dddd AMD Ryzen 7 7840HS testing with a Framework Laptop 16 (AMD Ryzen 7040 ) FRANMZCP07 (03.01 BIOS) and AMD Radeon 780M 512MB on Ubuntu 24.04 via the Phoronix Test Suite. a: Processor: AMD Ryzen 7 7840HS @ 5.29GHz (8 Cores / 16 Threads), Motherboard: Framework Laptop 16 (AMD Ryzen 7040 ) FRANMZCP07 (03.01 BIOS), Chipset: AMD Device 14e8, Memory: 2 x 8GB DDR5-5600MT/s A-DATA AD5S56008G-B, Disk: 512GB Western Digital PC SN810 SDCPNRY-512G, Graphics: AMD Radeon 780M 512MB, Audio: AMD Navi 31 HDMI/DP, Network: MEDIATEK MT7922 802.11ax PCI OS: Ubuntu 24.04, Kernel: 6.8.0-39-generic (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2~git2406200600.0ac0fb~oibaf~n (git-0ac0fbc 2024-06-20 noble-oibaf-ppa) (LLVM 17.0.6 DRM 3.57), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 2560x1600 aa: Processor: AMD Ryzen 7 7840HS @ 5.29GHz (8 Cores / 16 Threads), Motherboard: Framework Laptop 16 (AMD Ryzen 7040 ) FRANMZCP07 (03.01 BIOS), Chipset: AMD Device 14e8, Memory: 2 x 8GB DDR5-5600MT/s A-DATA AD5S56008G-B, Disk: 512GB Western Digital PC SN810 SDCPNRY-512G, Graphics: AMD Radeon 780M 512MB, Audio: AMD Navi 31 HDMI/DP, Network: MEDIATEK MT7922 802.11ax PCI OS: Ubuntu 24.04, Kernel: 6.8.0-40-generic (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2~git2406200600.0ac0fb~oibaf~n (git-0ac0fbc 2024-06-20 noble-oibaf-ppa) (LLVM 17.0.6 DRM 3.57), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 2560x1600 b: Processor: AMD Ryzen 7 7840HS @ 5.29GHz (8 Cores / 16 Threads), Motherboard: Framework Laptop 16 (AMD Ryzen 7040 ) FRANMZCP07 (03.01 BIOS), Chipset: AMD Device 14e8, Memory: 2 x 8GB DDR5-5600MT/s A-DATA AD5S56008G-B, Disk: 512GB Western Digital PC SN810 SDCPNRY-512G, Graphics: AMD Radeon 780M 512MB, Audio: AMD Navi 31 HDMI/DP, Network: MEDIATEK MT7922 802.11ax PCI OS: Ubuntu 24.04, Kernel: 6.8.0-40-generic (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2~git2406200600.0ac0fb~oibaf~n (git-0ac0fbc 2024-06-20 noble-oibaf-ppa) (LLVM 17.0.6 DRM 3.57), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 2560x1600 d: Processor: AMD Ryzen 7 7840HS @ 5.29GHz (8 Cores / 16 Threads), Motherboard: Framework Laptop 16 (AMD Ryzen 7040 ) FRANMZCP07 (03.01 BIOS), Chipset: AMD Device 14e8, Memory: 2 x 8GB DDR5-5600MT/s A-DATA AD5S56008G-B, Disk: 512GB Western Digital PC SN810 SDCPNRY-512G, Graphics: AMD Radeon 780M 512MB, Audio: AMD Navi 31 HDMI/DP, Network: MEDIATEK MT7922 802.11ax PCI OS: Ubuntu 24.04, Kernel: 6.8.0-40-generic (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2~git2406200600.0ac0fb~oibaf~n (git-0ac0fbc 2024-06-20 noble-oibaf-ppa) (LLVM 17.0.6 DRM 3.57), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 2560x1600 Unvanquished 0.55 Resolution: 1920 x 1080 - Effects Quality: High Frames Per Second > Higher Is Better a .. 460.1 |================================================================= aa . 473.3 |=================================================================== b .. 471.6 |=================================================================== d .. 472.3 |=================================================================== Unvanquished 0.55 Resolution: 1920 x 1200 - Effects Quality: High Frames Per Second > Higher Is Better a .. 437.5 |=================================================================== aa . 439.3 |=================================================================== b .. 438.0 |=================================================================== d .. 436.4 |=================================================================== Unvanquished 0.55 Resolution: 2560 x 1440 - Effects Quality: High Frames Per Second > Higher Is Better a .. 288.6 |=================================================================== aa . 289.6 |=================================================================== b .. 289.8 |=================================================================== d .. 288.7 |=================================================================== Unvanquished 0.55 Resolution: 2560 x 1600 - Effects Quality: High Frames Per Second > Higher Is Better a .. 266.5 |=================================================================== aa . 266.7 |=================================================================== b .. 266.4 |=================================================================== d .. 266.9 |=================================================================== Unvanquished 0.55 Resolution: 1920 x 1080 - Effects Quality: Ultra Frames Per Second > Higher Is Better a .. 418.2 |================================================================== aa . 417.3 |================================================================== b .. 416.3 |================================================================== d .. 422.2 |=================================================================== Unvanquished 0.55 Resolution: 1920 x 1200 - Effects Quality: Ultra Frames Per Second > Higher Is Better a .. 385.3 |=================================================================== aa . 384.1 |=================================================================== b .. 384.2 |=================================================================== d .. 380.8 |================================================================== Unvanquished 0.55 Resolution: 2560 x 1440 - Effects Quality: Ultra Frames Per Second > Higher Is Better a .. 253.4 |=================================================================== aa . 254.7 |=================================================================== b .. 253.9 |=================================================================== d .. 252.4 |================================================================== Unvanquished 0.55 Resolution: 2560 x 1600 - Effects Quality: Ultra Frames Per Second > Higher Is Better a .. 233.9 |=================================================================== aa . 234.6 |=================================================================== b .. 