cascade lake refresh 2 x Intel Xeon Gold 5220R testing with a TYAN S7106 (V2.01.B40 BIOS) and ASPEED on Ubuntu 20.04 via the Phoronix Test Suite. a: Processor: 2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads), Motherboard: TYAN S7106 (V2.01.B40 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 94GB, Disk: 500GB Samsung SSD 860, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel I210 + 2 x QLogic cLOM8214 1/10GbE OS: Ubuntu 20.04, Kernel: 5.9.0-050900rc6-generic (x86_64) 20200920, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.13, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 1920x1080 b: Processor: 2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads), Motherboard: TYAN S7106 (V2.01.B40 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 94GB, Disk: 500GB Samsung SSD 860, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel I210 + 2 x QLogic cLOM8214 1/10GbE OS: Ubuntu 20.04, Kernel: 5.9.0-050900rc6-generic (x86_64) 20200920, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.13, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 1920x1080 PostgreSQL 15 Scaling Factor: 100 - Clients: 1 - Mode: Read Write TPS > Higher Is Better a . 671 |====================================================================== b . 326 |================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 1 - Mode: Read Write - Average Latency ms < Lower Is Better a . 1.491 |================================= b . 3.065 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Write - Average Latency ms < Lower Is Better a . 565.86 |====================================== b . 985.48 |=================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Write TPS > Higher Is Better a . 442 |====================================================================== b . 254 |======================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 2.50 |===================================================================== b . 1.54 |=========================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Repartition Test Time Seconds < Lower Is Better a . 2.63 |============================================ b . 4.09 |===================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Write TPS > Higher Is Better a . 297 |====================================================================== b . 201 |=============================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Write - Average Latency ms < Lower Is Better a . 1682.55 |============================================= b . 2481.62 |================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 4.26 |=============================================== b . 6.22 |===================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Write TPS > Higher Is Better a . 623 |====================================================================== b . 431 |================================================ PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Write - Average Latency ms < Lower Is Better a . 160.47 |============================================== b . 231.89 |=================================================================== ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, First Run / Cold Cache Queries Per Minute, Geo Mean > Higher Is Better a . 142.18 |============================================== b . 205.30 |=================================================================== LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: Rhodopsin Protein ns/day > Higher Is Better a . 17.95 |==================================================================== b . 13.09 |================================================== Stress-NG 0.14.06 Test: Socket Activity Bogo Ops/s > Higher Is Better a . 26882.84 |================================================================= b . 20197.23 |================================================= Stargate Digital Audio Workstation 22.11.5 Sample Rate: 480000 - Buffer Size: 512 Render Ratio > Higher Is Better a . 3.394244 |================================================================= b . 2.559217 |================================================= Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 1:1 Ops/sec > Higher Is Better a . 707625.49 |================================================= b . 930057.66 |================================================================ Stargate Digital Audio Workstation 22.11.5 Sample Rate: 96000 - Buffer Size: 1024 Render Ratio > Higher Is Better a . 2.617020 |================================================================= b . 2.019155 |================================================== CockroachDB 22.2 Workload: KV, 10% Reads - Concurrency: 256 ops/s > Higher Is Better a . 13759.6 |===================================================== b . 17242.8 |================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - Inner Join Test Time Seconds < Lower Is Better a . 4.67 |======================================================= b . 5.81 |===================================================================== OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU ms < Lower Is Better a . 0.98 |========================================================= b . 1.18 |===================================================================== OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU FPS > Higher Is Better a . 36342.30 |================================================================= b . 30254.31 |====================================================== Stress-NG 0.14.06 Test: CPU Cache Bogo Ops/s > Higher Is Better a . 89.3 |===================================================================== b . 76.5 |=========================================================== TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: ResNet-50 images/sec > Higher Is Better a . 19.21 |========================================================== b . 22.42 |==================================================================== CockroachDB 22.2 Workload: KV, 10% Reads - Concurrency: 512 ops/s > Higher Is Better a . 29267.4 |========================================================= b . 34085.9 |================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency ms < Lower Is Better a . 9.744 |========================================================== b . 11.326 |=================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 50 - Mode: Read Write TPS > Higher Is Better a . 5131 |===================================================================== b . 4415 |=========================================================== EnCodec 0.1.1 Target Bandwidth: 3 kbps Seconds < Lower Is Better a . 40.41 |==================================================================== b . 35.12 |=========================================================== CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 512 ops/s > Higher Is Better a . 58375.2 |========================================================== b . 66868.9 |================================================================== oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 784.13 |=========================================================== b . 