12600k 2023 intel alder lake Intel Core i5-12600K testing with a ASUS PRIME Z690-P WIFI D4 (0605 BIOS) and ASUS Intel ADL-S GT1 15GB on Ubuntu 22.04 via the Phoronix Test Suite. a: Processor: Intel Core i5-12600K @ 6.30GHz (10 Cores / 16 Threads), Motherboard: ASUS PRIME Z690-P WIFI D4 (0605 BIOS), Chipset: Intel Device 7aa7, Memory: 16GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: ASUS Intel ADL-S GT1 15GB (1450MHz), Audio: Realtek ALC897, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel Device 7af0 OS: Ubuntu 22.04, Kernel: 5.19.0-051900rc6daily20220716-generic (x86_64), Desktop: GNOME Shell 42.1, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.0.1, OpenCL: OpenCL 3.0, Vulkan: 1.2.204, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 3840x2160 b: Processor: Intel Core i5-12600K @ 6.30GHz (10 Cores / 16 Threads), Motherboard: ASUS PRIME Z690-P WIFI D4 (0605 BIOS), Chipset: Intel Device 7aa7, Memory: 16GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: ASUS Intel ADL-S GT1 15GB (1450MHz), Audio: Realtek ALC897, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel Device 7af0 OS: Ubuntu 22.04, Kernel: 5.19.0-051900rc6daily20220716-generic (x86_64), Desktop: GNOME Shell 42.1, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.0.1, OpenCL: OpenCL 3.0, Vulkan: 1.2.204, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 3840x2160 c: Processor: Intel Core i5-12600K @ 6.30GHz (10 Cores / 16 Threads), Motherboard: ASUS PRIME Z690-P WIFI D4 (0605 BIOS), Chipset: Intel Device 7aa7, Memory: 16GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: ASUS Intel ADL-S GT1 15GB (1450MHz), Audio: Realtek ALC897, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel Device 7af0 OS: Ubuntu 22.04, Kernel: 5.19.0-051900rc6daily20220716-generic (x86_64), Desktop: GNOME Shell 42.1, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.0.1, OpenCL: OpenCL 3.0, Vulkan: 1.2.204, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 3840x2160 OpenVINO 2022.3 Model: Weld Porosity Detection FP16 - Device: CPU ms < Lower Is Better a . 51.54 |==================================================================== b . 51.54 |==================================================================== c . 14.28 |=================== OpenVINO 2022.3 Model: Weld Porosity Detection FP16 - Device: CPU FPS > Higher Is Better a . 193.79 |============================================== b . 193.69 |============================================== c . 279.92 |=================================================================== AOM AV1 3.6 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 136.63 |======================================================== b . 140.24 |========================================================= c . 163.64 |=================================================================== AOM AV1 3.6 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 67.61 |========================================================== b . 79.57 |==================================================================== c . 79.17 |==================================================================== AOM AV1 3.6 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 61.03 |================================================================== b . 56.44 |============================================================= c . 63.33 |==================================================================== oneDNN 3.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1.086640 |================================================================= b . 0.990775 |=========================================================== c . 0.984883 |=========================================================== AOM AV1 3.6 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 164.98 |=================================================================== b . 163.82 |=================================================================== c . 149.70 |============================================================= RocksDB 7.9.2 Test: Sequential Fill Op/s > Higher Is Better a . 1148744 |=============================================================== b . 1196791 |================================================================== c . 1099266 |============================================================= AOM AV1 3.6 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 74.26 |=============================================================== b . 78.40 |=================================================================== c . 79.72 |==================================================================== ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run Queries Per Minute, Geo Mean > Higher Is Better a . 171.51 |=================================================================== b . 172.35 |=================================================================== c . 163.56 |================================================================ oneDNN 3.0 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 9.91932 |================================================================== b . 9.47685 |=============================================================== c . 9.46418 |=============================================================== SVT-AV1 1.4 Encoder Mode: Preset 12 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 114.11 |================================================================ b . 119.15 |=================================================================== c . 117.34 |================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 49.09 |==================================================================== b . 47.02 |================================================================= c . 48.61 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 101.79 |================================================================ b . 106.23 |=================================================================== c . 102.66 |================================================================= SVT-AV1 1.4 Encoder Mode: Preset 13 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 130.63 |================================================================ b . 135.92 |=================================================================== c . 135.24 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 105.94 |=================================================================== b . 102.00 |================================================================= c . 105.53 |=================================================================== AOM AV1 3.6 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 70.59 |================================================================= b . 72.39 |=================================================================== c . 73.29 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 47.17 |================================================================== b . 48.96 |==================================================================== c . 47.34 |================================================================== AOM AV1 3.6 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 166.34 |================================================================= b . 172.61 |=================================================================== c . 