AMD Ryzen 9 9950X 16-Core testing with a ASUS ROG STRIX X670E-E GAMING WIFI (2204 BIOS) and AMD Radeon RX 7900 GRE 16GB on Ubuntu 24.04 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 2408225-NE-9950XONNX44

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
Show Result Confidence Charts

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
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
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

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):

9950X onnx svt AMD Ryzen 9 9950X 16-Core testing with a ASUS ROG STRIX X670E-E GAMING WIFI (2204 BIOS) and AMD Radeon RX 7900 GRE 16GB on Ubuntu 24.04 via the Phoronix Test Suite. a: Processor: AMD Ryzen 9 9950X 16-Core @ 5.75GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG STRIX X670E-E GAMING WIFI (2204 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 32GB DDR5-6400MT/s Corsair CMK64GX5M2B6400C32, Disk: 2000GB Corsair MP700 PRO, Graphics: AMD Radeon RX 7900 GRE 16GB, Audio: AMD Navi 31 HDMI/DP, Monitor: DELL U2723QE, Network: Intel I225-V + Intel Wi-Fi 6E OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2~git2406040600.8112d4~oibaf~n (git-8112d44 2024-06-04 noble-oibaf-ppa) (LLVM 17.0.6 DRM 3.57), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160 b: Processor: AMD Ryzen 9 9950X 16-Core @ 5.75GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG STRIX X670E-E GAMING WIFI (2204 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 32GB DDR5-6400MT/s Corsair CMK64GX5M2B6400C32, Disk: 2000GB Corsair MP700 PRO, Graphics: AMD Radeon RX 7900 GRE 16GB, Audio: AMD Navi 31 HDMI/DP, Monitor: DELL U2723QE, Network: Intel I225-V + Intel Wi-Fi 6E OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2~git2406040600.8112d4~oibaf~n (git-8112d44 2024-06-04 noble-oibaf-ppa) (LLVM 17.0.6 DRM 3.57), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160 c: Processor: AMD Ryzen 9 9950X 16-Core @ 5.75GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG STRIX X670E-E GAMING WIFI (2204 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 32GB DDR5-6400MT/s Corsair CMK64GX5M2B6400C32, Disk: 2000GB Corsair MP700 PRO, Graphics: AMD Radeon RX 7900 GRE 16GB, Audio: AMD Navi 31 HDMI/DP, Monitor: DELL U2723QE, Network: Intel I225-V + Intel Wi-Fi 6E OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2~git2406040600.8112d4~oibaf~n (git-8112d44 2024-06-04 noble-oibaf-ppa) (LLVM 17.0.6 DRM 3.57), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160 d: Processor: AMD Ryzen 9 9950X 16-Core @ 5.75GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG STRIX X670E-E GAMING WIFI (2204 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 32GB DDR5-6400MT/s Corsair CMK64GX5M2B6400C32, Disk: 2000GB Corsair MP700 PRO, Graphics: AMD Radeon RX 7900 GRE 16GB, Audio: AMD Navi 31 HDMI/DP, Monitor: DELL U2723QE, Network: Intel I225-V + Intel Wi-Fi 6E OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2~git2406040600.8112d4~oibaf~n (git-8112d44 2024-06-04 noble-oibaf-ppa) (LLVM 17.0.6 DRM 3.57), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160 e: Processor: AMD Ryzen 9 9950X 16-Core @ 5.75GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG STRIX X670E-E GAMING WIFI (2204 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 32GB DDR5-6400MT/s Corsair CMK64GX5M2B6400C32, Disk: 2000GB Corsair MP700 PRO, Graphics: AMD Radeon RX 7900 GRE 16GB, Audio: AMD Navi 31 HDMI/DP, Monitor: DELL U2723QE, Network: Intel I225-V + Intel Wi-Fi 6E OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2~git2406040600.8112d4~oibaf~n (git-8112d44 2024-06-04 noble-oibaf-ppa) (LLVM 17.0.6 DRM 3.57), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160 ONNX Runtime 1.19 Model: yolov4 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 7.71368 |=========================================================== b . 7.68899 |=========================================================== c . 8.03773 |============================================================= d . 8.62837 |================================================================== e . 7.82444 |============================================================ ONNX Runtime 1.19 Model: bertsquad-12 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 25.10 |==================================================================== b . 25.05 |==================================================================== c . 25.05 |==================================================================== d . 23.41 |=============================================================== e . 25.02 |==================================================================== ONNX Runtime 1.19 Model: T5 Encoder - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 190.62 |================================================================== b . 192.68 |=================================================================== c . 192.82 |=================================================================== d . 183.02 |=============================================================== e . 193.25 |=================================================================== ONNX Runtime 1.19 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 221.94 |=================================================================== b . 220.47 |================================================================== c . 214.48 |================================================================ d . 223.21 |=================================================================== e . 217.92 |================================================================= ONNX Runtime 1.19 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 11.78 |=================================================================== b . 11.60 |================================================================== c . 11.98 |==================================================================== d . 11.71 |================================================================== e . 11.75 |=================================================================== ONNX Runtime 1.19 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 61.50 |=================================================================== b . 60.48 |================================================================== c . 62.20 |==================================================================== d . 62.15 |==================================================================== e . 60.32 |================================================================== ONNX Runtime 1.19 Model: GPT-2 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 161.41 |=================================================================== b . 156.72 |================================================================= c . 157.63 |================================================================= d . 157.69 |================================================================= e . 157.65 |================================================================= ONNX Runtime 1.19 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 245.28 |=================================================================== b . 243.73 |================================================================== c . 242.24 |================================================================== d . 245.87 |=================================================================== e . 239.03 |================================================================= Whisperfile 20Aug24 Model Size: Tiny Seconds < Lower Is Better a . 29.63 |================================================================== b . 30.31 |==================================================================== c . 30.04 |=================================================================== d . 30.04 |=================================================================== e . 30.37 |==================================================================== ONNX Runtime 1.19 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 152.64 |=================================================================== b . 152.85 |=================================================================== c . 149.51 |================================================================== d . 149.30 |================================================================= e . 