892.23 |=================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Inner Join Test Time Seconds < Lower Is Better a . 3.23 |===================================================================== b . 2.84 |============================================================= CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 128 ops/s > Higher Is Better a . 12434.3 |================================================================== b . 10945.5 |========================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Write TPS > Higher Is Better a . 812 |====================================================================== b . 718 |============================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average Latency ms < Lower Is Better a . 1.231 |============================================================ b . 1.392 |==================================================================== CockroachDB 22.2 Workload: MoVR - Concurrency: 256 ops/s > Higher Is Better a . 202.9 |============================================================ b . 228.8 |==================================================================== Stress-NG 0.14.06 Test: Context Switching Bogo Ops/s > Higher Is Better a . 6260590.45 |======================================================== b . 7049324.49 |=============================================================== Dragonflydb 0.6 Clients: 200 - Set To Get Ratio: 5:1 Ops/sec > Higher Is Better a . 942134.52 |================================================================ b . 839630.53 |========================================================= Dragonflydb 0.6 Clients: 200 - Set To Get Ratio: 1:1 Ops/sec > Higher Is Better a . 994293.90 |================================================================ b . 890721.27 |========================================================= Facebook RocksDB 7.5.3 Test: Random Read Op/s > Higher Is Better a . 107719684 |========================================================= b . 120010661 |================================================================ Dragonflydb 0.6 Clients: 200 - Set To Get Ratio: 1:5 Ops/sec > Higher Is Better a . 1044459.26 |=============================================================== b . 937646.51 |========================================================= Stargate Digital Audio Workstation 22.11.5 Sample Rate: 480000 - Buffer Size: 1024 Render Ratio > Higher Is Better a . 2.90554 |=========================================================== b . 3.23369 |================================================================== ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, Third Run Queries Per Minute, Geo Mean > Higher Is Better a . 198.59 |============================================================ b . 220.22 |=================================================================== AOM AV1 3.5 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 23.87 |============================================================= b . 26.43 |==================================================================== Stargate Digital Audio Workstation 22.11.5 Sample Rate: 44100 - Buffer Size: 512 Render Ratio > Higher Is Better a . 3.281164 |================================================================= b . 2.979784 |=========================================================== CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 256 ops/s > Higher Is Better a . 30111.3 |================================================================== b . 27413.2 |============================================================ Stress-NG 0.14.06 Test: Futex Bogo Ops/s > Higher Is Better a . 1051825.91 |========================================================= b . 1152673.55 |=============================================================== EnCodec 0.1.1 Target Bandwidth: 24 kbps Seconds < Lower Is Better a . 48.81 |============================================================== b . 53.47 |==================================================================== NCNN 20220729 Target: CPU - Model: alexnet ms < Lower Is Better a . 8.45 |=============================================================== b . 9.25 |===================================================================== NCNN 20220729 Target: CPU - Model: vgg16 ms < Lower Is Better a . 35.89 |============================================================== b . 39.21 |==================================================================== Numenta Anomaly Benchmark 1.1 Detector: KNN CAD Seconds < Lower Is Better a . 135.46 |============================================================= b . 147.75 |=================================================================== Stress-NG 0.14.06 Test: Atomic Bogo Ops/s > Higher Is Better a . 126894.32 |================================================================ b . 116358.20 |=========================================================== NCNN 20220729 Target: CPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better a . 11.44 |============================================================== b . 12.46 |==================================================================== Redis 7.0.4 Test: GET - Parallel Connections: 50 Requests Per Second > Higher Is Better a . 2617818.25 |=============================================================== b . 2404467.25 |========================================================== NCNN 20220729 Target: CPU - Model: FastestDet ms < Lower Is Better a . 15.69 |==================================================================== b . 14.43 |=============================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - Repartition Test Time Seconds < Lower Is Better a . 5.61 |===================================================================== b . 5.16 |=============================================================== NCNN 20220729 Target: CPU - Model: efficientnet-b0 ms < Lower Is Better a . 15.0 |=============================================================== b . 16.3 |===================================================================== CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 128 ops/s > Higher Is Better a . 15412.3 |================================================================== b . 14191.7 |============================================================= NCNN 20220729 Target: CPU - Model: shufflenet-v2 ms < Lower Is Better a . 11.83 |=============================================================== b . 12.81 |==================================================================== Redis 7.0.4 Test: GET - Parallel Connections: 500 Requests Per Second > Higher Is Better a . 2908381.75 |=============================================================== b . 2700561.50 |========================================================== NCNN 20220729 Target: CPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better a . 10.44 |=============================================================== b . 11.24 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - Group By Test Time Seconds < Lower Is Better a . 8.24 |===================================================================== b . 