AMD Ryzen 9 7950X 16-Core testing with a ASUS ROG STRIX X670E-E GAMING WIFI (1416 BIOS) and AMD Radeon RX 6700 XT on Ubuntu 23.04 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 2308012-PTS-VULKANBE49
vulkan benchmarks,
"NCNN 20230517 - Target: CPU - Model: mobilenet",
Lower Results Are Better
"a",8.1,8.02,8.03
"b",
"c",
"NCNN 20230517 - Target: CPU-v2-v2 - Model: mobilenet-v2",
Lower Results Are Better
"a",3.15,3.16,3.16
"b",
"c",
"NCNN 20230517 - Target: CPU - Model: shufflenet-v2",
Lower Results Are Better
"a",3.32,3.34,3.36
"b",
"c",
"NCNN 20230517 - Target: CPU - Model: mnasnet",
Lower Results Are Better
"a",2.95,2.97,2.98
"b",
"c",
"NCNN 20230517 - Target: CPU - Model: efficientnet-b0",
Lower Results Are Better
"a",3.99,3.85,3.85
"b",
"c",
"NCNN 20230517 - Target: CPU - Model: blazeface",
Lower Results Are Better
"a",1.37,1.38,1.38
"b",
"c",
"NCNN 20230517 - Target: CPU - Model: googlenet",
Lower Results Are Better
"a",8.15,7.86,7.8
"b",
"c",
"NCNN 20230517 - Target: CPU - Model: vgg16",
Lower Results Are Better
"a",24.35,23.47,23.44
"b",
"c",
"NCNN 20230517 - Target: CPU - Model: resnet18",
Lower Results Are Better
"a",5.42,5.23,5.21
"b",
"c",
"NCNN 20230517 - Target: CPU - Model: alexnet",
Lower Results Are Better
"a",4.63,4.3,4.3
"b",
"c",
"NCNN 20230517 - Target: CPU - Model: resnet50",
Lower Results Are Better
"a",10.65,10,9.94
"b",
"c",
"NCNN 20230517 - Target: CPU - Model: yolov4-tiny",
Lower Results Are Better
"a",13.12,12.8,12.79
"b",
"c",
"NCNN 20230517 - Target: CPU - Model: squeezenet_ssd",
Lower Results Are Better
"a",7.05,7.09,7.08
"b",
"c",
"NCNN 20230517 - Target: CPU - Model: regnety_400m",
Lower Results Are Better
"a",8.12,8.16,8.27
"b",
"c",
"NCNN 20230517 - Target: CPU - Model: vision_transformer",
Lower Results Are Better
"a",32.74,32.83,31.91
"b",
"c",
"NCNN 20230517 - Target: CPU - Model: FastestDet",
Lower Results Are Better
"a",4.06,2.72,4.08
"b",
"c",
"NCNN 20230517 - Target: CPU-v3-v3 - Model: mobilenet-v3",
Lower Results Are Better
"a",3.18,3.18
"c",
"NCNN 20230517 - Target: Vulkan GPU - Model: mobilenet",
Lower Results Are Better
"a",8.08,8.06,8
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2",
Lower Results Are Better
"a",3.18,3.18,3.14
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3",
Lower Results Are Better
"a",3.16,3.2,3.15
"c",
"NCNN 20230517 - Target: Vulkan GPU - Model: shufflenet-v2",
Lower Results Are Better
"a",3.36,3.36,3.32
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU - Model: mnasnet",
Lower Results Are Better
"a",2.98,3,2.96
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU - Model: efficientnet-b0",
Lower Results Are Better
"a",3.86,3.88,3.84
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU - Model: blazeface",
Lower Results Are Better
"a",1.39,1.39,1.36
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU - Model: googlenet",
Lower Results Are Better
"a",7.92,7.92,7.85
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU - Model: vgg16",
Lower Results Are Better
"a",23.51,23.59,23.44
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU - Model: resnet18",
Lower Results Are Better
"a",5.28,5.29,5.26
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU - Model: alexnet",
Lower Results Are Better
"a",4.31,4.32,4.29
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU - Model: resnet50",
Lower Results Are Better
"a",10,10.06,9.98
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU - Model: yolov4-tiny",
Lower Results Are Better
"a",12.84,12.88,12.81
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU - Model: squeezenet_ssd",
Lower Results Are Better
"a",7.1,7.12,7.04
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU - Model: regnety_400m",
Lower Results Are Better
"a",8.2,8.33,7.96
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU - Model: vision_transformer",
Lower Results Are Better
"a",32.05,31.78,31.8
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU - Model: FastestDet",
Lower Results Are Better
"a",4.1,4.1,4.1
"b",
"c",
