5800x3d smoke okt AMD Ryzen 7 5800X3D 8-Core testing with a ASUS ROG CROSSHAIR VIII HERO (4201 BIOS) and Intel DG2 8GB on Ubuntu 22.04 via the Phoronix Test Suite. A: Processor: AMD Ryzen 7 5800X3D 8-Core @ 3.40GHz (8 Cores / 16 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (4201 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GB, Graphics: Intel DG2 8GB (2400MHz), Audio: Intel Device 4f90, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE + Intel I211 OS: Ubuntu 22.04, Kernel: 5.15.47+prerelease3723 (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.2.0-devel (git-44289c46d9), Vulkan: 1.3.219, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 B: Processor: AMD Ryzen 7 5800X3D 8-Core @ 3.40GHz (8 Cores / 16 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (4201 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GB, Graphics: Intel DG2 8GB (2400MHz), Audio: Intel Device 4f90, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE + Intel I211 OS: Ubuntu 22.04, Kernel: 5.15.47+prerelease3723 (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.2.0-devel (git-44289c46d9), Vulkan: 1.3.219, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 C: Processor: AMD Ryzen 7 5800X3D 8-Core @ 3.40GHz (8 Cores / 16 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (4201 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GB, Graphics: Intel DG2 8GB (2400MHz), Audio: Intel Device 4f90, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE + Intel I211 OS: Ubuntu 22.04, Kernel: 5.15.47+prerelease3723 (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.2.0-devel (git-44289c46d9), Vulkan: 1.3.219, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 D: Processor: AMD Ryzen 7 5800X3D 8-Core @ 3.40GHz (8 Cores / 16 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (4201 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GB, Graphics: Intel DG2 8GB (2400MHz), Audio: Intel Device 4f90, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE + Intel I211 OS: Ubuntu 22.04, Kernel: 5.15.47+prerelease3723 (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.2.0-devel (git-44289c46d9), Vulkan: 1.3.219, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: VGG-16 images/sec > Higher Is Better A . 5.86 |===================================================================== D . 5.88 |===================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: ResNet-50 images/sec > Higher Is Better A . 11.87 |==================================================================== D . 11.86 |==================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 512 - Model: GoogLeNet images/sec > Higher Is Better A . 36.02 |==================================================================== D . 35.96 |==================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: VGG-16 images/sec > Higher Is Better A . 5.94 |===================================================================== B . 5.95 |===================================================================== D . 5.93 |===================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: GoogLeNet images/sec > Higher Is Better A . 36.26 |==================================================================== D . 36.38 |==================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: VGG-16 images/sec > Higher Is Better A . 5.81 |===================================================================== B . 5.82 |===================================================================== D . 5.81 |===================================================================== OpenRadioss 2022.10.13 Model: INIVOL and Fluid Structure Interaction Drop Container Seconds < Lower Is Better A . 569.41 |=================================================================== B . 571.31 |=================================================================== C . 568.90 |=================================================================== D . 571.12 |=================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: ResNet-50 images/sec > Higher Is Better A . 12.65 |==================================================================== D . 12.67 |==================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 512 - Model: AlexNet images/sec > Higher Is Better A . 123.66 |=================================================================== D . 124.44 |=================================================================== SMHasher 2022-08-22 Hash: SHA3-256 cycles/hash < Lower Is Better A . 2033.50 |=============================================================== B . 1979.33 |============================================================== C . 2115.65 |================================================================== D . 1988.99 |============================================================== SMHasher 2022-08-22 Hash: SHA3-256 MiB/sec > Higher Is Better A . 191.23 |================================================================= B . 196.15 |=================================================================== C . 183.14 |=============================================================== D . 194.55 |================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: VGG-16 images/sec > Higher Is Better A . 5.55 |===================================================================== B . 5.55 |===================================================================== D . 5.55 |===================================================================== OpenRadioss 2022.10.13 Model: Bird Strike on Windshield Seconds < Lower Is Better A . 279.30 |================================================================ B . 291.67 |=================================================================== C . 279.49 |================================================================ D . 280.05 |================================================================ TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: ResNet-50 images/sec > Higher Is Better A . 13.53 |==================================================================== D . 13.58 |==================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: AlexNet images/sec > Higher Is Better A . 122.89 |=================================================================== D . 123.47 |=================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: GoogLeNet images/sec > Higher Is Better A . 37.81 |==================================================================== D . 37.85 |==================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 512 - Model: VGG-16 images/sec > Higher Is Better OpenRadioss 2022.10.13 Model: Rubber O-Ring Seal Installation Seconds < Lower Is Better A . 146.06 |=================================================================== B . 146.45 |=================================================================== C . 146.60 |=================================================================== D . 145.56 |=================================================================== OpenRadioss 2022.10.13 Model: Bumper Beam Seconds < Lower Is Better A . 144.69 |================================================================= B . 145.55 |================================================================= C . 149.29 |=================================================================== D . 145.41 |================================================================= PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency ms < Lower Is Better A . 2.564 |==================================================================== B . 2.540 |=================================================================== D . 2.519 |=================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Write TPS > Higher Is Better A . 