7.68 |================================================================ EnCodec 0.1.1 Target Bandwidth: 1.5 kbps Seconds < Lower Is Better a . 41.89 |================================================================ b . 44.75 |==================================================================== NCNN 20220729 Target: CPU - Model: googlenet ms < Lower Is Better a . 21.60 |================================================================ b . 23.01 |==================================================================== JPEG XL libjxl 0.7 Input: JPEG - Quality: 100 MP/s > Higher Is Better a . 0.49 |===================================================================== b . 0.46 |================================================================= Mobile Neural Network 2.1 Model: mobilenet-v1-1.0 ms < Lower Is Better a . 3.695 |==================================================================== b . 3.487 |================================================================ CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 256 ops/s > Higher Is Better a . 24394.6 |================================================================== b . 23024.3 |============================================================== NCNN 20220729 Target: CPU - Model: mnasnet ms < Lower Is Better a . 10.43 |================================================================ b . 11.03 |==================================================================== AOM AV1 3.5 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 5.62 |================================================================= b . 5.94 |===================================================================== CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 512 ops/s > Higher Is Better a . 49424.7 |================================================================== b . 46804.8 |=============================================================== NCNN 20220729 Target: CPU - Model: squeezenet_ssd ms < Lower Is Better a . 29.15 |==================================================================== b . 27.75 |================================================================= Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 1:5 Ops/sec > Higher Is Better a . 989118.75 |============================================================ b . 1038762.14 |=============================================================== Xmrig 6.18.1 Variant: Monero - Hash Count: 1M H/s > Higher Is Better a . 9938.1 |=============================================================== b . 10411.8 |================================================================== Stargate Digital Audio Workstation 22.11.5 Sample Rate: 192000 - Buffer Size: 512 Render Ratio > Higher Is Better a . 1.044224 |============================================================== b . 1.093912 |================================================================= NCNN 20220729 Target: CPU - Model: regnety_400m ms < Lower Is Better a . 48.89 |================================================================= b . 51.14 |==================================================================== SVT-AV1 1.4 Encoder Mode: Preset 4 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 2.631 |==================================================================== b . 2.524 |================================================================= Stargate Digital Audio Workstation 22.11.5 Sample Rate: 96000 - Buffer Size: 512 Render Ratio > Higher Is Better a . 1.840618 |================================================================= b . 1.765949 |============================================================== NCNN 20220729 Target: CPU - Model: blazeface ms < Lower Is Better a . 5.70 |================================================================== b . 5.94 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 5.48 |================================================================== b . 5.71 |===================================================================== ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, Second Run Queries Per Minute, Geo Mean > Higher Is Better a . 205.73 |================================================================ b . 213.89 |=================================================================== Numenta Anomaly Benchmark 1.1 Detector: Earthgecko Skyline Seconds < Lower Is Better a . 99.19 |==================================================================== b . 95.43 |================================================================= Mobile Neural Network 2.1 Model: resnet-v2-50 ms < Lower Is Better a . 15.24 |==================================================================== b . 14.66 |================================================================= NCNN 20220729 Target: CPU - Model: yolov4-tiny ms < Lower Is Better a . 31.71 |================================================================== b . 32.91 |==================================================================== CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 128 ops/s > Higher Is Better a . 89867.4 |================================================================== b . 86632.5 |================================================================ Cpuminer-Opt 3.20.3 Algorithm: Myriad-Groestl kH/s > Higher Is Better a . 11570 |================================================================== b . 12000 |==================================================================== WebP2 Image Encode 20220823 Encode Settings: Quality 75, Compression Effort 7 MP/s > Higher Is Better a . 0.28 |===================================================================== b . 0.27 |=================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Group By Test Time Seconds < Lower Is Better a . 6.47 |===================================================================== b . 6.24 |=================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Only TPS > Higher Is Better a . 23407 |==================================================================== b . 22579 |================================================================== SVT-AV1 1.4 Encoder Mode: Preset 13 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 106.68 |================================================================= b . 110.56 |=================================================================== CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 1024 ops/s > Higher Is Better a . 61797.2 |================================================================ b . 63998.7 |================================================================== CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 1024 ops/s > Higher Is Better a . 67899.4 |================================================================ b . 70300.1 |================================================================== NCNN 20220729 Target: CPU - Model: resnet18 ms < Lower Is Better a . 13.35 |================================================================== b . 13.82 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 33.82 |================================================================== b . 34.99 |==================================================================== Timed PHP Compilation 8.1.9 Time To Compile Seconds < Lower Is Better a . 