169.95 |================================================================== RocksDB 7.9.2 Test: Random Read Op/s > Higher Is Better a . 72263080 |================================================================= b . 69770221 |=============================================================== c . 72249376 |================================================================= Zstd Compression 1.5.4 Compression Level: 3, Long Mode - Compression Speed MB/s > Higher Is Better a . 972.3 |==================================================================== b . 950.0 |================================================================== c . 977.3 |==================================================================== SVT-AV1 1.4 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 470.00 |================================================================= b . 482.18 |=================================================================== c . 483.26 |=================================================================== ET: Legacy 2.81 Resolution: 1920 x 1080 Frames Per Second > Higher Is Better a . 150.3 |================================================================== b . 153.6 |==================================================================== c . 154.2 |==================================================================== SVT-AV1 1.4 Encoder Mode: Preset 4 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 9.676 |================================================================== b . 9.685 |================================================================== c . 9.910 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 16.48 |================================================================== b . 16.79 |==================================================================== c . 16.88 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 60.64 |==================================================================== b . 59.55 |=================================================================== c . 59.22 |================================================================== Stargate Digital Audio Workstation 22.11.5 Sample Rate: 192000 - Buffer Size: 512 Render Ratio > Higher Is Better a . 1.715890 |================================================================ b . 1.754839 |================================================================= c . 1.749982 |================================================================= Zstd Compression 1.5.4 Compression Level: 8 - Compression Speed MB/s > Higher Is Better a . 220.8 |================================================================== b . 225.8 |==================================================================== c . 225.4 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 27.77 |==================================================================== b . 27.44 |=================================================================== c . 27.19 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 36.00 |=================================================================== b . 36.44 |=================================================================== c . 36.78 |==================================================================== Embree 4.0 Binary: Pathtracer - Model: Crown Frames Per Second > Higher Is Better a . 12.49 |=================================================================== b . 12.68 |==================================================================== c . 12.76 |==================================================================== FluidX3D 2.3 Test: FP32-FP16S MLUPs/s > Higher Is Better a . 508 |====================================================================== b . 498 |===================================================================== c . 499 |===================================================================== GROMACS 2023 Implementation: MPI CPU - Input: water_GMX50_bare Ns Per Day > Higher Is Better a . 0.975 |==================================================================== b . 0.978 |==================================================================== c . 0.960 |=================================================================== OpenVINO 2022.3 Model: Weld Porosity Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 13.62 |==================================================================== b . 13.37 |=================================================================== c . 13.39 |=================================================================== OpenVINO 2022.3 Model: Weld Porosity Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 729.74 |================================================================== b . 743.26 |=================================================================== c . 742.24 |=================================================================== RocksDB 7.9.2 Test: Read While Writing Op/s > Higher Is Better a . 2058765 |================================================================= b . 2060652 |================================================================= c . 2095257 |================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 97.30 |==================================================================== b . 95.71 |=================================================================== c . 97.35 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 10.28 |=================================================================== b . 10.45 |==================================================================== c . 10.27 |=================================================================== oneDNN 3.0 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1.46294 |================================================================= b . 1.46343 |================================================================= c . 1.48795 |================================================================== Zstd Compression 1.5.4 Compression Level: 12 - Decompression Speed MB/s > Higher Is Better a . 2036.5 |================================================================== b . 2065.7 |=================================================================== c . 2069.1 |=================================================================== Embree 4.0 Binary: Pathtracer - Model: Asian Dragon Frames Per Second > Higher Is Better a . 14.77 |==================================================================== b . 14.54 |=================================================================== c . 14.77 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 32.90 |==================================================================== b . 32.70 |==================================================================== c . 32.39 |=================================================================== RocksDB 7.9.2 Test: Update Random Op/s > Higher Is Better a . 608982 |=================================================================== b . 600126 |================================================================== c . 609355 |=================================================================== Zstd Compression 1.5.4 Compression Level: 3 - Compression Speed MB/s > Higher Is Better a . 1873.1 |=================================================================== b . 1869.4 |=================================================================== c . 