AMD Ryzen Threadripper 7980X 64-Cores testing with a System76 Thelio Major (FA Z5 BIOS) and AMD Radeon Pro W7900 on Ubuntu 24.10 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 2408227-PTS-ONNX119192
onnx 119
AMD Ryzen Threadripper 7980X 64-Cores testing with a System76 Thelio Major (FA Z5 BIOS) and AMD Radeon Pro W7900 on Ubuntu 24.10 via the Phoronix Test Suite.
a:
Processor: AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (FA Z5 BIOS), Chipset: AMD Device 14a4, Memory: 4 x 32GB DDR5-4800MT/s Micron MTC20F1045S1RC48BA2, Disk: 1000GB CT1000T700SSD5, Graphics: AMD Radeon Pro W7900, Audio: AMD Device 14cc, Monitor: DELL P2415Q, Network: Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6E
OS: Ubuntu 24.10, Kernel: 6.8.0-31-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.0.9-0ubuntu2 (LLVM 17.0.6 DRM 3.57), Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1920x1200
b:
Processor: AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (FA Z5 BIOS), Chipset: AMD Device 14a4, Memory: 4 x 32GB DDR5-4800MT/s Micron MTC20F1045S1RC48BA2, Disk: 1000GB CT1000T700SSD5, Graphics: AMD Radeon Pro W7900, Audio: AMD Device 14cc, Monitor: DELL P2415Q, Network: Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6E
OS: Ubuntu 24.10, Kernel: 6.8.0-31-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.0.9-0ubuntu2 (LLVM 17.0.6 DRM 3.57), Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1920x1200
c:
Processor: AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (FA Z5 BIOS), Chipset: AMD Device 14a4, Memory: 4 x 32GB DDR5-4800MT/s Micron MTC20F1045S1RC48BA2, Disk: 1000GB CT1000T700SSD5, Graphics: AMD Radeon Pro W7900, Audio: AMD Device 14cc, Monitor: DELL P2415Q, Network: Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6E
OS: Ubuntu 24.10, Kernel: 6.8.0-31-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.0.9-0ubuntu2 (LLVM 17.0.6 DRM 3.57), Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1920x1200
d:
Processor: AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (FA Z5 BIOS), Chipset: AMD Device 14a4, Memory: 4 x 32GB DDR5-4800MT/s Micron MTC20F1045S1RC48BA2, Disk: 1000GB CT1000T700SSD5, Graphics: AMD Radeon Pro W7900, Audio: AMD Device 14cc, Monitor: DELL P2415Q, Network: Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6E
OS: Ubuntu 24.10, Kernel: 6.8.0-31-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.0.9-0ubuntu2 (LLVM 17.0.6 DRM 3.57), Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1920x1200
e:
Processor: AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (FA Z5 BIOS), Chipset: AMD Device 14a4, Memory: 4 x 32GB DDR5-4800MT/s Micron MTC20F1045S1RC48BA2, Disk: 1000GB CT1000T700SSD5, Graphics: AMD Radeon Pro W7900, Audio: AMD Device 14cc, Monitor: DELL P2415Q, Network: Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6E
OS: Ubuntu 24.10, Kernel: 6.8.0-31-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.0.9-0ubuntu2 (LLVM 17.0.6 DRM 3.57), Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1920x1200
SVT-AV1 2.2
Encoder Mode: Preset 3 - Input: Beauty 4K 10-bit
Frames Per Second > Higher Is Better
a . 1.864 |====================================================================
b . 1.857 |===================================================================
c . 1.867 |====================================================================
d . 1.874 |====================================================================
e . 1.867 |====================================================================
ONNX Runtime 1.19
Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel
Inference Time Cost (ms) < Lower Is Better
a . 908.30 |===================================================================
b . 913.54 |===================================================================
c . 913.49 |===================================================================
d . 873.47 |================================================================
e . 889.23 |=================================================================
ONNX Runtime 1.19
Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel
Inferences Per Second > Higher Is Better
a . 1.10358 |================================================================
b . 1.09825 |===============================================================
c . 1.09469 |===============================================================
d . 1.14486 |==================================================================
e . 1.12456 |=================================================================
ONNX Runtime 1.19
Model: fcn-resnet101-11 - Device: CPU - Executor: Standard
Inference Time Cost (ms) < Lower Is Better
a . 257.99 |===========================================================
b . 252.34 |==========================================================
c . 291.44 |===================================================================
d . 288.12 |==================================================================
e . 276.92 |================================================================
ONNX Runtime 1.19
Model: fcn-resnet101-11 - Device: CPU - Executor: Standard
Inferences Per Second > Higher Is Better
a . 3.92686 |=================================================================
b . 4.00404 |==================================================================
c . 3.43115 |=========================================================
d . 3.47069 |=========================================================
e . 3.61108 |============================================================
SVT-AV1 2.2
Encoder Mode: Preset 3 - Input: Bosphorus 4K
Frames Per Second > Higher Is Better
a . 13.40 |===================================================================
b . 13.35 |===================================================================
c . 13.53 |====================================================================
d . 13.38 |===================================================================
e . 13.41 |===================================================================
SVT-AV1 2.2
Encoder Mode: Preset 5 - Input: Beauty 4K 10-bit
Frames Per Second > Higher Is Better
a . 7.775 |====================================================================
b . 7.801 |====================================================================
c . 7.811 |====================================================================
d . 7.809 |====================================================================
e . 7.765 |====================================================================
ONNX Runtime 1.19
Model: ZFNet-512 - Device: CPU - Executor: Standard
Inference Time Cost (ms) < Lower Is Better
a . 12.23 |=================================================================