38997 |=================================================================== B . 39365 |=================================================================== D . 39700 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 1 - Mode: Read Only - Average Latency ms < Lower Is Better A . 0.029 |================================================================== B . 0.030 |==================================================================== C . 0.029 |================================================================== D . 0.028 |=============================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 1 - Mode: Read Only TPS > Higher Is Better A . 34362 |================================================================== B . 33875 |================================================================= C . 34948 |=================================================================== D . 35562 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency ms < Lower Is Better A . 1.311 |==================================================================== B . 1.316 |==================================================================== D . 1.312 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 50 - Mode: Read Write TPS > Higher Is Better A . 38140 |==================================================================== B . 37994 |==================================================================== D . 38108 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency ms < Lower Is Better A . 0.336 |==================================================================== B . 0.334 |==================================================================== D . 0.332 |=================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Only TPS > Higher Is Better A . 297424 |================================================================== B . 299533 |=================================================================== D . 300952 |=================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 1 - Mode: Read Write - Average Latency ms < Lower Is Better A . 0.421 |==================================================================== B . 0.417 |=================================================================== D . 0.418 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 1 - Mode: Read Write TPS > Higher Is Better A . 2378 |==================================================================== B . 2400 |===================================================================== D . 2394 |===================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency ms < Lower Is Better A . 0.167 |==================================================================== B . 0.166 |==================================================================== D . 0.164 |=================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 50 - Mode: Read Only TPS > Higher Is Better A . 299777 |================================================================== B . 301135 |================================================================== D . 305622 |=================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Only - Average Latency ms < Lower Is Better A . 0.027 |================================================================== B . 0.028 |==================================================================== C . 0.028 |==================================================================== D . 0.028 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Only TPS > Higher Is Better A . 37199 |==================================================================== B . 35381 |================================================================= C . 35743 |================================================================= D . 35777 |================================================================= PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Write - Average Latency ms < Lower Is Better A . 34.95 |==================================================================== B . 35.02 |==================================================================== D . 34.81 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Write TPS > Higher Is Better A . 2861 |===================================================================== B . 2856 |===================================================================== D . 2873 |===================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average Latency ms < Lower Is Better A . 15.99 |==================================================================== B . 15.97 |==================================================================== C . 15.93 |==================================================================== D . 15.96 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 50 - Mode: Read Write TPS > Higher Is Better A . 3127 |===================================================================== B . 3131 |===================================================================== C . 3138 |===================================================================== D . 3133 |===================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average Latency ms < Lower Is Better A . 0.399 |=================================================================== B . 0.402 |==================================================================== C . 0.402 |==================================================================== D . 0.403 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Write TPS > Higher Is Better A . 2507 |===================================================================== B . 2488 |==================================================================== C . 2486 |==================================================================== D . 2484 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Only - Average Latency ms < Lower Is Better A . 0.325 |==================================================================== B . 0.323 |==================================================================== C . 0.325 |==================================================================== D . 0.322 |=================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Only TPS > Higher Is Better A . 307562 |================================================================== B . 309250 |=================================================================== C . 307586 |================================================================== D . 310891 |=================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average Latency ms < Lower Is Better A . 0.161 |==================================================================== B . 0.161 |==================================================================== C . 0.162 |==================================================================== D . 0.159 |=================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 50 - Mode: Read Only TPS > Higher Is Better A . 310942 |================================================================== B . 311138 |================================================================== C . 308393 |================================================================== D . 314549 |=================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: ResNet-50 images/sec > Higher Is Better A . 14.55 |==================================================================== D . 14.49 |==================================================================== OpenRadioss 2022.10.13 Model: Cell Phone Drop Test Seconds < Lower Is Better A . 100.35 |================================================================= B . 100.26 |================================================================= C . 100.11 |================================================================= D . 