onnx runtime zstd AMD Ryzen 7 PRO 6850U testing with a LENOVO 21CM0001US (R22ET51W 1.21 BIOS) and AMD Radeon 680M 1GB on Ubuntu 22.10 via the Phoronix Test Suite. a: Processor: AMD Ryzen 7 PRO 6850U @ 4.77GHz (8 Cores / 16 Threads), Motherboard: LENOVO 21CM0001US (R22ET51W 1.21 BIOS), Chipset: AMD Device 14b5, Memory: 16GB, Disk: 512GB Micron MTFDKBA512TFK, Graphics: AMD Radeon 680M 1GB (2200/400MHz), Audio: AMD Rembrandt Radeon HD Audio, Network: Qualcomm QCNFA765 OS: Ubuntu 22.10, Kernel: 6.1.0-060100rc2daily20221028-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.2.1 (LLVM 15.0.2 DRM 3.49), Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1200 b: Processor: AMD Ryzen 7 PRO 6850U @ 4.77GHz (8 Cores / 16 Threads), Motherboard: LENOVO 21CM0001US (R22ET51W 1.21 BIOS), Chipset: AMD Device 14b5, Memory: 16GB, Disk: 512GB Micron MTFDKBA512TFK, Graphics: AMD Radeon 680M 1GB (2200/400MHz), Audio: AMD Rembrandt Radeon HD Audio, Network: Qualcomm QCNFA765 OS: Ubuntu 22.10, Kernel: 6.1.0-060100rc2daily20221028-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.2.1 (LLVM 15.0.2 DRM 3.49), Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1200 c: Processor: AMD Ryzen 7 PRO 6850U @ 4.77GHz (8 Cores / 16 Threads), Motherboard: LENOVO 21CM0001US (R22ET51W 1.21 BIOS), Chipset: AMD Device 14b5, Memory: 16GB, Disk: 512GB Micron MTFDKBA512TFK, Graphics: AMD Radeon 680M 1GB (2200/400MHz), Audio: AMD Rembrandt Radeon HD Audio, Network: Qualcomm QCNFA765 OS: Ubuntu 22.10, Kernel: 6.1.0-060100rc2daily20221028-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.2.1 (LLVM 15.0.2 DRM 3.49), Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1200 d: Processor: AMD Ryzen 7 PRO 6850U @ 4.77GHz (8 Cores / 16 Threads), Motherboard: LENOVO 21CM0001US (R22ET51W 1.21 BIOS), Chipset: AMD Device 14b5, Memory: 16GB, Disk: 512GB Micron MTFDKBA512TFK, Graphics: AMD Radeon 680M 1GB (2200/400MHz), Audio: AMD Rembrandt Radeon HD Audio, Network: Qualcomm QCNFA765 OS: Ubuntu 22.10, Kernel: 6.1.0-060100rc2daily20221028-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.2.1 (LLVM 15.0.2 DRM 3.49), Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1200 Zstd Compression 1.5.4 Compression Level: 3 - Compression Speed MB/s > Higher Is Better a . 1003.7 |=================================================================== b . 1006.6 |=================================================================== c . 1008.4 |=================================================================== d . 999.8 |================================================================== Zstd Compression 1.5.4 Compression Level: 3 - Decompression Speed MB/s > Higher Is Better a . 1627.1 |================================================================== b . 1631.2 |=================================================================== c . 1632.0 |=================================================================== d . 1640.9 |=================================================================== Zstd Compression 1.5.4 Compression Level: 8 - Compression Speed MB/s > Higher Is Better a . 275.6 |==================================================================== b . 276.1 |==================================================================== c . 276.8 |==================================================================== d . 275.0 |==================================================================== Zstd Compression 1.5.4 Compression Level: 8 - Decompression Speed MB/s > Higher Is Better a . 1723.7 |================================================================== b . 1738.6 |================================================================== c . 1749.9 |=================================================================== d . 1754.5 |=================================================================== Zstd Compression 1.5.4 Compression Level: 12 - Compression Speed MB/s > Higher Is Better a . 99.0 |===================================================================== b . 99.6 |===================================================================== c . 98.8 |==================================================================== d . 99.3 |===================================================================== Zstd Compression 1.5.4 Compression Level: 12 - Decompression Speed MB/s > Higher Is Better a . 1782.6 |=================================================================== b . 1790.2 |=================================================================== c . 1763.8 |================================================================== d . 1753.1 |================================================================== Zstd Compression 1.5.4 Compression Level: 19 - Compression Speed MB/s > Higher Is Better a . 10.3 |==================================================================== b . 10.4 |===================================================================== c . 10.4 |===================================================================== d . 10.2 |==================================================================== Zstd Compression 1.5.4 Compression Level: 19 - Decompression Speed MB/s > Higher Is Better a . 1503.9 |=================================================================== b . 1501.7 |=================================================================== c . 1503.7 |=================================================================== d . 1510.8 |=================================================================== Zstd Compression 1.5.4 Compression Level: 3, Long Mode - Compression Speed MB/s > Higher Is Better a . 448.2 |=========================================================== b . 448.6 |=========================================================== c . 515.3 |==================================================================== d . 455.3 |============================================================ Zstd Compression 1.5.4 Compression Level: 3, Long Mode - Decompression Speed MB/s > Higher Is Better a . 1629.9 |================================================================== b . 1645.9 |================================================================== c . 1658.4 |=================================================================== d . 1648.9 |=================================================================== Zstd Compression 1.5.4 Compression Level: 8, Long Mode - Compression Speed MB/s > Higher Is Better a . 281.3 |==================================================================== b . 282.3 |==================================================================== c . 282.9 |==================================================================== d . 281.9 |==================================================================== Zstd Compression 1.5.4 Compression Level: 8, Long Mode - Decompression Speed MB/s > Higher Is Better a . 1780.2 |=================================================================== b . 1778.5 |=================================================================== c . 1754.7 |================================================================== d . 1764.0 |================================================================== Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Compression Speed MB/s > Higher Is Better a . 6.05 |===================================================================== b . 5.98 |==================================================================== c . 5.96 |==================================================================== d . 6.06 |===================================================================== Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Decompression Speed MB/s > Higher Is Better a . 1439.0 |=================================================================== b . 1438.8 |=================================================================== c . 1433.9 |=================================================================== d . 1436.0 |=================================================================== ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 79.90 |==================================================================== b . 80.06 |==================================================================== c . 79.90 |==================================================================== d . 79.17 |=================================================================== ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 12.51 |=================================================================== b . 12.48 |=================================================================== c . 12.51 |=================================================================== d . 12.62 |==================================================================== ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 82.18 |============================================================= b . 89.42 |================================================================== c . 92.34 |==================================================================== d . 80.96 |============================================================ ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 12.16 |=================================================================== b . 11.17 |============================================================== c . 10.82 |============================================================ d . 12.34 |==================================================================== ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 4.81183 |================================================================= b . 4.89053 |================================================================== c . 4.85635 |================================================================== d . 4.71553 |================================================================ ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 207.82 |================================================================== b . 204.47 |================================================================= c . 205.91 |================================================================= d . 212.06 |=================================================================== ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 6.66706 |================================================================== b . 6.33386 |=============================================================== c . 4.63770 |============================================== d . 