b . 12.29 |=================================================================
c . 12.12 |================================================================
d . 12.24 |=================================================================
e . 12.79 |====================================================================
ONNX Runtime 1.19
Model: ZFNet-512 - Device: CPU - Executor: Standard
Inferences Per Second > Higher Is Better
a . 81.78 |===================================================================
b . 81.42 |===================================================================
c . 82.50 |====================================================================
d . 81.67 |===================================================================
e . 78.16 |================================================================
ONNX Runtime 1.19
Model: yolov4 - Device: CPU - Executor: Parallel
Inference Time Cost (ms) < Lower Is Better
a . 189.68 |================================================================
b . 195.13 |=================================================================
c . 188.50 |===============================================================
d . 199.71 |===================================================================
e . 195.37 |==================================================================
ONNX Runtime 1.19
Model: yolov4 - Device: CPU - Executor: Parallel
Inferences Per Second > Higher Is Better
a . 5.27246 |==================================================================
b . 5.12789 |================================================================
c . 5.30486 |==================================================================
d . 5.00717 |==============================================================
e . 5.11842 |================================================================
ONNX Runtime 1.19
Model: bertsquad-12 - Device: CPU - Executor: Standard
Inference Time Cost (ms) < Lower Is Better
a . 78.92 |====================================================================
b . 78.57 |====================================================================
c . 75.87 |=================================================================
d . 76.94 |==================================================================
e . 78.47 |====================================================================
ONNX Runtime 1.19
Model: bertsquad-12 - Device: CPU - Executor: Standard
Inferences Per Second > Higher Is Better
a . 12.67 |=================================================================
b . 12.74 |==================================================================
c . 13.18 |====================================================================
d . 13.00 |===================================================================
e . 12.74 |==================================================================
ONNX Runtime 1.19
Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel
Inference Time Cost (ms) < Lower Is Better
a . 34.83 |=================================================================
b . 34.65 |=================================================================
c . 36.16 |====================================================================
d . 36.21 |====================================================================
e . 36.02 |====================================================================
ONNX Runtime 1.19
Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel
Inferences Per Second > Higher Is Better
a . 28.73 |====================================================================
b . 28.88 |====================================================================
c . 27.65 |=================================================================
d . 27.61 |=================================================================
e . 27.76 |=================================================================
ONNX Runtime 1.19
Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel
Inference Time Cost (ms) < Lower Is Better
a . 4.88925 |=========================================================
b . 4.99490 |===========================================================
c . 5.61236 |==================================================================
d . 4.69742 |=======================================================
e . 4.74627 |========================================================
ONNX Runtime 1.19
Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel
Inferences Per Second > Higher Is Better
a . 204.48 |================================================================
b . 200.84 |===============================================================
c . 178.13 |========================================================
d . 212.81 |===================================================================
e . 210.62 |==================================================================
ONNX Runtime 1.19
Model: bertsquad-12 - Device: CPU - Executor: Parallel
Inference Time Cost (ms) < Lower Is Better
a . 147.81 |===================================================================
b . 145.78 |==================================================================
c . 144.56 |==================================================================
d . 140.72 |================================================================
e . 142.42 |=================================================================
ONNX Runtime 1.19
Model: bertsquad-12 - Device: CPU - Executor: Parallel
Inferences Per Second > Higher Is Better
a . 6.76854 |===============================================================
b . 6.86262 |================================================================
c . 6.91740 |================================================================
d . 7.10593 |==================================================================
e . 7.02121 |=================================================================
SVT-AV1 2.2
Encoder Mode: Preset 8 - Input: Beauty 4K 10-bit
Frames Per Second > Higher Is Better
a . 10.84 |===================================================================
b . 10.83 |===================================================================
c . 10.85 |===================================================================
d . 10.87 |===================================================================
e . 10.97 |====================================================================
SVT-AV1 2.2
Encoder Mode: Preset 3 - Input: Bosphorus 1080p
Frames Per Second > Higher Is Better
a . 36.61 |====================================================================
b . 36.55 |====================================================================