1844.8 |================================================================== ClickHouse 22.12.3.5 100M Rows Hits Dataset, First Run / Cold Cache Queries Per Minute, Geo Mean > Higher Is Better a . 153.25 |=================================================================== b . 152.82 |=================================================================== c . 150.99 |================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 151.81 |================================================================== b . 152.82 |================================================================== c . 154.08 |=================================================================== RocksDB 7.9.2 Test: Random Fill Sync Op/s > Higher Is Better a . 14849 |==================================================================== b . 14631 |=================================================================== c . 14657 |=================================================================== Embree 4.0 Binary: Pathtracer ISPC - Model: Crown Frames Per Second > Higher Is Better a . 13.69 |=================================================================== b . 13.89 |==================================================================== c . 13.87 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 48.96 |==================================================================== b . 48.81 |==================================================================== c . 48.28 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 20.42 |=================================================================== b . 20.49 |=================================================================== c . 20.71 |==================================================================== AOM AV1 3.6 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 161.35 |================================================================== b . 163.60 |=================================================================== c . 161.69 |================================================================== oneDNN 3.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 2.70187 |================================================================== b . 2.68101 |================================================================= c . 2.71814 |================================================================== SVT-AV1 1.4 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 110.06 |================================================================== b . 111.08 |=================================================================== c . 111.57 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 77.29 |==================================================================== b . 76.49 |=================================================================== c . 77.49 |==================================================================== Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast Frames Per Second > Higher Is Better a . 175.08 |================================================================== b . 177.32 |=================================================================== c . 176.51 |=================================================================== AOM AV1 3.6 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 17.35 |=================================================================== b . 17.56 |==================================================================== c . 17.57 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 164.18 |=================================================================== b . 163.85 |=================================================================== c . 162.14 |================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 64.54 |=================================================================== b . 65.32 |==================================================================== c . 64.51 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 30.45 |=================================================================== b . 30.44 |=================================================================== c . 30.82 |==================================================================== VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Faster Frames Per Second > Higher Is Better a . 8.133 |=================================================================== b . 8.227 |==================================================================== c . 8.165 |=================================================================== CockroachDB 22.2 Workload: MoVR - Concurrency: 128 ops/s > Higher Is Better a . 412.1 |==================================================================== b . 407.7 |=================================================================== c . 412.4 |==================================================================== Zstd Compression 1.5.4 Compression Level: 12 - Compression Speed MB/s > Higher Is Better a . 97.0 |===================================================================== b . 95.9 |==================================================================== c . 96.5 |===================================================================== Stargate Digital Audio Workstation 22.11.5 Sample Rate: 96000 - Buffer Size: 512 Render Ratio > Higher Is Better a . 2.709695 |================================================================ b . 2.739379 |================================================================= c . 2.731158 |================================================================= Stargate Digital Audio Workstation 22.11.5 Sample Rate: 44100 - Buffer Size: 512 Render Ratio > Higher Is Better a . 3.908665 |================================================================ b . 3.945383 |================================================================= c . 3.950512 |================================================================= Embree 4.0 Binary: Pathtracer ISPC - Model: Asian Dragon Frames Per Second > Higher Is Better a . 17.00 |=================================================================== b . 17.17 |==================================================================== c . 17.03 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 11.01 |=================================================================== b . 11.12 |==================================================================== c . 11.08 |==================================================================== OpenVINO 2022.3 Model: Vehicle Detection FP16 - Device: CPU FPS > Higher Is Better a . 202.76 |================================================================== b . 204.69 |=================================================================== c . 204.06 |=================================================================== Zstd Compression 1.5.4 Compression Level: 3 - Decompression Speed MB/s > Higher Is Better a . 1936.3 |=================================================================== b . 1918.1 |================================================================== c . 1921.9 |=================================================================== ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run Queries Per Minute, Geo Mean > Higher Is Better a . 170.82 |================================================================== b . 