103.13 |=================================================================== AOM AV1 3.5 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 7.61 |==================================================================== B . 7.69 |===================================================================== C . 7.66 |===================================================================== D . 7.67 |===================================================================== AOM AV1 3.5 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 0.21 |===================================================================== B . 0.21 |===================================================================== C . 0.21 |===================================================================== D . 0.21 |===================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: GoogLeNet images/sec > Higher Is Better A . 39.37 |==================================================================== D . 39.35 |==================================================================== spaCy 3.4.1 Model: en_core_web_trf tokens/sec > Higher Is Better A . 740 |===================================================================== B . 748 |===================================================================== C . 756 |====================================================================== D . 747 |===================================================================== spaCy 3.4.1 Model: en_core_web_lg tokens/sec > Higher Is Better A . 15416 |==================================================================== B . 15357 |==================================================================== C . 15401 |==================================================================== D . 15424 |==================================================================== oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 2717.67 |================================================================== B . 2701.46 |================================================================= C . 2711.47 |================================================================== D . 2726.78 |================================================================== oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 2724.50 |================================================================== B . 2715.72 |================================================================== C . 2719.71 |================================================================== D . 2722.90 |================================================================== oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 2724.19 |================================================================== B . 2707.34 |================================================================== C . 2717.02 |================================================================== D . 2721.31 |================================================================== oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 1400.14 |================================================================== B . 1388.94 |================================================================= C . 1393.85 |================================================================== D . 1393.64 |================================================================== oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 1395.86 |================================================================== B . 1389.29 |================================================================== C . 1391.77 |================================================================== D . 1393.37 |================================================================== oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 1392.31 |================================================================== B . 1385.11 |================================================================== C . 1389.43 |================================================================== D . 1390.76 |================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: AlexNet images/sec > Higher Is Better A . 109.77 |=================================================================== D . 109.92 |=================================================================== AOM AV1 3.5 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 14.43 |=================================================================== B . 14.67 |==================================================================== C . 14.52 |=================================================================== D . 14.53 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 482.49 |=================================================================== B . 484.97 |=================================================================== D . 478.28 |================================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 8.2900 |=================================================================== B . 8.2282 |================================================================== D . 8.3401 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 113.46 |=================================================================== B . 114.29 |=================================================================== D . 113.52 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 35.25 |==================================================================== B . 34.99 |=================================================================== D . 35.23 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 117.01 |=================================================================== B . 117.46 |=================================================================== D . 116.50 |================================================================== Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 34.18 |==================================================================== B . 34.05 |=================================================================== D . 34.33 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 478.97 |=================================================================== B . 480.44 |=================================================================== D . 476.77 |================================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 8.3235 |=================================================================== B . 8.3116 |=================================================================== D . 8.3717 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 33.27 |==================================================================== B . 33.30 |==================================================================== D . 33.33 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 30.05 |==================================================================== B . 30.02 |==================================================================== D . 30.00 |==================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: GoogLeNet images/sec > Higher Is Better A . 41.31 |==================================================================== D . 41.39 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 123.95 |=================================================================== B . 124.43 |=================================================================== D . 123.70 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 8.0673 |=================================================================== B . 8.0362 |=================================================================== D . 8.0834 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 123.03 |=================================================================== B . 