234.0 |=================================================================== d .. 235.0 |=================================================================== Unvanquished 0.55 Resolution: 1920 x 1080 - Effects Quality: Medium Frames Per Second > Higher Is Better a .. 542.5 |=================================================================== aa . 539.8 |=================================================================== b .. 542.4 |=================================================================== d .. 540.7 |=================================================================== Unvanquished 0.55 Resolution: 1920 x 1200 - Effects Quality: Medium Frames Per Second > Higher Is Better a .. 511.8 |================================================================== aa . 512.5 |================================================================== b .. 517.5 |=================================================================== d .. 504.8 |================================================================= Unvanquished 0.55 Resolution: 2560 x 1440 - Effects Quality: Medium Frames Per Second > Higher Is Better a .. 371.2 |=================================================================== aa . 373.2 |=================================================================== b .. 373.5 |=================================================================== d .. 373.4 |=================================================================== Unvanquished 0.55 Resolution: 2560 x 1600 - Effects Quality: Medium Frames Per Second > Higher Is Better a .. 336.0 |=================================================================== aa . 336.2 |=================================================================== b .. 336.6 |=================================================================== d .. 337.0 |=================================================================== ParaView 5.13 Test: Many Spheres - Frames: 600 - Resolution: 1920 x 1080 Frames / Sec > Higher Is Better a . 0.18 |===================================================================== ParaView 5.13 Test: Many Spheres - Frames: 600 - Resolution: 1920 x 1080 MiPolys / Sec > Higher Is Better a . 17.86 |==================================================================== ParaView 5.13 Test: Many Spheres - Frames: 600 - Resolution: 1920 x 1200 Frames / Sec > Higher Is Better a . 0.18 |===================================================================== ParaView 5.13 Test: Many Spheres - Frames: 600 - Resolution: 1920 x 1200 MiPolys / Sec > Higher Is Better a . 17.80 |==================================================================== ParaView 5.13 Test: Many Spheres - Frames: 600 - Resolution: 2560 x 1440 Frames / Sec > Higher Is Better a . 0.17 |===================================================================== ParaView 5.13 Test: Many Spheres - Frames: 600 - Resolution: 2560 x 1440 MiPolys / Sec > Higher Is Better a . 17.38 |==================================================================== CP2K Molecular Dynamics 2024.3 Input: H20-64 Seconds < Lower Is Better aa . 99.80 |================================================================== b .. 96.29 |=============================================================== d .. 100.10 |================================================================== CP2K Molecular Dynamics 2024.3 Input: H20-256 Seconds < Lower Is Better aa . 1002.99 |============================================================== b .. 1010.62 |============================================================== d .. 1052.13 |================================================================= CP2K Molecular Dynamics 2024.3 Input: Fayalite-FIST Seconds < Lower Is Better aa . 147.31 |=============================================================== b .. 154.83 |================================================================== d .. 151.94 |================================================================= NAMD 3.0 Input: ATPase with 327,506 Atoms ns/day > Higher Is Better aa . 1.32956 |================================================================= b .. 1.27220 |============================================================== d .. 1.28715 |=============================================================== NAMD 3.0 Input: STMV with 1,066,628 Atoms ns/day > Higher Is Better aa . 0.38378 |================================================================= b .. 0.37007 |=============================================================== d .. 0.37644 |================================================================ Epoch 4.19.4 Epoch3D Deck: Cone Seconds < Lower Is Better aa . 546.93 |================================================================= b .. 554.79 |================================================================== d .. 549.16 |================================================================= WarpX 24.10 Input: Uniform Plasma Seconds < Lower Is Better aa . 21.18 |================================================================= b .. 21.70 |=================================================================== d .. 21.71 |=================================================================== WarpX 24.10 Input: Plasma Acceleration Seconds < Lower Is Better aa . 55.37 |============================================================== b .. 56.63 |=============================================================== d .. 60.22 |=================================================================== BYTE Unix Benchmark 5.1.3-git Computational Test: Pipe LPS > Higher Is Better aa . 16671392.5 |========================================================= b .. 18027399.0 |============================================================== d .. 16434910.2 |========================================================= BYTE Unix Benchmark 5.1.3-git Computational Test: Dhrystone 2 LPS > Higher Is Better aa . 719195925.3 |========================================================= b .. 