149.91 |================================================================== ONNX Runtime 1.19 Model: super-resolution-10 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 225.16 |=================================================================== b . 224.14 |=================================================================== c . 223.79 |=================================================================== d . 224.24 |=================================================================== e . 220.16 |================================================================== ONNX Runtime 1.19 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 24.48 |=================================================================== b . 24.45 |=================================================================== c . 24.28 |=================================================================== d . 24.77 |==================================================================== e . 24.26 |=================================================================== SVT-AV1 2.2 Encoder Mode: Preset 8 - Input: Beauty 4K 10-bit Frames Per Second > Higher Is Better a . 10.59 |=================================================================== b . 10.61 |=================================================================== c . 10.53 |=================================================================== d . 10.53 |=================================================================== e . 10.74 |==================================================================== ONNX Runtime 1.19 Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 1.41808 |================================================================= b . 1.41079 |================================================================= c . 1.42067 |================================================================= d . 1.40886 |================================================================= e . 1.43691 |================================================================== ONNX Runtime 1.19 Model: T5 Encoder - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 190.55 |=================================================================== b . 190.48 |=================================================================== c . 187.74 |================================================================== d . 190.60 |=================================================================== e . 191.36 |=================================================================== ONNX Runtime 1.19 Model: yolov4 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 13.78 |=================================================================== b . 13.88 |==================================================================== c . 13.91 |==================================================================== d . 13.95 |==================================================================== e . 13.71 |=================================================================== ONNX Runtime 1.19 Model: ZFNet-512 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 71.08 |=================================================================== b . 70.80 |=================================================================== c . 71.60 |==================================================================== d . 70.55 |=================================================================== e . 71.64 |==================================================================== Whisperfile 20Aug24 Model Size: Small Seconds < Lower Is Better a . 127.97 |================================================================== b . 128.24 |================================================================== c . 129.63 |=================================================================== d . 129.80 |=================================================================== e . 129.38 |=================================================================== ONNX Runtime 1.19 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 578.94 |=================================================================== b . 573.43 |================================================================== c . 571.19 |================================================================== d . 574.32 |================================================================== e . 575.42 |=================================================================== ONNX Runtime 1.19 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 41.33 |==================================================================== b . 41.30 |==================================================================== c . 40.89 |=================================================================== d . 41.08 |==================================================================== e . 40.82 |=================================================================== ONNX Runtime 1.19 Model: ZFNet-512 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 127.19 |=================================================================== b . 125.63 |================================================================== c . 126.00 |================================================================== d . 127.17 |=================================================================== e . 126.02 |================================================================== ONNX Runtime 1.19 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 851.24 |================================================================== b . 852.42 |================================================================== c . 855.08 |================================================================== d . 854.14 |================================================================== e . 861.65 |=================================================================== SVT-AV1 2.2 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 98.66 |==================================================================== b . 99.26 |==================================================================== c . 99.22 |==================================================================== d . 98.24 |=================================================================== e . 98.06 |=================================================================== SVT-AV1 2.2 Encoder Mode: Preset 13 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 257.20 |=================================================================== b . 258.65 |=================================================================== c . 257.42 |=================================================================== d . 255.71 |================================================================== e . 256.15 |================================================================== ONNX Runtime 1.19 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 2.22498 |================================================================= b . 2.25003 |================================================================== c . 2.24795 |================================================================== d . 2.23680 |================================================================== e . 2.23767 |================================================================== ONNX Runtime 1.19 Model: GPT-2 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 150.87 |=================================================================== b . 151.25 |=================================================================== c . 149.57 |================================================================== d . 150.29 |=================================================================== e . 151.20 |=================================================================== ONNX Runtime 1.19 Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 2.55959 |================================================================== b . 2.55502 |================================================================= c . 2.57815 |================================================================== d . 2.55793 |================================================================= e . 2.55063 |================================================================= ONNX Runtime 1.19 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 4.95375 |================================================================== b . 4.92894 |================================================================= c . 4.98053 |================================================================== d . 