57.28 |================================================================== b . 59.27 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 29.56 |==================================================================== b . 28.57 |================================================================== AOM AV1 3.5 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 48.30 |==================================================================== b . 46.73 |================================================================== libavif avifenc 0.11 Encoder Speed: 0 Seconds < Lower Is Better a . 115.42 |=================================================================== b . 111.68 |================================================================= CockroachDB 22.2 Workload: KV, 10% Reads - Concurrency: 128 ops/s > Higher Is Better a . 6941.0 |=================================================================== b . 6717.4 |================================================================= GraphicsMagick 1.3.38 Operation: Rotate Iterations Per Minute > Higher Is Better a . 594 |====================================================================== b . 575 |==================================================================== CockroachDB 22.2 Workload: KV, 10% Reads - Concurrency: 1024 ops/s > Higher Is Better a . 38341.3 |================================================================ b . 39590.8 |================================================================== Stress-NG 0.14.06 Test: System V Message Passing Bogo Ops/s > Higher Is Better a . 3795441.99 |=============================================================== b . 3677320.93 |============================================================= CockroachDB 22.2 Workload: MoVR - Concurrency: 512 ops/s > Higher Is Better a . 111.5 |==================================================================== b . 108.1 |================================================================== Stargate Digital Audio Workstation 22.11.5 Sample Rate: 192000 - Buffer Size: 1024 Render Ratio > Higher Is Better a . 1.601382 |=============================================================== b . 1.650224 |================================================================= OpenVKL 1.3.1 Benchmark: vklBenchmark Scalar Items / Sec > Higher Is Better a . 176 |====================================================================== b . 171 |==================================================================== spaCy 3.4.1 Model: en_core_web_trf tokens/sec > Higher Is Better a . 2007 |===================================================================== b . 1950 |=================================================================== libavif avifenc 0.11 Encoder Speed: 2 Seconds < Lower Is Better a . 59.90 |==================================================================== b . 58.23 |================================================================== miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 GFInst/s > Higher Is Better a . 735.75 |================================================================= b . 756.81 |=================================================================== miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 Billion Interactions/s > Higher Is Better a . 29.43 |================================================================== b . 30.27 |==================================================================== JPEG XL libjxl 0.7 Input: PNG - Quality: 80 MP/s > Higher Is Better a . 8.15 |===================================================================== b . 7.93 |=================================================================== AOM AV1 3.5 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 19.60 |================================================================== b . 20.13 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency ms < Lower Is Better a . 16.54 |================================================================== b . 16.98 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Write TPS > Higher Is Better a . 6045 |===================================================================== b . 5890 |=================================================================== WebP2 Image Encode 20220823 Encode Settings: Default MP/s > Higher Is Better a . 6.59 |=================================================================== b . 6.76 |===================================================================== AOM AV1 3.5 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 13.58 |==================================================================== b . 13.24 |================================================================== OpenVKL 1.3.1 Benchmark: vklBenchmark ISPC Items / Sec > Higher Is Better a . 362 |====================================================================== b . 353 |==================================================================== oneDNN 2.7 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 3.40068 |================================================================== b . 3.31851 |================================================================ WebP2 Image Encode 20220823 Encode Settings: Quality 100, Compression Effort 5 MP/s > Higher Is Better a . 7.27 |=================================================================== b . 7.45 |===================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Only - Average Latency ms < Lower Is Better a . 0.043 |================================================================== b . 0.044 |==================================================================== GraphicsMagick 1.3.38 Operation: Swirl Iterations Per Minute > Higher Is Better a . 816 |====================================================================== b . 798 |==================================================================== SVT-AV1 1.4 Encoder Mode: Preset 4 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 6.245 |=================================================================== b . 6.385 |==================================================================== GraphicsMagick 1.3.38 Operation: HWB Color Space Iterations Per Minute > Higher Is Better a . 735 |====================================================================== b . 719 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 1 - Mode: Read Only - Average Latency ms < Lower Is Better a . 0.045 |=================================================================== b . 0.046 |==================================================================== OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU FPS > Higher Is Better a . 421.71 |=================================================================== b . 412.75 |================================================================== OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU ms < Lower Is Better a . 21.30 |=================================================================== b . 21.76 |==================================================================== Numenta Anomaly Benchmark 1.1 Detector: Bayesian Changepoint Seconds < Lower Is Better a . 34.99 |=================================================================== b . 