172.43 |=================================================================== c . 171.84 |=================================================================== VVenC 1.7 Video Input: Bosphorus 1080p - Video Preset: Faster Frames Per Second > Higher Is Better a . 25.03 |==================================================================== b . 24.79 |=================================================================== c . 24.90 |==================================================================== OpenVINO 2022.3 Model: Vehicle Detection FP16 - Device: CPU ms < Lower Is Better a . 19.71 |==================================================================== b . 19.53 |=================================================================== c . 19.58 |==================================================================== Embree 4.0 Binary: Pathtracer - Model: Asian Dragon Obj Frames Per Second > Higher Is Better a . 13.37 |=================================================================== b . 13.49 |==================================================================== c . 13.40 |==================================================================== Zstd Compression 1.5.4 Compression Level: 8 - Decompression Speed MB/s > Higher Is Better a . 2079.9 |=================================================================== b . 2061.3 |================================================================== c . 2064.4 |=================================================================== AOM AV1 3.6 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 12.61 |=================================================================== b . 12.72 |==================================================================== c . 12.70 |==================================================================== Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Very Fast Frames Per Second > Higher Is Better a . 99.79 |================================================================== b . 100.63 |=================================================================== c . 100.60 |=================================================================== SVT-AV1 1.4 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 521.73 |=================================================================== b . 520.74 |=================================================================== c . 517.39 |================================================================== oneDNN 3.0 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 12.55 |==================================================================== b . 12.48 |=================================================================== c . 12.58 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 446.00 |=================================================================== b . 442.78 |=================================================================== c . 444.21 |=================================================================== uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Slow Frames Per Second > Higher Is Better a . 32.35 |==================================================================== b . 32.58 |==================================================================== c . 32.42 |==================================================================== Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Medium Frames Per Second > Higher Is Better a . 49.71 |==================================================================== b . 49.53 |==================================================================== c . 49.36 |==================================================================== CockroachDB 22.2 Workload: KV, 10% Reads - Concurrency: 128 ops/s > Higher Is Better a . 44237.1 |================================================================== b . 44047.1 |================================================================== c . 43929.4 |================================================================== ET: Legacy 2.81 Resolution: 2560 x 1440 Frames Per Second > Higher Is Better a . 86.6 |===================================================================== b . 86.5 |===================================================================== c . 86.0 |===================================================================== CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 128 ops/s > Higher Is Better a . 56929.9 |================================================================== b . 56545.9 |================================================================== c . 56896.1 |================================================================== CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 128 ops/s > Higher Is Better a . 53622.6 |================================================================== b . 53329.2 |================================================================== c . 53689.5 |================================================================== OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU ms < Lower Is Better a . 1.49 |===================================================================== b . 1.50 |===================================================================== c . 1.50 |===================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 103.78 |=================================================================== b . 103.12 |=================================================================== c . 103.80 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 137.73 |=================================================================== b . 138.63 |=================================================================== c . 138.28 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 7.2603 |=================================================================== b . 7.2133 |=================================================================== c . 7.2317 |=================================================================== oneDNN 3.0 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 2.30066 |================================================================== b . 2.28589 |================================================================== c . 2.28705 |================================================================== OpenVINO 2022.3 Model: Person Vehicle Bike Detection FP16 - Device: CPU ms < Lower Is Better a . 11.03 |==================================================================== b . 11.06 |==================================================================== c . 11.10 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 39.65 |==================================================================== b . 39.48 |==================================================================== c . 39.72 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 25.21 |==================================================================== b . 25.32 |==================================================================== c . 25.17 |==================================================================== RocksDB 7.9.2 Test: Read Random Write Random Op/s > Higher Is Better a . 2016456 |================================================================== b . 2004326 |================================================================== c . 