774189636.1 |============================================================= d .. 709502408.8 |======================================================== BYTE Unix Benchmark 5.1.3-git Computational Test: System Call LPS > Higher Is Better aa . 16049531.4 |========================================================= b .. 17367015.3 |============================================================== d .. 15836969.9 |========================================================= BYTE Unix Benchmark 5.1.3-git Computational Test: Whetstone Double MWIPS > Higher Is Better aa . 155612.4 |================================================================ b .. 137723.9 |========================================================= d .. 125618.1 |==================================================== SVT-AV1 2.3 Encoder Mode: Preset 3 - Input: Bosphorus 4K Frames Per Second > Higher Is Better aa . 4.169 |=================================================================== b .. 4.022 |================================================================= d .. 3.748 |============================================================ SVT-AV1 2.3 Encoder Mode: Preset 5 - Input: Bosphorus 4K Frames Per Second > Higher Is Better aa . 15.06 |=================================================================== b .. 14.52 |================================================================= d .. 13.96 |============================================================== SVT-AV1 2.3 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better aa . 49.91 |=================================================================== b .. 49.52 |================================================================== d .. 46.58 |=============================================================== SVT-AV1 2.3 Encoder Mode: Preset 13 - Input: Bosphorus 4K Frames Per Second > Higher Is Better aa . 121.14 |================================================================== b .. 119.37 |================================================================= d .. 114.05 |============================================================== SVT-AV1 2.3 Encoder Mode: Preset 3 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better aa . 14.29 |=================================================================== b .. 13.80 |================================================================= d .. 12.77 |============================================================ SVT-AV1 2.3 Encoder Mode: Preset 5 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better aa . 49.16 |=================================================================== b .. 47.19 |================================================================ d .. 44.33 |============================================================ SVT-AV1 2.3 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better aa . 163.33 |================================================================== b .. 160.58 |================================================================= d .. 149.78 |============================================================= SVT-AV1 2.3 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better aa . 497.58 |================================================================== b .. 489.20 |================================================================= d .. 460.22 |============================================================= SVT-AV1 2.3 Encoder Mode: Preset 3 - Input: Beauty 4K 10-bit Frames Per Second > Higher Is Better aa . 0.705 |=================================================================== b .. 0.674 |================================================================ d .. 0.619 |=========================================================== SVT-AV1 2.3 Encoder Mode: Preset 5 - Input: Beauty 4K 10-bit Frames Per Second > Higher Is Better aa . 3.119 |=================================================================== b .. 2.918 |=============================================================== d .. 2.659 |========================================================= SVT-AV1 2.3 Encoder Mode: Preset 8 - Input: Beauty 4K 10-bit Frames Per Second > Higher Is Better aa . 5.343 |=================================================================== b .. 4.909 |============================================================== d .. 4.484 |======================================================== SVT-AV1 2.3 Encoder Mode: Preset 13 - Input: Beauty 4K 10-bit Frames Per Second > Higher Is Better aa . 7.579 |=================================================================== b .. 6.830 |============================================================ d .. 6.224 |======================================================= Stockfish 17 Chess Benchmark Nodes Per Second > Higher Is Better aa . 21157157 |================================================================ b .. 20057178 |============================================================= d .. 20267956 |============================================================= Primesieve 12.5 Length: 1e12 Seconds < Lower Is Better aa . 15.38 |============================================================== b .. 15.34 |============================================================= d .. 16.75 |=================================================================== Primesieve 12.5 Length: 1e13 Seconds < Lower Is Better aa . 188.66 |============================================================ b .. 191.96 |============================================================= d .. 206.12 |================================================================== oneDNN 3.6 Harness: IP Shapes 1D - Engine: CPU ms < Lower Is Better aa . 2.51714 |=========================================================== b .. 2.54144 |=========================================================== d .. 2.79418 |================================================================= oneDNN 3.6 Harness: IP Shapes 3D - Engine: CPU ms < Lower Is Better aa . 4.57722 |================================================================ b .. 