35.73 |==================================================================== Node.js V8 Web Tooling Benchmark runs/s > Higher Is Better a . 9.93 |=================================================================== b . 10.14 |==================================================================== JPEG XL libjxl 0.7 Input: PNG - Quality: 100 MP/s > Higher Is Better a . 0.49 |===================================================================== b . 0.48 |==================================================================== BRL-CAD 7.32.6 VGR Performance Metric VGR Performance Metric > Higher Is Better a . 257085 |=================================================================== b . 251911 |================================================================== oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 1409.26 |================================================================== b . 1381.57 |================================================================= NCNN 20220729 Target: CPU - Model: mobilenet ms < Lower Is Better a . 23.38 |==================================================================== b . 22.93 |=================================================================== SVT-AV1 1.4 Encoder Mode: Preset 12 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 120.58 |=================================================================== b . 118.27 |================================================================== oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 786.58 |================================================================== b . 801.80 |=================================================================== Facebook RocksDB 7.5.3 Test: Read While Writing Op/s > Higher Is Better a . 5155074 |================================================================= b . 5254605 |================================================================== Xmrig 6.18.1 Variant: Wownero - Hash Count: 1M H/s > Higher Is Better a . 16896.5 |================================================================== b . 16579.3 |================================================================= JPEG XL Decoding libjxl 0.7 CPU Threads: 1 MP/s > Higher Is Better a . 33.54 |==================================================================== b . 32.92 |=================================================================== OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU FPS > Higher Is Better a . 687.33 |=================================================================== b . 674.84 |================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Write TPS > Higher Is Better a . 7613 |===================================================================== b . 7475 |==================================================================== OpenRadioss 2022.10.13 Model: Bird Strike on Windshield Seconds < Lower Is Better a . 205.44 |=================================================================== b . 201.72 |================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency ms < Lower Is Better a . 65.68 |=================================================================== b . 66.89 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Only TPS > Higher Is Better a . 882773 |================================================================== b . 899014 |=================================================================== OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU ms < Lower Is Better a . 13.06 |=================================================================== b . 13.30 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency ms < Lower Is Better a . 0.113 |==================================================================== b . 0.111 |=================================================================== Y-Cruncher 0.7.10.9513 Pi Digits To Calculate: 500M Seconds < Lower Is Better a . 11.12 |=================================================================== b . 11.32 |==================================================================== JPEG XL libjxl 0.7 Input: PNG - Quality: 90 MP/s > Higher Is Better a . 8.03 |===================================================================== b . 7.89 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency ms < Lower Is Better a . 34.87 |=================================================================== b . 35.48 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 250 - Mode: Read Write TPS > Higher Is Better a . 7170 |===================================================================== b . 7046 |==================================================================== CockroachDB 22.2 Workload: MoVR - Concurrency: 1024 ops/s > Higher Is Better a . 111.1 |==================================================================== b . 109.2 |=================================================================== Stress-NG 0.14.06 Test: Glibc Qsort Data Sorting Bogo Ops/s > Higher Is Better a . 417.0 |=================================================================== b . 424.2 |==================================================================== JPEG XL libjxl 0.7 Input: JPEG - Quality: 90 MP/s > Higher Is Better a . 7.69 |===================================================================== b . 7.56 |==================================================================== Redis 7.0.4 Test: GET - Parallel Connections: 1000 Requests Per Second > Higher Is Better a . 2852955.50 |=============================================================== b . 2805580.75 |============================================================== EnCodec 0.1.1 Target Bandwidth: 6 kbps Seconds < Lower Is Better a . 40.51 |==================================================================== b . 39.85 |=================================================================== Mobile Neural Network 2.1 Model: inception-v3 ms < Lower Is Better a . 36.76 |==================================================================== b . 36.17 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 18.65 |==================================================================== b . 18.36 |=================================================================== Mobile Neural Network 2.1 Model: mobilenetV3 ms < Lower Is Better a . 3.386 |==================================================================== b . 3.334 |=================================================================== CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 1024 ops/s > Higher Is Better a . 94378.8 |================================================================== b . 92938.9 |================================================================= oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 2.55381 |================================================================= b . 2.59337 |================================================================== Stress-NG 0.14.06 Test: SENDFILE Bogo Ops/s > Higher Is Better a . 437831.75 |=============================================================== b . 444590.02 |================================================================ Mobile Neural Network 2.1 Model: MobileNetV2_224 ms < Lower Is Better a . 