4.93277 |================================================================= e . 4.93075 |================================================================= SVT-AV1 2.2 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 302.42 |=================================================================== b . 304.33 |=================================================================== c . 303.06 |=================================================================== d . 303.12 |=================================================================== e . 301.64 |================================================================== SVT-AV1 2.2 Encoder Mode: Preset 5 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 128.71 |=================================================================== b . 127.96 |=================================================================== c . 128.37 |=================================================================== d . 128.10 |=================================================================== e . 127.61 |================================================================== SVT-AV1 2.2 Encoder Mode: Preset 5 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 44.10 |==================================================================== b . 43.97 |==================================================================== c . 43.77 |=================================================================== d . 43.87 |==================================================================== e . 43.74 |=================================================================== SVT-AV1 2.2 Encoder Mode: Preset 3 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 11.81 |==================================================================== b . 11.82 |==================================================================== c . 11.79 |==================================================================== d . 11.82 |==================================================================== e . 11.74 |==================================================================== Whisperfile 20Aug24 Model Size: Medium Seconds < Lower Is Better a . 328.97 |=================================================================== b . 327.13 |=================================================================== c . 329.24 |=================================================================== d . 328.29 |=================================================================== e . 328.01 |=================================================================== SVT-AV1 2.2 Encoder Mode: Preset 5 - Input: Beauty 4K 10-bit Frames Per Second > Higher Is Better a . 7.574 |==================================================================== b . 7.588 |==================================================================== c . 7.583 |==================================================================== d . 7.540 |==================================================================== e . 7.541 |==================================================================== ONNX Runtime 1.19 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 55.74 |==================================================================== b . 56.05 |==================================================================== c . 56.01 |==================================================================== d . 56.03 |==================================================================== e . 55.91 |==================================================================== SVT-AV1 2.2 Encoder Mode: Preset 13 - Input: Beauty 4K 10-bit Frames Per Second > Higher Is Better a . 19.40 |==================================================================== b . 19.40 |==================================================================== c . 19.42 |==================================================================== d . 19.49 |==================================================================== e . 19.49 |==================================================================== SVT-AV1 2.2 Encoder Mode: Preset 3 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 37.31 |==================================================================== b . 37.21 |==================================================================== c . 37.20 |==================================================================== d . 37.15 |==================================================================== e . 37.20 |==================================================================== SVT-AV1 2.2 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 1009.64 |================================================================== b . 1011.24 |================================================================== c . 1012.77 |================================================================== d . 1011.43 |================================================================== e . 1010.76 |================================================================== SVT-AV1 2.2 Encoder Mode: Preset 3 - Input: Beauty 4K 10-bit Frames Per Second > Higher Is Better a . 1.760 |==================================================================== b . 1.758 |==================================================================== c . 1.760 |==================================================================== d . 1.759 |==================================================================== e . 1.759 |==================================================================== ONNX Runtime 1.19 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 16.26 |=================================================================== b . 16.53 |==================================================================== c . 16.08 |================================================================== d . 16.09 |================================================================== e . 16.58 |==================================================================== ONNX Runtime 1.19 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 24.19 |=================================================================== b . 24.21 |=================================================================== c . 24.45 |==================================================================== d . 24.34 |==================================================================== e . 24.49 |==================================================================== ONNX Runtime 1.19 Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 390.73 |=================================================================== b . 391.38 |=================================================================== c . 387.87 |================================================================== d . 390.94 |=================================================================== e . 392.06 |=================================================================== ONNX Runtime 1.19 Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 705.21 |=================================================================== b . 708.82 |=================================================================== c . 703.89 |================================================================== d . 709.79 |=================================================================== e . 695.94 |================================================================== ONNX Runtime 1.19 Model: super-resolution-10 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 4.44116 |================================================================= b . 4.46130 |================================================================= c . 4.46838 |================================================================= d . 4.45929 |================================================================= e . 4.54187 |================================================================== ONNX Runtime 1.19 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 4.50538 |================================================================ b . 4.53509 |================================================================ c . 4.66209 |================================================================== d . 4.47960 |=============================================================== e . 4.58833 |================================================================= ONNX Runtime 1.19 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 1.72670 |================================================================= b . 