4.66200 |================================================================= d .. 4.66831 |================================================================= oneDNN 3.6 Harness: Convolution Batch Shapes Auto - Engine: CPU ms < Lower Is Better aa . 13.36 |=================================================================== b .. 13.33 |=================================================================== d .. 13.33 |=================================================================== oneDNN 3.6 Harness: Deconvolution Batch shapes_1d - Engine: CPU ms < Lower Is Better aa . 6.10289 |============================================================ b .. 6.13915 |============================================================= d .. 6.58308 |================================================================= oneDNN 3.6 Harness: Deconvolution Batch shapes_3d - Engine: CPU ms < Lower Is Better aa . 4.86939 |======================================================= b .. 4.92932 |======================================================== d .. 5.72961 |================================================================= oneDNN 3.6 Harness: Recurrent Neural Network Training - Engine: CPU ms < Lower Is Better aa . 3155.62 |============================================================= b .. 3104.92 |============================================================ d .. 3379.99 |================================================================= oneDNN 3.6 Harness: Recurrent Neural Network Inference - Engine: CPU ms < Lower Is Better aa . 1770.50 |============================================================== b .. 1727.88 |============================================================= d .. 1844.16 |================================================================= Opus Codec Encoding 1.5.2 WAV To Opus Encode Seconds < Lower Is Better aa . 22.17 |=================================================== b .. 26.28 |============================================================= d .. 28.91 |=================================================================== ASTC Encoder 5.0 Preset: Fast MT/s > Higher Is Better aa . 170.77 |================================================================== b .. 156.30 |============================================================ d .. 142.70 |======================================================= ASTC Encoder 5.0 Preset: Medium MT/s > Higher Is Better aa . 67.67 |=================================================================== b .. 62.17 |============================================================== d .. 56.73 |======================================================== ASTC Encoder 5.0 Preset: Thorough MT/s > Higher Is Better aa . 8.8155 |================================================================== b .. 8.1192 |============================================================= d .. 7.4152 |======================================================== ASTC Encoder 5.0 Preset: Exhaustive MT/s > Higher Is Better aa . 0.7361 |================================================================== b .. 0.6837 |============================================================= d .. 0.6236 |======================================================== ASTC Encoder 5.0 Preset: Very Thorough MT/s > Higher Is Better aa . 1.2075 |================================================================== b .. 1.1154 |============================================================= d .. 1.0170 |======================================================== LiteRT 2024-10-15 Model: DeepLab V3 Microseconds < Lower Is Better aa . 2125.78 |========================================================== b .. 2128.84 |========================================================== d .. 2378.54 |================================================================= LiteRT 2024-10-15 Model: SqueezeNet Microseconds < Lower Is Better aa . 2288.03 |=========================================================== b .. 2286.41 |=========================================================== d .. 2504.03 |================================================================= LiteRT 2024-10-15 Model: Inception V4 Microseconds < Lower Is Better aa . 33358.0 |============================================================ b .. 33308.8 |============================================================ d .. 36136.2 |================================================================= LiteRT 2024-10-15 Model: NASNet Mobile Microseconds < Lower Is Better aa . 7642.71 |========================================================== b .. 7816.00 |=========================================================== d .. 8630.17 |================================================================= LiteRT 2024-10-15 Model: Mobilenet Float Microseconds < Lower Is Better aa . 1527.48 |============================================================= b .. 1491.33 |============================================================ d .. 1622.81 |================================================================= LiteRT 2024-10-15 Model: Mobilenet Quant Microseconds < Lower Is Better aa . 1249.46 |======================================================== b .. 1276.41 |========================================================= d .. 1458.15 |================================================================= LiteRT 2024-10-15 Model: Inception ResNet V2 Microseconds < Lower Is Better aa . 28571.2 |============================================================= b .. 28254.4 |============================================================ d .. 30683.2 |================================================================= LiteRT 2024-10-15 Model: Quantized COCO SSD MobileNet v1 Microseconds < Lower Is Better aa . 2016.71 |====== b .. 22695.20 |================================================================ d .. 2338.08 |======= XNNPACK b7b048 Model: FP32MobileNetV1 us < Lower Is Better aa . 1536 |======= b .. 13914 |=================================================================== d .. 