5.143 |=================================================================== b . 5.221 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - Calculate Pi Benchmark Seconds < Lower Is Better a . 64.83 |=================================================================== b . 65.80 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 4.78 |==================================================================== b . 4.85 |===================================================================== miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 GFInst/s > Higher Is Better a . 776.35 |================================================================== b . 787.50 |=================================================================== miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 Billion Interactions/s > Higher Is Better a . 31.05 |=================================================================== b . 31.50 |==================================================================== srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM eNb Mb/s > Higher Is Better a . 293.3 |==================================================================== b . 289.2 |=================================================================== Stargate Digital Audio Workstation 22.11.5 Sample Rate: 44100 - Buffer Size: 1024 Render Ratio > Higher Is Better a . 3.634671 |================================================================= b . 3.584121 |================================================================ AOM AV1 3.5 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 0.72 |==================================================================== b . 0.73 |===================================================================== SVT-AV1 1.4 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 85.02 |=================================================================== b . 86.18 |==================================================================== srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM UE Mb/s > Higher Is Better a . 130.9 |==================================================================== b . 129.2 |=================================================================== JPEG XL libjxl 0.7 Input: JPEG - Quality: 80 MP/s > Higher Is Better a . 7.78 |===================================================================== b . 7.68 |==================================================================== Stress-NG 0.14.06 Test: CPU Stress Bogo Ops/s > Higher Is Better a . 59047.56 |================================================================= b . 58316.18 |================================================================ srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM UE Mb/s > Higher Is Better a . 136.3 |==================================================================== b . 134.7 |=================================================================== AOM AV1 3.5 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 16.04 |=================================================================== b . 16.23 |==================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: GoogLeNet images/sec > Higher Is Better a . 77.03 |==================================================================== b . 76.16 |=================================================================== Blender 3.4 Blend File: Classroom - Compute: CPU-Only Seconds < Lower Is Better a . 164.77 |=================================================================== b . 162.95 |================================================================== 7-Zip Compression 22.01 Test: Compression Rating MIPS > Higher Is Better a . 171677 |=================================================================== b . 169842 |================================================================== CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 256 ops/s > Higher Is Better a . 98923.9 |================================================================= b . 99986.0 |================================================================== oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 781.00 |================================================================== b . 789.36 |=================================================================== srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM UE Mb/s > Higher Is Better a . 126.1 |==================================================================== b . 124.8 |=================================================================== ASTC Encoder 4.0 Preset: Medium MT/s > Higher Is Better a . 138.09 |=================================================================== b . 136.69 |================================================================== Timed Erlang/OTP Compilation 25.0 Time To Compile Seconds < Lower Is Better a . 121.47 |================================================================== b . 122.71 |=================================================================== Stress-NG 0.14.06 Test: Memory Copying Bogo Ops/s > Higher Is Better a . 4644.12 |================================================================= b . 4691.35 |================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: VGG-16 images/sec > Higher Is Better a . 10.85 |=================================================================== b . 10.96 |==================================================================== Cpuminer-Opt 3.20.3 Algorithm: Blake-2 S kH/s > Higher Is Better a . 2216930 |================================================================= b . 2239380 |================================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 114.35 |================================================================== b . 115.50 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 8.7441 |=================================================================== b . 8.6568 |================================================================== Cpuminer-Opt 3.20.3 Algorithm: Ringcoin kH/s > Higher Is Better a . 3292.87 |================================================================= b . 3325.86 |================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 50 - Mode: Read Write TPS > Higher Is Better a . 716 |====================================================================== b . 709 |===================================================================== SVT-AV1 1.4 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 201.87 |=================================================================== b . 199.97 |================================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 114.27 |================================================================== b . 115.35 |=================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: AlexNet images/sec > Higher Is Better a . 143.41 |=================================================================== b . 142.07 |================================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 8.7499 |=================================================================== b . 8.6682 |================================================================== Aircrack-ng 1.7 k/s > Higher Is Better a . 