2012487 |================================================================== Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Frames Per Second > Higher Is Better a . 41.39 |==================================================================== b . 41.50 |==================================================================== c . 41.64 |==================================================================== Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Super Fast Frames Per Second > Higher Is Better a . 129.89 |=================================================================== b . 130.22 |=================================================================== c . 129.44 |=================================================================== OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU ms < Lower Is Better a . 1.66 |===================================================================== b . 1.67 |===================================================================== c . 1.67 |===================================================================== OpenVINO 2022.3 Model: Person Vehicle Bike Detection FP16 - Device: CPU FPS > Higher Is Better a . 362.19 |=================================================================== b . 361.30 |=================================================================== c . 360.04 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 48.16 |==================================================================== b . 48.40 |==================================================================== c . 48.12 |==================================================================== BRL-CAD 7.34 VGR Performance Metric VGR Performance Metric > Higher Is Better a . 221849 |=================================================================== b . 221135 |=================================================================== c . 222429 |=================================================================== Blender 3.4 Blend File: Classroom - Compute: CPU-Only Seconds < Lower Is Better a . 317.65 |=================================================================== b . 318.41 |=================================================================== c . 319.49 |=================================================================== OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU FPS > Higher Is Better a . 5690.26 |================================================================== b . 5674.99 |================================================================== c . 5657.60 |================================================================== OpenVINO 2022.3 Model: Person Detection FP32 - Device: CPU FPS > Higher Is Better a . 1.74 |===================================================================== b . 1.75 |===================================================================== c . 1.75 |===================================================================== uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast Frames Per Second > Higher Is Better a . 116.91 |=================================================================== b . 117.05 |=================================================================== c . 117.58 |=================================================================== OpenVKL 1.3.1 Benchmark: vklBenchmark ISPC Items / Sec > Higher Is Better a . 176 |====================================================================== b . 176 |====================================================================== c . 175 |====================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 13.58 |==================================================================== b . 13.57 |==================================================================== c . 13.64 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 73.64 |==================================================================== b . 73.69 |==================================================================== c . 73.29 |==================================================================== VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Fast Frames Per Second > Higher Is Better a . 3.835 |==================================================================== b . 3.826 |==================================================================== c . 3.816 |==================================================================== AOM AV1 3.6 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 41.27 |==================================================================== b . 41.47 |==================================================================== c . 41.32 |==================================================================== Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Decompression Speed MB/s > Higher Is Better a . 1728.1 |=================================================================== b . 1720.7 |=================================================================== c . 1729.0 |=================================================================== Blender 3.4 Blend File: Barbershop - Compute: CPU-Only Seconds < Lower Is Better a . 1253.26 |================================================================== b . 1247.27 |================================================================== c . 1247.42 |================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 7.8816 |=================================================================== b . 7.8447 |=================================================================== c . 7.8521 |=================================================================== oneDNN 3.0 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 2.09006 |================================================================== b . 2.08938 |================================================================== c . 2.09892 |================================================================== Timed Linux Kernel Compilation 6.1 Build: defconfig Seconds < Lower Is Better a . 83.01 |==================================================================== b . 83.07 |==================================================================== c . 82.70 |==================================================================== Zstd Compression 1.5.4 Compression Level: 19 - Decompression Speed MB/s > Higher Is Better a . 1809.4 |=================================================================== b . 1814.0 |=================================================================== c . 1817.2 |=================================================================== oneDNN 3.0 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 3.90670 |================================================================== b . 3.89382 |================================================================== c . 3.91022 |================================================================== AOM AV1 3.6 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 7.23 |===================================================================== b . 7.26 |===================================================================== c . 7.25 |===================================================================== uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Super Fast Frames Per Second > Higher Is Better a . 96.61 |==================================================================== b . 96.43 |==================================================================== c . 