4.65036 |============================================== ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 149.98 |=============================================== b . 157.87 |================================================= c . 215.62 |=================================================================== d . 215.03 |=================================================================== ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 7.30784 |=============================================================== b . 7.68535 |================================================================== c . 7.46141 |================================================================ d . 7.44275 |================================================================ ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 136.83 |=================================================================== b . 130.11 |================================================================ c . 134.02 |================================================================== d . 134.36 |================================================================== ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 10.89260 |================================================================ b . 11.02160 |================================================================= c . 10.86950 |================================================================ d . 7.28019 |=========================================== ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 91.80 |============================================= b . 90.72 |============================================ c . 91.99 |============================================= d . 137.35 |=================================================================== ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 283.47 |================================================================= b . 291.30 |=================================================================== c . 289.29 |=================================================================== d . 289.15 |=================================================================== ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 3.52574 |================================================================== b . 3.43070 |================================================================ c . 3.45450 |================================================================= d . 3.45622 |================================================================= ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 336.84 |=================================================================== b . 297.64 |=========================================================== c . 335.14 |=================================================================== d . 336.71 |=================================================================== ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 2.96616 |========================================================== b . 3.35715 |================================================================== c . 2.98143 |=========================================================== d . 2.96729 |========================================================== ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 0.652903 |============================================================== b . 0.660573 |============================================================== c . 0.688063 |================================================================= d . 0.687937 |================================================================= ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 1531.61 |================================================================== b . 1513.83 |================================================================= c . 1453.35 |=============================================================== d . 1453.61 |=============================================================== ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 1.067590 |================================================================= b . 0.692005 |========================================== c . 0.689648 |========================================== d . 1.071630 |================================================================= ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 936.68 |=========================================== b . 1445.07 |================================================================== c . 1450.01 |================================================================== d . 933.15 |========================================== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 14.71 |================================================================= b . 14.52 |================================================================= c . 15.28 |==================================================================== d . 14.91 |================================================================== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 67.99 |=================================================================== b . 68.86 |==================================================================== c . 65.45 |================================================================= d . 67.07 |================================================================== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 21.85 |==================================================================== b . 21.97 |==================================================================== c . 21.94 |==================================================================== d . 21.92 |==================================================================== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 45.77 |==================================================================== b . 45.52 |==================================================================== c . 45.57 |==================================================================== d . 45.62 |==================================================================== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 110.18 |=================================================================== b . 110.72 |=================================================================== c . 110.56 |=================================================================== d . 110.54 |=================================================================== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 9.07349 |================================================================== b . 9.02988 |================================================================== c . 9.04234 |================================================================== d . 9.04455 |================================================================== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 120.23 |=================================================================== b . 112.27 |=============================================================== c . 112.24 |=============================================================== d . 112.08 |============================================================== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 8.31409 |============================================================== b . 8.90396 |================================================================== c . 8.90587 |================================================================== d . 8.91846 |================================================================== ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 51.89 |=================================================================== b . 52.33 |==================================================================== c . 51.74 |=================================================================== d . 52.05 |==================================================================== ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 19.27 |==================================================================== b . 19.11 |=================================================================== c . 19.33 |==================================================================== d . 19.21 |==================================================================== ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 72.60 |==================================================================== b . 72.87 |==================================================================== c . 72.76 |==================================================================== d . 50.84 |=============================================== ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 13.77 |================================================ b . 13.72 |=============================================== c . 13.74 |================================================ d . 19.66 |==================================================================== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 25.25 |=================================================================== b . 25.27 |=================================================================== c . 25.67 |==================================================================== d . 25.65 |==================================================================== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 39.60 |==================================================================== b . 39.57 |==================================================================== c . 38.95 |=================================================================== d . 38.98 |=================================================================== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 30.17 |==================================================================== b . 26.44 |============================================================ c . 29.95 |==================================================================== d . 27.81 |=============================================================== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 33.14 |============================================================ b . 37.82 |==================================================================== c . 33.38 |============================================================ d . 35.96 |=================================================================