1.74330 |================================================================== c . 1.74974 |================================================================== d . 1.74031 |================================================================== e . 1.73720 |================================================================== ONNX Runtime 1.19 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 6.55079 |================================================================= b . 6.54126 |================================================================ c . 6.68702 |================================================================== d . 6.69723 |================================================================== e . 6.66991 |================================================================== ONNX Runtime 1.19 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 17.94 |==================================================================== b . 17.84 |==================================================================== c . 17.85 |==================================================================== d . 17.84 |==================================================================== e . 17.89 |==================================================================== ONNX Runtime 1.19 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 40.85 |=================================================================== b . 40.90 |=================================================================== c . 41.18 |==================================================================== d . 40.36 |=================================================================== e . 41.22 |==================================================================== ONNX Runtime 1.19 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 201.87 |=================================================================== b . 202.88 |=================================================================== c . 200.78 |================================================================== d . 202.72 |=================================================================== e . 202.81 |=================================================================== ONNX Runtime 1.19 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 449.48 |=================================================================== b . 444.44 |================================================================== c . 444.85 |================================================================== d . 447.06 |=================================================================== e . 446.89 |=================================================================== ONNX Runtime 1.19 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 1.17405 |================================================================== b . 1.17235 |================================================================== c . 1.16879 |================================================================== d . 1.17003 |================================================================== e . 1.15972 |================================================================= ONNX Runtime 1.19 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 4.07620 |================================================================ b . 4.10040 |================================================================= c . 4.12702 |================================================================= d . 4.06632 |================================================================ e . 4.18210 |================================================================== ONNX Runtime 1.19 Model: bertsquad-12 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 39.83 |=============================================================== b . 39.91 |================================================================ c . 39.92 |================================================================ d . 42.71 |==================================================================== e . 39.96 |================================================================ ONNX Runtime 1.19 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 84.93 |=================================================================== b . 86.20 |==================================================================== c . 83.45 |================================================================== d . 85.40 |=================================================================== e . 85.08 |=================================================================== ONNX Runtime 1.19 Model: T5 Encoder - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 5.24802 |=============================================================== b . 5.18948 |=============================================================== c . 5.18564 |=============================================================== d . 5.46322 |================================================================== e . 5.17395 |=============================================================== ONNX Runtime 1.19 Model: T5 Encoder - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 5.24748 |================================================================= b . 5.24914 |================================================================= c . 5.32595 |================================================================== d . 5.24590 |================================================================= e . 5.22498 |================================================================= ONNX Runtime 1.19 Model: ZFNet-512 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 7.86110 |================================================================= b . 7.95942 |================================================================== c . 7.93481 |================================================================== d . 7.86194 |================================================================= e . 7.93399 |================================================================== ONNX Runtime 1.19 Model: ZFNet-512 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 14.07 |==================================================================== b . 14.12 |==================================================================== c . 13.97 |=================================================================== d . 14.17 |==================================================================== e . 13.96 |=================================================================== ONNX Runtime 1.19 Model: yolov4 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 72.55 |==================================================================== b . 72.03 |=================================================================== c . 71.87 |=================================================================== d . 71.69 |=================================================================== e . 72.96 |==================================================================== ONNX Runtime 1.19 Model: yolov4 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 129.64 |=================================================================== b . 130.12 |=================================================================== c . 124.41 |================================================================ d . 115.89 |============================================================ e . 127.80 |================================================================== ONNX Runtime 1.19 Model: GPT-2 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 6.19550 |================================================================ b . 6.37911 |================================================================== c . 6.34248 |================================================================== d . 6.33978 |================================================================== e . 6.34139 |================================================================== ONNX Runtime 1.19 Model: GPT-2 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 6.62484 |================================================================= b . 6.60878 |================================================================= c . 6.68270 |================================================================== d . 6.65046 |================================================================== e . 6.61099 |=================================================================