96.83 |==================================================================== VVenC 1.7 Video Input: Bosphorus 1080p - Video Preset: Fast Frames Per Second > Higher Is Better a . 10.34 |==================================================================== b . 10.30 |==================================================================== c . 10.32 |==================================================================== oneDNN 3.0 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 2.97547 |================================================================== b . 2.98663 |================================================================== c . 2.97941 |================================================================== uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Medium Frames Per Second > Higher Is Better a . 36.13 |==================================================================== b . 36.22 |==================================================================== c . 36.09 |==================================================================== RocksDB 7.9.2 Test: Random Fill Op/s > Higher Is Better a . 965627 |=================================================================== b . 962203 |=================================================================== c . 964297 |=================================================================== Stargate Digital Audio Workstation 22.11.5 Sample Rate: 480000 - Buffer Size: 512 Render Ratio > Higher Is Better a . 3.889646 |================================================================= b . 3.880546 |================================================================= c . 3.875918 |================================================================= Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 624.39 |=================================================================== b . 625.84 |=================================================================== c . 626.60 |=================================================================== OpenVINO 2022.3 Model: Machine Translation EN To DE FP16 - Device: CPU FPS > Higher Is Better a . 31.46 |==================================================================== b . 31.57 |==================================================================== c . 31.56 |==================================================================== Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Super Fast Frames Per Second > Higher Is Better a . 30.40 |==================================================================== b . 30.48 |==================================================================== c . 30.50 |==================================================================== CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 128 ops/s > Higher Is Better a . 73875.4 |================================================================== b . 73935.7 |================================================================== c . 73700.7 |================================================================== Blender 3.4 Blend File: Fishy Cat - Compute: CPU-Only Seconds < Lower Is Better a . 157.62 |=================================================================== b . 158.09 |=================================================================== c . 157.90 |=================================================================== oneDNN 3.0 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 10.73 |==================================================================== b . 10.70 |==================================================================== c . 10.73 |==================================================================== OpenVINO 2022.3 Model: Machine Translation EN To DE FP16 - Device: CPU ms < Lower Is Better a . 126.99 |=================================================================== b . 126.67 |=================================================================== c . 126.62 |=================================================================== OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU FPS > Higher Is Better a . 6331.79 |================================================================== b . 6334.00 |================================================================== c . 6315.81 |================================================================== SVT-AV1 1.4 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 39.82 |==================================================================== b . 39.82 |==================================================================== c . 39.93 |==================================================================== OpenVINO 2022.3 Model: Face Detection FP16 - Device: CPU ms < Lower Is Better a . 1494.59 |================================================================== b . 1496.41 |================================================================== c . 1492.29 |================================================================== Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Slow Frames Per Second > Higher Is Better a . 47.65 |==================================================================== b . 47.58 |==================================================================== c . 47.71 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 7.2945 |=================================================================== b . 7.2801 |=================================================================== c . 7.2999 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 137.08 |=================================================================== b . 137.36 |=================================================================== c . 136.98 |=================================================================== Zstd Compression 1.5.4 Compression Level: 8, Long Mode - Compression Speed MB/s > Higher Is Better a . 221.2 |==================================================================== b . 221.1 |==================================================================== c . 221.7 |==================================================================== Stargate Digital Audio Workstation 22.11.5 Sample Rate: 480000 - Buffer Size: 1024 Render Ratio > Higher Is Better a . 4.314579 |================================================================= b . 4.305519 |================================================================= c . 4.303267 |================================================================= Blender 3.4 Blend File: BMW27 - Compute: CPU-Only Seconds < Lower Is Better a . 108.75 |=================================================================== b . 108.73 |=================================================================== c . 109.01 |=================================================================== OpenVINO 2022.3 Model: Person Detection FP32 - Device: CPU ms < Lower Is Better a . 2256.65 |================================================================== b . 2253.13 |================================================================== c . 2251.10 |================================================================== oneDNN 3.0 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 14.45 |==================================================================== b . 14.46 |==================================================================== c . 