1617 |======== XNNPACK b7b048 Model: FP32MobileNetV2 us < Lower Is Better aa . 1057 |========== b .. 6981 |==================================================================== d .. 1130 |=========== XNNPACK b7b048 Model: FP32MobileNetV3Large us < Lower Is Better aa . 1255 |========= b .. 9205 |==================================================================== d .. 1319 |========== XNNPACK b7b048 Model: FP32MobileNetV3Small us < Lower Is Better aa . 465 |================ b .. 1998 |==================================================================== d .. 515 |================== XNNPACK b7b048 Model: FP16MobileNetV1 us < Lower Is Better aa . 1868 |==================== b .. 6239 |==================================================================== d .. 2169 |======================== XNNPACK b7b048 Model: FP16MobileNetV2 us < Lower Is Better aa . 1337 |======== b .. 10687 |=================================================================== d .. 1533 |========== XNNPACK b7b048 Model: FP16MobileNetV3Large us < Lower Is Better aa . 1429 |======== b .. 11295 |=================================================================== d .. 1602 |========== XNNPACK b7b048 Model: FP16MobileNetV3Small us < Lower Is Better aa . 581 |============================================================= b .. 606 |================================================================ d .. 654 |===================================================================== XNNPACK b7b048 Model: QS8MobileNetV2 us < Lower Is Better aa . 533 |=============================================================== b .. 526 |============================================================== d .. 581 |===================================================================== Apache Cassandra 5.0 Test: Writes Op/s > Higher Is Better aa . 115862 |================================================================== b .. 108743 |============================================================== d .. 100972 |========================================================== ONNX Runtime 1.19 Model: GPT-2 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better aa . 106.36 |================================================================== b .. 104.50 |================================================================= d .. 102.47 |================================================================ ONNX Runtime 1.19 Model: GPT-2 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better aa . 9.39903 |=============================================================== b .. 9.56576 |================================================================ d .. 9.75407 |================================================================= ONNX Runtime 1.19 Model: GPT-2 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better aa . 122.65 |================================================================= b .. 124.72 |================================================================== d .. 121.50 |================================================================ ONNX Runtime 1.19 Model: GPT-2 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better aa . 8.14774 |================================================================ b .. 8.01188 |=============================================================== d .. 8.22476 |================================================================= ONNX Runtime 1.19 Model: yolov4 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better aa . 6.61722 |================================================================= b .. 6.63616 |================================================================= d .. 5.74356 |======================================================== ONNX Runtime 1.19 Model: yolov4 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better aa . 151.12 |========================================================= b .. 150.69 |========================================================= d .. 174.11 |================================================================== ONNX Runtime 1.19 Model: yolov4 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better aa . 9.36551 |================================================================= b .. 5.90138 |========================================= d .. 8.72880 |============================================================= ONNX Runtime 1.19 Model: yolov4 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better aa . 106.77 |========================================== b .. 169.45 |================================================================== d .. 114.56 |============================================= ONNX Runtime 1.19 Model: ZFNet-512 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better aa . 62.66 |=================================================================== b .. 62.32 |=================================================================== d .. 56.74 |============================================================= ONNX Runtime 1.19 Model: ZFNet-512 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better aa . 15.96 |============================================================= b .. 16.05 |============================================================= d .. 17.62 |=================================================================== ONNX Runtime 1.19 Model: ZFNet-512 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better aa . 86.77 |=================================================================== b .. 60.47 |=============================================== d .. 57.42 |============================================ ONNX Runtime 1.19 Model: ZFNet-512 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better aa . 11.52 |============================================ b .. 16.54 |================================================================ d .. 17.41 |=================================================================== ONNX Runtime 1.19 Model: T5 Encoder - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better aa . 