CATIA-06
SPECViewPerf 2020
Resolution: 1920 x 1080 - Viewset: MAYA-06
SPECViewPerf 2020
Resolution: 1920 x 1080 - Viewset: CREO-03
SPECViewPerf 2020
Resolution: 1920 x 1080 - Viewset: SNX-04
LuxMark
OpenCL Device: CPU+GPU - Scene: Luxball HDR
LuxMark
OpenCL Device: CPU+GPU - Scene: Microphone
LuxMark
OpenCL Device: GPU - Scene: Luxball HDR
LuxMark
OpenCL Device: GPU - Scene: Microphone
LuxMark
OpenCL Device: CPU+GPU - Scene: Hotel
LuxMark
OpenCL Device: GPU - Scene: Hotel
IndigoBench
Acceleration: CPU - Scene: Supercar
IndigoBench
Acceleration: CPU - Scene: Bedroom
TensorFlow
Device: GPU - Batch Size: 512 - Model: GoogLeNet
TensorFlow
Device: GPU - Batch Size: 256 - Model: ResNet-50
TensorFlow
Device: GPU - Batch Size: 256 - Model: GoogLeNet
TensorFlow
Device: GPU - Batch Size: 64 - Model: ResNet-50
TensorFlow
Device: GPU - Batch Size: 64 - Model: GoogLeNet
TensorFlow
Device: GPU - Batch Size: 32 - Model: ResNet-50
TensorFlow
Device: GPU - Batch Size: 32 - Model: GoogLeNet
TensorFlow
Device: GPU - Batch Size: 16 - Model: ResNet-50
TensorFlow
Device: GPU - Batch Size: 16 - Model: GoogLeNet
TensorFlow
Device: GPU - Batch Size: 512 - Model: AlexNet
TensorFlow
Device: GPU - Batch Size: 256 - Model: AlexNet
TensorFlow
Device: GPU - Batch Size: 1 - Model: ResNet-50
TensorFlow
Device: GPU - Batch Size: 1 - Model: GoogLeNet
TensorFlow
Device: GPU - Batch Size: 64 - Model: AlexNet
TensorFlow
Device: GPU - Batch Size: 32 - Model: AlexNet
TensorFlow
Device: GPU - Batch Size: 16 - Model: AlexNet
TensorFlow
Device: GPU - Batch Size: 64 - Model: VGG-16
TensorFlow
Device: GPU - Batch Size: 32 - Model: VGG-16
TensorFlow
Device: GPU - Batch Size: 16 - Model: VGG-16
TensorFlow
Device: GPU - Batch Size: 1 - Model: AlexNet
TensorFlow
Device: GPU - Batch Size: 1 - Model: VGG-16
ParaView
Test: Wavelet Contour - Resolution: 1920 x 1080
ParaView
Test: Many Spheres - Resolution: 1920 x 1080
Xonotic
Resolution: 1920 x 1080 - Effects Quality: Ultimate
Xonotic
Resolution: 1920 x 1080 - Effects Quality: Ultra
Xonotic
Resolution: 1920 x 1080 - Effects Quality: High
Xonotic
Resolution: 1920 x 1080 - Effects Quality: Low
Unigine Heaven
Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL
OpenArena
Resolution: 1920 x 1080
VkFFT
Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling
VkFFT
Test: FFT + iFFT C2C multidimensional in single precision
VkFFT
Test: FFT + iFFT C2C 1D batched in single precision
VkFFT
Test: FFT + iFFT C2C Bluestein in single precision
VkFFT
Test: FFT + iFFT R2C / C2R
vkpeak
fp16-vec4
vkpeak
fp16-scalar
vkpeak
fp32-vec4
vkpeak
fp32-scalar
TensorFlow
Device: GPU - Batch Size: 64 - Model: ResNet-50
TensorFlow
Device: GPU - Batch Size: 64 - Model: GoogLeNet
TensorFlow