123.90 |=================================================================== D . 123.72 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 8.1277 |=================================================================== B . 8.0704 |=================================================================== D . 8.0822 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 33.20 |==================================================================== B . 33.24 |==================================================================== D . 33.15 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 30.11 |==================================================================== B . 30.08 |==================================================================== D . 30.16 |==================================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 22.23 |==================================================================== B . 22.19 |==================================================================== D . 22.22 |==================================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 44.98 |==================================================================== B . 45.05 |==================================================================== D . 44.99 |==================================================================== Y-Cruncher 0.7.10.9513 Pi Digits To Calculate: 1B Seconds < Lower Is Better A . 39.19 |==================================================================== B . 39.03 |==================================================================== C . 39.05 |==================================================================== D . 39.24 |==================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: AlexNet images/sec > Higher Is Better A . 91.50 |==================================================================== D . 91.54 |==================================================================== AOM AV1 3.5 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 17.71 |==================================================================== B . 17.71 |==================================================================== C . 17.73 |==================================================================== D . 17.59 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 55.75 |==================================================================== B . 55.82 |==================================================================== D . 55.70 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 71.73 |==================================================================== B . 71.64 |==================================================================== D . 71.79 |==================================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 42.06 |==================================================================== B . 42.06 |==================================================================== D . 42.06 |==================================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 95.07 |==================================================================== B . 95.07 |==================================================================== D . 95.06 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 16.59 |==================================================================== B . 16.43 |=================================================================== D . 16.52 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 60.26 |=================================================================== B . 60.85 |==================================================================== D . 60.52 |==================================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 87.11 |==================================================================== B . 86.78 |==================================================================== D . 85.93 |=================================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 45.91 |=================================================================== B . 46.08 |=================================================================== D . 46.51 |==================================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 11.82 |==================================================================== B . 11.83 |==================================================================== D . 11.83 |==================================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 84.57 |==================================================================== B . 84.50 |==================================================================== D . 84.53 |==================================================================== AOM AV1 3.5 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 0.64 |===================================================================== B . 0.64 |===================================================================== C . 0.64 |===================================================================== D . 0.64 |===================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: AlexNet images/sec > Higher Is Better A . 68.32 |==================================================================== B . 68.45 |==================================================================== D . 68.16 |==================================================================== QuadRay 2022.05.25 Scene: 5 - Resolution: 4K FPS > Higher Is Better A . 0.53 |===================================================================== B . 0.53 |===================================================================== C . 0.53 |===================================================================== D . 0.53 |===================================================================== oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 7.23318 |================================================================= B . 6.83968 |============================================================= C . 7.37916 |================================================================== D . 7.10311 |================================================================ oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 1.79935 |================================================================== B . 1.79390 |================================================================== C . 1.79785 |================================================================== D . 1.79717 |================================================================== QuadRay 2022.05.25 Scene: 3 - Resolution: 4K FPS > Higher Is Better A . 1.96 |==================================================================== B . 1.98 |===================================================================== C . 1.97 |===================================================================== D . 1.98 |===================================================================== QuadRay 2022.05.25 Scene: 2 - Resolution: 4K FPS > Higher Is Better A . 2.30 |===================================================================== B . 2.31 |===================================================================== C . 2.31 |===================================================================== D . 2.30 |===================================================================== QuadRay 2022.05.25 Scene: 1 - Resolution: 4K FPS > Higher Is Better A . 8.42 |===================================================================== B . 8.43 |===================================================================== C . 8.38 |===================================================================== D . 8.40 |===================================================================== QuadRay 2022.05.25 Scene: 5 - Resolution: 1080p FPS > Higher Is Better A . 