14.48 |==================================================================== Embree 4.0 Binary: Pathtracer ISPC - Model: Asian Dragon Obj Frames Per Second > Higher Is Better a . 14.86 |==================================================================== b . 14.88 |==================================================================== c . 14.84 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 7.8994 |=================================================================== b . 7.8807 |=================================================================== c . 7.8890 |=================================================================== oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 4396.69 |================================================================== b . 4403.60 |================================================================== c . 4406.49 |================================================================== Zstd Compression 1.5.4 Compression Level: 8, Long Mode - Decompression Speed MB/s > Higher Is Better a . 2065.8 |=================================================================== b . 2070.4 |=================================================================== c . 2070.2 |=================================================================== Zstd Compression 1.5.4 Compression Level: 3, Long Mode - Decompression Speed MB/s > Higher Is Better a . 1956.6 |=================================================================== b . 1952.3 |=================================================================== c . 1953.8 |=================================================================== Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Compression Speed MB/s > Higher Is Better a . 9.20 |===================================================================== b . 9.21 |===================================================================== c . 9.22 |===================================================================== ET: Legacy 2.81 Resolution: 1920 x 1200 Frames Per Second > Higher Is Better a . 138.2 |==================================================================== b . 138.4 |==================================================================== c . 138.5 |==================================================================== Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Slow Frames Per Second > Higher Is Better a . 9.57 |===================================================================== b . 9.59 |===================================================================== c . 9.59 |===================================================================== Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium Frames Per Second > Higher Is Better a . 9.85 |===================================================================== b . 9.87 |===================================================================== c . 9.87 |===================================================================== Stargate Digital Audio Workstation 22.11.5 Sample Rate: 96000 - Buffer Size: 1024 Render Ratio > Higher Is Better a . 3.149404 |================================================================= b . 3.149566 |================================================================= c . 3.143371 |================================================================= SVT-AV1 1.4 Encoder Mode: Preset 4 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 3.104 |==================================================================== b . 3.107 |==================================================================== c . 3.101 |==================================================================== oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 4404.20 |================================================================== b . 4396.82 |================================================================== c . 4397.11 |================================================================== OpenVINO 2022.3 Model: Person Detection FP16 - Device: CPU ms < Lower Is Better a . 2255.62 |================================================================== b . 2253.25 |================================================================== c . 2251.89 |================================================================== Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Very Fast Frames Per Second > Higher Is Better a . 24.45 |==================================================================== b . 24.43 |==================================================================== c . 24.47 |==================================================================== uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Slow Frames Per Second > Higher Is Better a . 6.17 |===================================================================== b . 6.17 |===================================================================== c . 6.18 |===================================================================== Blender 3.4 Blend File: Pabellon Barcelona - Compute: CPU-Only Seconds < Lower Is Better a . 383.98 |=================================================================== b . 383.36 |=================================================================== c . 383.83 |=================================================================== uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Frames Per Second > Higher Is Better a . 25.88 |==================================================================== b . 25.87 |==================================================================== c . 25.91 |==================================================================== uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Medium Frames Per Second > Higher Is Better a . 6.97 |===================================================================== b . 6.98 |===================================================================== c . 6.97 |===================================================================== uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Super Fast Frames Per Second > Higher Is Better a . 21.32 |==================================================================== b . 21.30 |==================================================================== c . 21.29 |==================================================================== oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 2161.41 |================================================================== b . 2163.06 |================================================================== c . 2160.62 |================================================================== oneDNN 3.0 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 8.00328 |================================================================== b . 7.99647 |================================================================== c . 7.99461 |================================================================== oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 4401.46 |================================================================== b . 4398.13 |================================================================== c . 4402.72 |================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 623.58 |=================================================================== b . 624.21 |=================================================================== c . 