Device: GPU - Batch Size: 32 - Model: ResNet-50
TensorFlow
Device: GPU - Batch Size: 32 - Model: GoogLeNet
TensorFlow
Device: GPU - Batch Size: 16 - Model: ResNet-50
TensorFlow
Device: GPU - Batch Size: 16 - Model: GoogLeNet
TensorFlow
Device: GPU - Batch Size: 512 - Model: AlexNet
TensorFlow
Device: GPU - Batch Size: 256 - Model: AlexNet
TensorFlow
Device: GPU - Batch Size: 1 - Model: ResNet-50
TensorFlow
Device: GPU - Batch Size: 1 - Model: GoogLeNet
TensorFlow
Device: GPU - Batch Size: 64 - Model: AlexNet
TensorFlow
Device: GPU - Batch Size: 32 - Model: AlexNet
TensorFlow
Device: GPU - Batch Size: 16 - Model: AlexNet
TensorFlow
Device: GPU - Batch Size: 32 - Model: VGG-16
TensorFlow
Device: GPU - Batch Size: 16 - Model: VGG-16
TensorFlow
Device: GPU - Batch Size: 1 - Model: AlexNet
TensorFlow
Device: GPU - Batch Size: 1 - Model: VGG-16
NeatBench
Acceleration: GPU
Blender
Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX
Blender
Blend File: Barbershop - Compute: NVIDIA OptiX
Blender
Blend File: Fishy Cat - Compute: NVIDIA OptiX
Blender
Blend File: Classroom - Compute: NVIDIA OptiX
Blender
Blend File: BMW27 - Compute: NVIDIA OptiX
ViennaCL
Test: OpenCL BLAS - dGEMM-TT
ViennaCL
Test: OpenCL BLAS - dGEMM-TN
ViennaCL
Test: OpenCL BLAS - dGEMM-NT
ViennaCL
Test: OpenCL BLAS - dGEMM-NN
ViennaCL
Test: OpenCL BLAS - dGEMV-T
ViennaCL
Test: OpenCL BLAS - dGEMV-N
ViennaCL
Test: OpenCL BLAS - dDOT
ViennaCL
Test: OpenCL BLAS - dAXPY
ViennaCL
Test: OpenCL BLAS - dCOPY
clpeak
OpenCL Test: Double-Precision Double
FAHBench
VkResample
Upscale: 2x - Precision: Double
VkFFT
Test: FFT + iFFT C2C Bluestein benchmark in double precision
VkFFT
Test: FFT + iFFT C2C 1D batched in double precision
ProjectPhysX OpenCL-Benchmark
Operation: FP64 Compute
SHOC Scalable HeterOgeneous Computing
Target: OpenCL - Benchmark: Max SP Flops
ParaView
Test: Wavelet Contour - Resolution: 1920 x 1080
ParaView
Test: Wavelet Volume - Resolution: 1920 x 1080
ParaView
Test: Wavelet Volume - Resolution: 1920 x 1080
ParaView
Test: Many Spheres - Resolution: 1920 x 1080
VkFFT
Test: FFT + iFFT C2C 1D batched in half precision
NCNN
Target: Vulkan GPU - Model: FastestDet
NCNN
Target: Vulkan GPU - Model: vgg16
NCNN
Target: Vulkan GPU - Model: blazeface
NCNN
Target: Vulkan GPU - Model: efficientnet-b0
NCNN
Target: Vulkan GPU - Model: mnasnet
NCNN
Target: Vulkan GPU - Model: shufflenet-v2
NCNN
Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3
NCNN
Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2
MandelGPU
OpenCL Device: GPU
FinanceBench
Benchmark: Black-Scholes OpenCL
RealSR-NCNN
Scale: 4x - TAA: No
ProjectPhysX OpenCL-Benchmark
Operation: INT16 Compute
ProjectPhysX OpenCL-Benchmark
Operation: INT64 Compute
Phoronix Test Suite v10.8.5