12900k okt Intel Core i9-12900K testing with a ASUS ROG STRIX Z690-E GAMING WIFI (1720 BIOS) and llvmpipe on Ubuntu 22.04 via the Phoronix Test Suite. A: Processor: Intel Core i9-12900K @ 5.20GHz (16 Cores / 24 Threads), Motherboard: ASUS ROG STRIX Z690-E GAMING WIFI (1720 BIOS), Chipset: Intel Alder Lake-S PCH, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GB, Graphics: Intel DG2 8GB (2400MHz), Audio: Intel Alder Lake-S HD Audio, Monitor: ASUS VP28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411 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: Intel Core i9-12900K @ 5.20GHz (16 Cores / 24 Threads), Motherboard: ASUS ROG STRIX Z690-E GAMING WIFI (1720 BIOS), Chipset: Intel Alder Lake-S PCH, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GB, Graphics: Intel DG2 8GB (2400MHz), Audio: Intel Alder Lake-S HD Audio, Monitor: ASUS VP28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411 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: Intel Core i9-12900K @ 5.20GHz (16 Cores / 24 Threads), Motherboard: ASUS ROG STRIX Z690-E GAMING WIFI (1720 BIOS), Chipset: Intel Alder Lake-S PCH, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GB, Graphics: llvmpipe, Audio: Intel Alder Lake-S HD Audio, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411 OS: Ubuntu 22.04, Kernel: 5.17.0-1019-oem (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3, OpenGL: 4.5 Mesa 22.2.0-devel (git-44289c46d9) (LLVM 13.0.1 256 bits), Vulkan: 1.3.219, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 D: Processor: Intel Core i9-12900K @ 5.20GHz (16 Cores / 24 Threads), Motherboard: ASUS ROG STRIX Z690-E GAMING WIFI (1720 BIOS), Chipset: Intel Alder Lake-S PCH, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GB, Graphics: llvmpipe, Audio: Intel Alder Lake-S HD Audio, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411 OS: Ubuntu 22.04, Kernel: 5.17.0-1019-oem (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3, OpenGL: 4.5 Mesa 22.2.0-devel (git-44289c46d9) (LLVM 13.0.1 256 bits), Vulkan: 1.3.219, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 10.33 |==================================================================== B . 10.33 |==================================================================== C . 10.31 |==================================================================== D . 10.32 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 9.7302 |=================================================================== B . 9.7666 |=================================================================== C . 9.7475 |=================================================================== D . 9.7409 |=================================================================== 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 . 44.81 |=================================================================== B . 45.22 |==================================================================== C . 44.78 |=================================================================== D . 44.85 |=================================================================== 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 . 32.10 |==================================================================== B . 31.60 |=================================================================== C . 31.75 |=================================================================== D . 31.35 |================================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 69.47 |=================================================================== B . 69.53 |=================================================================== C . 69.44 |=================================================================== D . 70.32 |==================================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 57.29 |==================================================================== B . 56.89 |==================================================================== C . 56.85 |=================================================================== D . 56.78 |=================================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 138.12 |================================================================== B . 138.44 |================================================================== C . 136.60 |================================================================= D . 139.94 |=================================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 99.46 |==================================================================== B . 99.37 |==================================================================== C . 99.04 |==================================================================== D . 99.37 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 86.96 |==================================================================== B . 87.21 |==================================================================== C . 87.08 |==================================================================== D . 87.06 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 70.88 |==================================================================== B . 70.48 |=================================================================== C . 71.11 |==================================================================== D . 71.33 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 43.42 |==================================================================== B . 43.45 |==================================================================== C . 43.51 |==================================================================== D . 43.59 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 36.23 |==================================================================== B . 35.96 |=================================================================== C . 35.67 |=================================================================== D . 35.69 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 10.25 |================================================================== B . 10.31 |================================================================== C . 10.52 |==================================================================== D . 10.56 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 9.6708 |=================================================================== B . 9.6943 |=================================================================== C . 9.6862 |=================================================================== D . 9.6637 |=================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Only TPS > Higher Is Better A . 82889 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Write TPS > Higher Is Better A . 3587 |===================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 50 - Mode: Read Only TPS > Higher Is Better A . 801682 |=================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Only TPS > Higher Is Better A . 889537 |=================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Only TPS > Higher Is Better A . 738775 |=================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Only - Average Latency ms < Lower Is Better A . 0.012 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average Latency ms < Lower Is Better A . 0.279 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average Latency ms < Lower Is Better A . 0.062 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Only - Average Latency ms < Lower Is Better A . 0.112 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Only - Average Latency ms < Lower Is Better A . 0.338 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 751.72 |=================================================================== B . 751.24 |=================================================================== C . 753.52 |=================================================================== D . 751.12 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 102.77 |=================================================================== B . 102.39 |=================================================================== C . 102.59 |=================================================================== D . 102.66 |=================================================================== 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 . 177.09 |=================================================================== B . 176.08 |=================================================================== C . 177.18 |=================================================================== D . 177.15 |=================================================================== 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 . 31.15 |================================================================== B . 31.64 |=================================================================== C . 31.49 |=================================================================== D . 31.89 |==================================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 114.70 |=================================================================== B . 114.59 |=================================================================== C . 114.62 |=================================================================== D . 113.32 |================================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 17.45 |=================================================================== B . 17.57 |==================================================================== C . 17.59 |==================================================================== D . 17.61 |==================================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 57.82 |=================================================================== B . 57.65 |=================================================================== C . 58.43 |==================================================================== D . 57.10 |================================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 10.05 |==================================================================== B . 10.06 |==================================================================== C . 10.09 |==================================================================== D . 10.06 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 91.79 |==================================================================== B . 91.60 |==================================================================== C . 91.74 |==================================================================== D . 91.71 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 14.11 |==================================================================== B . 14.18 |==================================================================== C . 14.06 |=================================================================== D . 14.02 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 184.09 |=================================================================== B . 183.78 |=================================================================== C . 183.66 |=================================================================== D . 182.16 |================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 27.60 |=================================================================== B . 27.81 |=================================================================== C . 28.03 |==================================================================== D . 28.01 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 755.92 |=================================================================== B . 752.72 |=================================================================== C . 749.66 |================================================================== D . 748.31 |================================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 103.40 |=================================================================== B . 103.15 |=================================================================== C . 103.24 |=================================================================== D . 103.48 |=================================================================== OpenRadioss 2022.10.13 Model: Bumper Beam Seconds < Lower Is Better A . 123.73 |=================================================== B . 123.94 |=================================================== C . 163.44 |=================================================================== D . 161.02 |================================================================== OpenRadioss 2022.10.13 Model: Cell Phone Drop Test Seconds < Lower Is Better A . 77.11 |================================================== B . 75.31 |================================================= C . 101.73 |================================================================== D . 102.69 |=================================================================== OpenRadioss 2022.10.13 Model: Bird Strike on Windshield Seconds < Lower Is Better A . 253.61 |=================================================================== B . 200.58 |===================================================== C . 245.63 |================================================================= D . 247.09 |================================================================= OpenRadioss 2022.10.13 Model: Rubber O-Ring Seal Installation Seconds < Lower Is Better A . 175.49 |=================================================================== B . 127.49 |================================================ C . 176.46 |=================================================================== D . 175.67 |=================================================================== OpenRadioss 2022.10.13 Model: INIVOL and Fluid Structure Interaction Drop Container Seconds < Lower Is Better A . 376.04 |===================================================== B . 477.98 |=================================================================== C . 467.59 |================================================================== D . 475.39 |===================================================================