140.29 |================================================================== b .. 137.13 |================================================================= d .. 137.21 |================================================================= ONNX Runtime 1.19 Model: T5 Encoder - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better aa . 7.12656 |================================================================ b .. 7.29084 |================================================================= d .. 7.28642 |================================================================= ONNX Runtime 1.19 Model: T5 Encoder - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better aa . 142.37 |=============================================================== b .. 148.56 |================================================================== d .. 147.26 |================================================================= ONNX Runtime 1.19 Model: T5 Encoder - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better aa . 7.02169 |================================================================= b .. 6.72951 |============================================================== d .. 6.78853 |=============================================================== ONNX Runtime 1.19 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better aa . 9.11603 |================================================================= b .. 8.48061 |============================================================ d .. 8.13821 |========================================================== ONNX Runtime 1.19 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better aa . 109.70 |=========================================================== b .. 117.91 |=============================================================== d .. 122.88 |================================================================== ONNX Runtime 1.19 Model: bertsquad-12 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better aa . 15.78 |=================================================================== b .. 15.70 |=================================================================== d .. 12.63 |====================================================== ONNX Runtime 1.19 Model: bertsquad-12 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better aa . 63.37 |====================================================== b .. 63.71 |====================================================== d .. 79.18 |=================================================================== ONNX Runtime 1.19 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better aa . 456.27 |================================================================== b .. 456.34 |================================================================== d .. 434.39 |=============================================================== ONNX Runtime 1.19 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better aa . 2.19001 |============================================================== b .. 2.18961 |============================================================== d .. 2.30027 |================================================================= ONNX Runtime 1.19 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better aa . 498.19 |================================================================= b .. 502.55 |================================================================== d .. 479.39 |=============================================================== ONNX Runtime 1.19 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better aa . 2.00621 |=============================================================== b .. 1.98870 |============================================================== d .. 2.08476 |================================================================= ONNX Runtime 1.19 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better aa . 0.885190 |================================================================ b .. 0.763448 |======================================================= d .. 0.809516 |=========================================================== ONNX Runtime 1.19 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better aa . 1129.70 |======================================================== b .. 1309.84 |================================================================= d .. 1235.30 |============================================================= ONNX Runtime 1.19 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better aa . 1.59037 |================================================================= b .. 1.34498 |======================================================= d .. 0.79605 |================================= ONNX Runtime 1.19 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better aa . 628.78 |================================= b .. 743.50 |====================================== d .. 1256.20 |================================================================= ONNX Runtime 1.19 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better aa . 20.96 |=================================================================== b .. 20.26 |================================================================= d .. 18.14 |========================================================== ONNX Runtime 1.19 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better aa . 47.72 |========================================================== b .. 49.36 |============================================================ d .. 55.13 |=================================================================== ONNX Runtime 1.19 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better aa . 20.59 |=========================================== b .. 32.40 |=================================================================== d .. 30.30 |=============================================================== ONNX Runtime 1.19 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better aa . 