623.70 |=================================================================== OpenVINO 2022.3 Model: Face Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 10.01 |==================================================================== b . 10.00 |==================================================================== c . 10.01 |==================================================================== oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 2159.93 |================================================================== b . 2160.83 |================================================================== c . 2158.91 |================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 53.64 |==================================================================== b . 53.69 |==================================================================== c . 53.65 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 18.64 |==================================================================== b . 18.62 |==================================================================== c . 18.64 |==================================================================== Stargate Digital Audio Workstation 22.11.5 Sample Rate: 44100 - Buffer Size: 1024 Render Ratio > Higher Is Better a . 4.323681 |================================================================= b . 4.322518 |================================================================= c . 4.325328 |================================================================= uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Very Fast Frames Per Second > Higher Is Better a . 90.14 |==================================================================== b . 90.19 |==================================================================== c . 90.15 |==================================================================== oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 2162.76 |================================================================== b . 2163.54 |================================================================== c . 2162.36 |================================================================== Timed Linux Kernel Compilation 6.1 Build: allmodconfig Seconds < Lower Is Better a . 1062.29 |================================================================== b . 1062.78 |================================================================== c . 1062.87 |================================================================== OpenVINO 2022.3 Model: Vehicle Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 482.44 |=================================================================== b . 482.26 |=================================================================== c . 482.51 |=================================================================== uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Very Fast Frames Per Second > Higher Is Better a . 20.27 |==================================================================== b . 20.26 |==================================================================== c . 20.27 |==================================================================== Stargate Digital Audio Workstation 22.11.5 Sample Rate: 192000 - Buffer Size: 1024 Render Ratio > Higher Is Better a . 2.078800 |================================================================= b . 2.078314 |================================================================= c . 2.078110 |================================================================= OpenVINO 2022.3 Model: Face Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 398.58 |=================================================================== b . 398.69 |=================================================================== c . 398.56 |=================================================================== OpenVINO 2022.3 Model: Vehicle Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 8.28 |===================================================================== b . 8.28 |===================================================================== c . 8.28 |===================================================================== OpenVINO 2022.3 Model: Person Detection FP16 - Device: CPU FPS > Higher Is Better a . 1.75 |===================================================================== b . 1.75 |===================================================================== c . 1.75 |===================================================================== OpenVINO 2022.3 Model: Face Detection FP16 - Device: CPU FPS > Higher Is Better a . 2.67 |===================================================================== b . 2.67 |===================================================================== c . 2.67 |===================================================================== OpenVKL 1.3.1 Benchmark: vklBenchmark Scalar Items / Sec > Higher Is Better a . 98 |======================================================================= b . 98 |======================================================================= c . 98 |======================================================================= AOM AV1 3.6 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 0.71 |===================================================================== b . 0.71 |===================================================================== c . 0.71 |===================================================================== AOM AV1 3.6 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 0.24 |===================================================================== b . 0.24 |===================================================================== c . 0.24 |===================================================================== Zstd Compression 1.5.4 Compression Level: 19 - Compression Speed MB/s > Higher Is Better a . 15.8 |===================================================================== b . 15.8 |===================================================================== c . 15.8 |===================================================================== FluidX3D 2.3 Test: FP32-FP16C MLUPs/s > Higher Is Better a . 294 |====================================================================== b . 294 |====================================================================== c . 294 |====================================================================== FluidX3D 2.3 Test: FP32-FP32 MLUPs/s > Higher Is Better a . 312 |====================================================================== b . 312 |====================================================================== c . 312 |====================================================================== ET: Legacy 2.81 Resolution: 3840 x 2160 Frames Per Second > Higher Is Better a . 38.7 |===================================================================== b . 38.7 |===================================================================== c . 38.7 |===================================================================== oneDNN 3.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 3.0 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 3.0 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 3.0 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 3.0 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 3.0 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better