2.14 |===================================================================== B . 2.14 |===================================================================== C . 2.14 |===================================================================== D . 2.14 |===================================================================== QuadRay 2022.05.25 Scene: 2 - Resolution: 1080p FPS > Higher Is Better A . 8.80 |=================================================================== B . 9.00 |===================================================================== C . 8.90 |==================================================================== D . 8.97 |===================================================================== QuadRay 2022.05.25 Scene: 3 - Resolution: 1080p FPS > Higher Is Better A . 7.70 |===================================================================== B . 7.75 |===================================================================== C . 7.62 |==================================================================== D . 7.67 |==================================================================== QuadRay 2022.05.25 Scene: 1 - Resolution: 1080p FPS > Higher Is Better A . 32.62 |==================================================================== B . 32.77 |==================================================================== C . 32.66 |==================================================================== D . 32.60 |==================================================================== Y-Cruncher 0.7.10.9513 Pi Digits To Calculate: 500M Seconds < Lower Is Better A . 17.74 |==================================================================== B . 17.61 |=================================================================== C . 17.70 |==================================================================== D . 17.83 |==================================================================== AOM AV1 3.5 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 36.34 |=================================================================== B . 36.61 |==================================================================== C . 36.36 |==================================================================== D . 36.52 |==================================================================== AOM AV1 3.5 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 44.51 |=================================================================== B . 44.99 |==================================================================== C . 44.92 |==================================================================== D . 45.05 |==================================================================== oneDNN 2.7 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 2.93636 |================================================================== B . 2.91481 |================================================================== C . 2.91791 |================================================================== D . 2.93008 |================================================================== oneDNN 2.7 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 1.24936 |================================================================== B . 1.24604 |================================================================== C . 1.24858 |================================================================== D . 1.24944 |================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 512 - Model: ResNet-50 images/sec > Higher Is Better oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 1.08635 |================================================================== B . 1.07920 |================================================================== C . 1.08253 |================================================================== D . 1.08663 |================================================================== oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 0.847434 |================================================================= B . 0.841664 |================================================================= C . 0.840243 |================================================================ D . 0.844385 |================================================================= SMHasher 2022-08-22 Hash: FarmHash128 cycles/hash < Lower Is Better A . 55.27 |==================================================================== B . 55.26 |==================================================================== C . 55.25 |==================================================================== D . 55.26 |==================================================================== SMHasher 2022-08-22 Hash: FarmHash128 MiB/sec > Higher Is Better A . 17295.31 |================================================================ B . 17506.62 |================================================================= C . 17175.32 |================================================================ D . 17426.17 |================================================================= AOM AV1 3.5 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 58.95 |==================================================================== B . 58.84 |==================================================================== C . 58.18 |=================================================================== D . 58.14 |=================================================================== SMHasher 2022-08-22 Hash: MeowHash x86_64 AES-NI cycles/hash < Lower Is Better A . 50.11 |==================================================================== B . 50.10 |==================================================================== C . 50.11 |==================================================================== D . 50.25 |==================================================================== SMHasher 2022-08-22 Hash: MeowHash x86_64 AES-NI MiB/sec > Higher Is Better A . 45994.36 |================================================================= B . 45752.01 |================================================================= C . 45844.24 |================================================================= D . 45447.31 |================================================================ oneDNN 2.7 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 6.73091 |=========================================================== B . 6.80659 |============================================================ C . 7.43205 |================================================================= D . 7.50774 |================================================================== oneDNN 2.7 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 0.608646 |================================================================ B . 0.610055 |================================================================= C . 0.610944 |================================================================= D . 0.613447 |================================================================= AOM AV1 3.5 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 74.81 |==================================================================== B . 73.60 |=================================================================== C . 74.15 |=================================================================== D . 73.14 |================================================================== AOM AV1 3.5 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 80.78 |=================================================================== B . 81.58 |==================================================================== C . 81.46 |==================================================================== D . 81.04 |==================================================================== AOM AV1 3.5 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 84.14 |=================================================================== B . 