48.56 |=================================================================== b .. 30.86 |=========================================== d .. 33.00 |============================================== ONNX Runtime 1.19 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better aa . 231.74 |================================================================== b .. 227.83 |================================================================= d .. 208.59 |=========================================================== ONNX Runtime 1.19 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better aa . 4.31466 |=========================================================== b .. 4.38853 |============================================================ d .. 4.79323 |================================================================= ONNX Runtime 1.19 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better aa . 243.29 |================================================================== b .. 225.30 |============================================================= d .. 209.12 |========================================================= ONNX Runtime 1.19 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better aa . 4.10903 |======================================================== b .. 4.43720 |============================================================ d .. 4.78049 |================================================================= ONNX Runtime 1.19 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better aa . 71.34 |=================================================================== b .. 68.13 |================================================================ d .. 61.25 |========================================================== ONNX Runtime 1.19 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better aa . 14.02 |========================================================== b .. 14.68 |============================================================ d .. 16.32 |=================================================================== ONNX Runtime 1.19 Model: super-resolution-10 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better aa . 113.98 |================================================================== b .. 111.03 |================================================================ d .. 101.97 |=========================================================== ONNX Runtime 1.19 Model: super-resolution-10 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better aa . 8.77190 |========================================================== b .. 9.00540 |============================================================ d .. 9.80512 |================================================================= ONNX Runtime 1.19 Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better aa . 0.466728 |================================================================ b .. 0.404181 |======================================================= d .. 0.356134 |================================================= ONNX Runtime 1.19 Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better aa . 2142.57 |================================================== b .. 2474.13 |========================================================= d .. 2807.93 |================================================================= ONNX Runtime 1.19 Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better aa . 0.729925 |================================================================ b .. 0.381099 |================================= d .. 0.611475 |====================================================== ONNX Runtime 1.19 Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better aa . 1370.00 |================================== b .. 2623.99 |================================================================= d .. 1635.39 |========================================= ONNX Runtime 1.19 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better aa . 40.20 |=================================================================== b .. 35.46 |=========================================================== d .. 33.28 |======================================================= ONNX Runtime 1.19 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better aa . 24.87 |======================================================= b .. 28.20 |=============================================================== d .. 30.04 |=================================================================== ONNX Runtime 1.19 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better aa . 52.40 |=================================================================== b .. 47.84 |============================================================= d .. 32.91 |========================================== ONNX Runtime 1.19 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better aa . 19.08 |========================================== b .. 20.90 |============================================== d .. 30.38 |=================================================================== Whisperfile 20Aug24 Model Size: Tiny Seconds < Lower Is Better aa . 55.19 |============================================================== b .. 58.16 |================================================================= d .. 59.90 |=================================================================== Whisperfile 20Aug24 Model Size: Small Seconds < Lower Is Better aa . 229.33 |============================================================== b .. 231.06 |=============================================================== d .. 243.97 |================================================================== Whisperfile 20Aug24 Model Size: Medium Seconds < Lower Is Better aa . 655.14 |=============================================================== b .. 657.64 |=============================================================== d .. 690.37 |==================================================================