"NCNN 20230517 - Target: CPU-v3-v3-v3 - Model: mobilenet",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: CPU-v3-v3-v3-v2-v2 - Model: mobilenet-v2",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: CPU-v3-v3-v3-v3-v3 - Model: mobilenet-v3",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: CPU-v3-v3-v3 - Model: shufflenet-v2",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: CPU-v3-v3-v3 - Model: mnasnet",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: CPU-v3-v3-v3 - Model: efficientnet-b0",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: CPU-v3-v3-v3 - Model: blazeface",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: CPU-v3-v3-v3 - Model: googlenet",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: CPU-v3-v3-v3 - Model: vgg16",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: CPU-v3-v3-v3 - Model: resnet18",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: CPU-v3-v3-v3 - Model: alexnet",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: CPU-v3-v3-v3 - Model: resnet50",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: CPU-v3-v3-v3 - Model: yolov4-tiny",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: CPU-v3-v3-v3 - Model: squeezenet_ssd",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: CPU-v3-v3-v3 - Model: regnety_400m",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: CPU-v3-v3-v3 - Model: vision_transformer",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: CPU-v3-v3-v3 - Model: FastestDet",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU-v3-v3-v3 - Model: mobilenet",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU-v3-v3-v3-v2-v2 - Model: mobilenet-v2",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU-v3-v3-v3-v3-v3 - Model: mobilenet-v3",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU-v3-v3-v3 - Model: shufflenet-v2",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU-v3-v3-v3 - Model: mnasnet",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU-v3-v3-v3 - Model: efficientnet-b0",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU-v3-v3-v3 - Model: blazeface",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU-v3-v3-v3 - Model: googlenet",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU-v3-v3-v3 - Model: vgg16",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU-v3-v3-v3 - Model: resnet18",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU-v3-v3-v3 - Model: alexnet",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU-v3-v3-v3 - Model: resnet50",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU-v3-v3-v3 - Model: yolov4-tiny",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU-v3-v3-v3 - Model: squeezenet_ssd",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU-v3-v3-v3 - Model: regnety_400m",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU-v3-v3-v3 - Model: vision_transformer",
Lower Results Are Better
"b",
"c",
"NCNN 20230517 - Target: Vulkan GPU-v3-v3-v3 - Model: FastestDet",
Lower Results Are Better
"b",
"c",
"VkFFT 1.2.31 - Test: FFT + iFFT R2C / C2R",
Higher Results Are Better
"a",42500,41970,41846
"b",
"c",
"VkFFT 1.2.31 - Test: FFT + iFFT C2C 1D batched in half precision",
Higher Results Are Better
"a",91606,91448,91737
"b",
"c",
"VkFFT 1.2.31 - Test: FFT + iFFT C2C Bluestein in single precision",
Higher Results Are Better
"a",11465,11277,11277
"b",
"c",
"VkFFT 1.2.31 - Test: FFT + iFFT C2C 1D batched in double precision",
Higher Results Are Better
"a",20794,20819,20834
"b",
"c",
"VkFFT 1.2.31 - Test: FFT + iFFT C2C 1D batched in single precision",
Higher Results Are Better
"a",47904,47886,47871
"b",
"c",
"VkFFT 1.2.31 - Test: FFT + iFFT C2C multidimensional in single precision",
Higher Results Are Better
"a",33076,33039,32887
"b",
"c",
"VkFFT 1.2.31 - Test: FFT + iFFT C2C Bluestein benchmark in double precision",
Higher Results Are Better
"a",4717,4717,4718
"b",
"c",
"VkFFT 1.2.31 - Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling",
Higher Results Are Better
"a",50500,50521,50491
"b",
"c",
"vkpeak 20230730 - fp32-scalar",
Higher Results Are Better
"a",13197.36,13182.88,13190.02
"b",
"c",
"vkpeak 20230730 - fp32-vec4",
Higher Results Are Better
"a",12733.7,12728.31,12728.22
"b",
"c",
"vkpeak 20230730 - fp16-scalar",
Higher Results Are Better
"a",13147.3,13153.96,13161.18
"b",
"c",
"vkpeak 20230730 - fp16-vec4",
Higher Results Are Better
"a",23221.66,23233.35,23242.25
"b",
"c",
"vkpeak 20230730 - fp64-scalar",
Higher Results Are Better
"a",841.09,841.27,841.83
"b",
"c",
"vkpeak 20230730 - fp64-vec4",
Higher Results Are Better
"a",842.39,841.71,841.29
"b",
"c",
"vkpeak 20230730 - int32-scalar",
Higher Results Are Better
"a",2272.07,2272.54,2273.25
"b",
"c",
"vkpeak 20230730 - int32-vec4",
Higher Results Are Better
"a",2658.24,2659.12,2658.84
"b",
"c",
"vkpeak 20230730 - int16-scalar",
Higher Results Are Better
"a",13101.22,13101.69,13105.34
"b",
"c",
"vkpeak 20230730 - int16-vec4",
Higher Results Are Better
"a",23080.77,23147.93,23142.6
"b",
"c",
"VkResample 1.0 - Upscale: 2x - Precision: Single",
Lower Results Are Better
"a",11.687,11.687,11.684
"b",
"c",