85.07 |==================================================================== C . 83.56 |=================================================================== D . 84.35 |=================================================================== SMHasher 2022-08-22 Hash: Spooky32 cycles/hash < Lower Is Better A . 31.72 |==================================================================== B . 31.65 |=================================================================== C . 31.90 |==================================================================== D . 31.55 |=================================================================== SMHasher 2022-08-22 Hash: Spooky32 MiB/sec > Higher Is Better A . 19181.60 |================================================================= B . 19233.26 |================================================================= C . 19034.70 |================================================================ D . 19265.23 |================================================================= SMHasher 2022-08-22 Hash: FarmHash32 x86_64 AVX cycles/hash < Lower Is Better A . 30.29 |=============================================================== B . 30.29 |=============================================================== C . 30.32 |=============================================================== D . 32.56 |==================================================================== SMHasher 2022-08-22 Hash: FarmHash32 x86_64 AVX MiB/sec > Higher Is Better A . 33756.46 |================================================================ B . 34042.82 |================================================================= C . 33899.05 |================================================================= D . 34051.80 |================================================================= SMHasher 2022-08-22 Hash: fasthash32 cycles/hash < Lower Is Better A . 25.97 |==================================================================== B . 25.73 |=================================================================== C . 25.81 |==================================================================== D . 25.75 |=================================================================== SMHasher 2022-08-22 Hash: fasthash32 MiB/sec > Higher Is Better A . 7536.68 |================================================================= B . 7602.61 |================================================================== C . 7573.13 |================================================================== D . 7589.92 |================================================================== SMHasher 2022-08-22 Hash: t1ha2_atonce cycles/hash < Lower Is Better A . 24.32 |==================================================================== B . 24.12 |=================================================================== C . 24.09 |=================================================================== D . 24.06 |=================================================================== SMHasher 2022-08-22 Hash: t1ha2_atonce MiB/sec > Higher Is Better A . 19795.33 |================================================================ B . 19752.83 |================================================================ C . 20051.08 |================================================================= D . 19749.24 |================================================================ oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 12.79 |================================================================= B . 12.87 |================================================================== C . 13.24 |=================================================================== D . 13.35 |==================================================================== oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 11.89 |==================================================================== B . 10.67 |============================================================= C . 11.18 |================================================================ D . 11.37 |================================================================= SMHasher 2022-08-22 Hash: t1ha0_aes_avx2 x86_64 cycles/hash < Lower Is Better A . 23.25 |==================================================================== B . 23.06 |=================================================================== C . 23.09 |==================================================================== D . 23.06 |=================================================================== SMHasher 2022-08-22 Hash: t1ha0_aes_avx2 x86_64 MiB/sec > Higher Is Better A . 77605.07 |================================================================= B . 73947.90 |============================================================== C . 74795.04 |=============================================================== D . 75226.23 |=============================================================== SMHasher 2022-08-22 Hash: wyhash cycles/hash < Lower Is Better A . 16.25 |================================================================== B . 16.30 |================================================================== C . 16.21 |================================================================== D . 16.75 |==================================================================== SMHasher 2022-08-22 Hash: wyhash MiB/sec > Higher Is Better A . 26419.11 |================================================================= B . 26334.38 |================================================================= C . 26302.30 |================================================================= D . 25891.34 |================================================================ AOM AV1 3.5 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 156.10 |=================================================================== B . 155.18 |=================================================================== C . 154.69 |================================================================== D . 155.73 |=================================================================== AOM AV1 3.5 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 189.92 |=================================================================== B . 189.67 |=================================================================== C . 188.95 |=================================================================== D . 189.14 |=================================================================== AOM AV1 3.5 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 199.11 |=================================================================== B . 200.46 |=================================================================== C . 194.65 |================================================================= D . 198.99 |=================================================================== oneDNN 2.7 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 5.61357 |================================================================== B . 5.59992 |================================================================== C . 5.61586 |================================================================== D . 5.61171 |================================================================== oneDNN 2.7 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 2.52002 |================================================================= B . 2.48677 |================================================================= C . 2.54366 |================================================================== D . 2.53624 |================================================================== oneDNN 2.7 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.7 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better