c . 36.66 |====================================================================
d . 36.71 |====================================================================
e . 36.46 |====================================================================
ONNX Runtime 1.19
Model: super-resolution-10 - Device: CPU - Executor: Standard
Inference Time Cost (ms) < Lower Is Better
a . 9.94497 |================================================================
b . 9.93654 |================================================================
c . 9.91284 |================================================================
d . 9.52165 |==============================================================
e . 10.05920 |=================================================================
ONNX Runtime 1.19
Model: super-resolution-10 - Device: CPU - Executor: Standard
Inferences Per Second > Higher Is Better
a . 100.59 |================================================================
b . 100.68 |================================================================
c . 100.88 |================================================================
d . 105.02 |===================================================================
e . 99.41 |===============================================================
ONNX Runtime 1.19
Model: yolov4 - Device: CPU - Executor: Standard
Inference Time Cost (ms) < Lower Is Better
a . 114.15 |===================================================================
b . 114.83 |===================================================================
c . 110.42 |================================================================
d . 113.73 |==================================================================
e . 110.03 |================================================================
ONNX Runtime 1.19
Model: yolov4 - Device: CPU - Executor: Standard
Inferences Per Second > Higher Is Better
a . 8.76007 |================================================================
b . 8.71251 |===============================================================
c . 9.05619 |==================================================================
d . 8.79279 |================================================================
e . 9.08788 |==================================================================
SVT-AV1 2.2
Encoder Mode: Preset 13 - Input: Beauty 4K 10-bit
Frames Per Second > Higher Is Better
a . 19.52 |====================================================================
b . 19.42 |====================================================================
c . 19.40 |====================================================================
d . 19.44 |====================================================================
e . 19.44 |====================================================================
ONNX Runtime 1.19
Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Parallel
Inference Time Cost (ms) < Lower Is Better
a . 621.23 |==================================================================
b . 625.06 |==================================================================
c . 617.60 |==================================================================
d . 630.81 |===================================================================
e . 621.08 |==================================================================
ONNX Runtime 1.19
Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Parallel
Inferences Per Second > Higher Is Better
a . 1.60987 |==================================================================
b . 1.59999 |=================================================================
c . 1.61916 |==================================================================
d . 1.58526 |=================================================================
e . 1.61010 |==================================================================
ONNX Runtime 1.19
Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standard
Inference Time Cost (ms) < Lower Is Better
a . 372.79 |===================================================================
b . 370.18 |==================================================================
c . 371.60 |==================================================================
d . 374.58 |===================================================================
e . 371.18 |==================================================================
ONNX Runtime 1.19
Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standard
Inferences Per Second > Higher Is Better
a . 2.68248 |==================================================================
b . 2.70145 |==================================================================
c . 2.69105 |==================================================================
d . 2.66966 |=================================================================
e . 2.69413 |==================================================================
ONNX Runtime 1.19
Model: GPT-2 - Device: CPU - Executor: Parallel
Inference Time Cost (ms) < Lower Is Better
a . 6.21628 |==================================================================
b . 6.18911 |==================================================================
c . 6.15989 |=================================================================
d . 6.17185 |==================================================================
e . 6.15756 |=================================================================
ONNX Runtime 1.19
Model: GPT-2 - Device: CPU - Executor: Parallel
Inferences Per Second > Higher Is Better
a . 160.71 |==================================================================
b . 161.41 |===================================================================
c . 162.18 |===================================================================
d . 161.86 |===================================================================
e . 162.25 |===================================================================
ONNX Runtime 1.19
Model: ZFNet-512 - Device: CPU - Executor: Parallel
Inference Time Cost (ms) < Lower Is Better
a . 18.73 |=================================================================
b . 18.33 |===============================================================
c . 19.71 |====================================================================
d . 18.41 |================================================================
e . 18.38 |===============================================================
ONNX Runtime 1.19
Model: ZFNet-512 - Device: CPU - Executor: Parallel
Inferences Per Second > Higher Is Better
a . 53.41 |===================================================================
b . 54.58 |====================================================================
c . 50.74 |===============================================================
d . 54.30 |====================================================================
e . 54.42 |====================================================================
ONNX Runtime 1.19
Model: GPT-2 - Device: CPU - Executor: Standard
Inference Time Cost (ms) < Lower Is Better
a . 9.51832 |==================================================================
b . 9.45128 |==================================================================
c . 9.46853 |==================================================================
d . 9.50891 |==================================================================
e . 9.28112 |================================================================
ONNX Runtime 1.19
Model: GPT-2 - Device: CPU - Executor: Standard
Inferences Per Second > Higher Is Better
a . 105.04 |=================================================================
b . 105.79 |==================================================================
c . 105.59 |==================================================================
d . 105.15 |=================================================================
e . 107.72 |===================================================================
ONNX Runtime 1.19
Model: T5 Encoder - Device: CPU - Executor: Parallel
Inference Time Cost (ms) < Lower Is Better
a . 2.97938 |==================================================================
b . 2.94936 |=================================================================
c . 2.94690 |=================================================================
d . 2.97608 |==================================================================
e . 2.95124 |=================================================================
ONNX Runtime 1.19
Model: T5 Encoder - Device: CPU - Executor: Parallel
Inferences Per Second > Higher Is Better
a . 335.50 |==================================================================
b . 338.93 |===================================================================
c . 339.18 |===================================================================
d . 335.86 |==================================================================
e . 338.70 |===================================================================
ONNX Runtime 1.19
Model: T5 Encoder - Device: CPU - Executor: Standard
Inference Time Cost (ms) < Lower Is Better
a . 7.09442 |=================================================================
b . 7.03694 |================================================================
c . 7.08004 |=================================================================
d . 7.23734 |==================================================================
e . 7.21415 |==================================================================
ONNX Runtime 1.19
Model: T5 Encoder - Device: CPU - Executor: Standard
Inferences Per Second > Higher Is Better
a . 140.96 |==================================================================
b . 142.11 |===================================================================
c . 141.23 |===================================================================
d . 138.16 |=================================================================
e . 138.61 |=================================================================
ONNX Runtime 1.19
Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel
Inference Time Cost (ms) < Lower Is Better
a . 79.34 |===================================================================
b . 80.16 |====================================================================
c . 80.70 |====================================================================
d . 79.29 |===================================================================
e . 77.85 |==================================================================
ONNX Runtime 1.19
Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel
Inferences Per Second > Higher Is Better
a . 12.60 |===================================================================
b . 12.48 |==================================================================
c . 12.39 |==================================================================
d . 12.61 |===================================================================
e . 12.85 |====================================================================
ONNX Runtime 1.19
Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard
Inference Time Cost (ms) < Lower Is Better
a . 26.08 |=================================================================
b . 27.06 |====================================================================
c . 25.78 |================================================================
d . 25.50 |================================================================
e . 27.26 |====================================================================
ONNX Runtime 1.19
Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard
Inferences Per Second > Higher Is Better
a . 38.35 |===================================================================
b . 36.97 |================================================================
c . 38.78 |===================================================================
d . 39.21 |====================================================================
e . 36.68 |================================================================
ONNX Runtime 1.19
Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard
Inference Time Cost (ms) < Lower Is Better
a . 22.44 |===================================================================
b . 22.49 |===================================================================
c . 22.70 |====================================================================
d . 22.08 |==================================================================
e . 22.67 |====================================================================
ONNX Runtime 1.19
Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard
Inferences Per Second > Higher Is Better
a . 44.56 |===================================================================
b . 44.46 |===================================================================
c . 44.04 |==================================================================
d . 45.29 |====================================================================
e . 44.11 |==================================================================
ONNX Runtime 1.19
Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard
Inference Time Cost (ms) < Lower Is Better
a . 2.19841 |=============================================================
b . 2.17339 |============================================================
c . 2.26126 |===============================================================
d . 2.38355 |==================================================================
e . 2.27019 |===============================================================
ONNX Runtime 1.19
Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard
Inferences Per Second > Higher Is Better
a . 454.72 |==================================================================
b . 460.02 |===================================================================
c . 442.12 |================================================================
d . 419.42 |=============================================================
e . 440.35 |================================================================
ONNX Runtime 1.19
Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel
Inference Time Cost (ms) < Lower Is Better
a . 13.47 |===================================================================
b . 13.45 |===================================================================
c . 13.67 |====================================================================
d . 13.61 |====================================================================
e . 13.45 |===================================================================
ONNX Runtime 1.19
Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel
Inferences Per Second > Higher Is Better
a . 74.21 |====================================================================
b . 74.36 |====================================================================
c . 73.12 |===================================================================
d . 73.47 |===================================================================
e . 74.33 |====================================================================
ONNX Runtime 1.19
Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard
Inference Time Cost (ms) < Lower Is Better
a . 4.97187 |================================================================
b . 4.96437 |================================================================
c . 5.14489 |==================================================================
d . 4.90503 |===============================================================
e . 4.93285 |===============================================================
ONNX Runtime 1.19
Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard
Inferences Per Second > Higher Is Better
a . 201.10 |==================================================================
b . 201.42 |==================================================================
c . 194.34 |================================================================
d . 203.84 |===================================================================
e . 202.69 |===================================================================
ONNX Runtime 1.19
Model: super-resolution-10 - Device: CPU - Executor: Parallel
Inference Time Cost (ms) < Lower Is Better
a . 7.61417 |==================================================================
b . 7.66242 |==================================================================
c . 7.64590 |==================================================================
d . 7.56180 |=================================================================
e . 7.61659 |==================================================================
ONNX Runtime 1.19
Model: super-resolution-10 - Device: CPU - Executor: Parallel
Inferences Per Second > Higher Is Better
a . 131.31 |===================================================================
b . 130.49 |==================================================================
c . 130.77 |==================================================================
d . 132.22 |===================================================================
e . 131.27 |===================================================================
SVT-AV1 2.2
Encoder Mode: Preset 5 - Input: Bosphorus 4K
Frames Per Second > Higher Is Better
a . 45.61 |====================================================================
b . 45.34 |====================================================================
c . 45.66 |====================================================================
d . 45.17 |===================================================================
e . 45.41 |====================================================================
SVT-AV1 2.2
Encoder Mode: Preset 5 - Input: Bosphorus 1080p
Frames Per Second > Higher Is Better
a . 119.22 |===================================================================
b . 119.23 |===================================================================
c . 119.77 |===================================================================
d . 118.80 |==================================================================
e . 119.92 |===================================================================
SVT-AV1 2.2
Encoder Mode: Preset 8 - Input: Bosphorus 4K
Frames Per Second > Higher Is Better
a . 96.21 |===================================================================
b . 96.42 |====================================================================
c . 96.06 |===================================================================
d . 97.05 |====================================================================
e . 96.78 |====================================================================
SVT-AV1 2.2
Encoder Mode: Preset 13 - Input: Bosphorus 4K
Frames Per Second > Higher Is Better
a . 231.11 |==================================================================
b . 233.25 |===================================================================
c . 232.40 |===================================================================
d . 228.83 |==================================================================
e . 228.97 |==================================================================
SVT-AV1 2.2
Encoder Mode: Preset 8 - Input: Bosphorus 1080p
Frames Per Second > Higher Is Better
a . 271.68 |===================================================================
b . 269.88 |===================================================================
c . 266.01 |==================================================================
d . 269.43 |==================================================================
e . 268.76 |==================================================================
SVT-AV1 2.2
Encoder Mode: Preset 13 - Input: Bosphorus 1080p
Frames Per Second > Higher Is Better
a . 740.00 |===============================================================
b . 740.79 |===============================================================
c . 764.00 |=================================================================
d . 783.12 |===================================================================
e . 749.26 |================================================================