99753.68 |================================================================= b . 98829.75 |================================================================ srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM eNb Mb/s > Higher Is Better a . 324.2 |==================================================================== b . 321.2 |=================================================================== GraphicsMagick 1.3.38 Operation: Sharpen Iterations Per Minute > Higher Is Better a . 220 |====================================================================== b . 218 |===================================================================== oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 0.477096 |================================================================ b . 0.481461 |================================================================= Stress-NG 0.14.06 Test: NUMA Bogo Ops/s > Higher Is Better a . 577.50 |=================================================================== b . 572.28 |================================================================== srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM eNb Mb/s > Higher Is Better a . 294.0 |==================================================================== b . 291.4 |=================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average Latency ms < Lower Is Better a . 69.87 |=================================================================== b . 70.48 |==================================================================== oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 6.35819 |================================================================= b . 6.41270 |================================================================== srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM UE Mb/s > Higher Is Better a . 118.9 |==================================================================== b . 117.9 |=================================================================== JPEG XL Decoding libjxl 0.7 CPU Threads: All MP/s > Higher Is Better a . 80.94 |==================================================================== b . 80.26 |=================================================================== Facebook RocksDB 7.5.3 Test: Update Random Op/s > Higher Is Better a . 174193 |=================================================================== b . 172766 |================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: AlexNet images/sec > Higher Is Better a . 106.64 |=================================================================== b . 105.78 |================================================================== WebP Image Encode 1.2.4 Encode Settings: Quality 100, Lossless MP/s > Higher Is Better a . 1.25 |===================================================================== b . 1.24 |==================================================================== GraphicsMagick 1.3.38 Operation: Enhanced Iterations Per Minute > Higher Is Better a . 506 |====================================================================== b . 502 |===================================================================== AOM AV1 3.5 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 38.05 |==================================================================== b . 37.75 |=================================================================== FLAC Audio Encoding 1.4 WAV To FLAC Seconds < Lower Is Better a . 22.41 |=================================================================== b . 22.58 |==================================================================== AOM AV1 3.5 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 22.76 |==================================================================== b . 22.59 |=================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency ms < Lower Is Better a . 0.271 |==================================================================== b . 0.273 |==================================================================== Mobile Neural Network 2.1 Model: SqueezeNetV1.0 ms < Lower Is Better a . 7.533 |==================================================================== b . 7.588 |==================================================================== 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 . 99.48 |==================================================================== b . 98.77 |==================================================================== Mobile Neural Network 2.1 Model: nasnet ms < Lower Is Better a . 22.53 |==================================================================== b . 22.37 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 250 - Mode: Read Only TPS > Higher Is Better a . 922066 |=================================================================== b . 915519 |=================================================================== Stress-NG 0.14.06 Test: Glibc C String Functions Bogo Ops/s > Higher Is Better a . 1715303.02 |=============================================================== b . 1703193.63 |=============================================================== Numenta Anomaly Benchmark 1.1 Detector: Windowed Gaussian Seconds < Lower Is Better a . 7.529 |==================================================================== b . 7.476 |==================================================================== 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 . 180.54 |=================================================================== b . 181.80 |=================================================================== Redis 7.0.4 Test: SET - Parallel Connections: 500 Requests Per Second > Higher Is Better a . 2217236.25 |=============================================================== b . 2232581.50 |=============================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 135.75 |=================================================================== b . 136.68 |=================================================================== oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 11.48 |==================================================================== b . 11.56 |==================================================================== OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU FPS > Higher Is Better a . 78.04 |==================================================================== b . 77.53 |==================================================================== libavif avifenc 0.11 Encoder Speed: 6, Lossless Seconds < Lower Is Better a . 10.043 |=================================================================== b . 9.978 |=================================================================== OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU ms < Lower Is Better a . 115.20 |=================================================================== b . 115.95 |=================================================================== WebP Image Encode 1.2.4 Encode Settings: Default MP/s > Higher Is Better a . 13.83 |==================================================================== b . 13.92 |==================================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 132.44 |=================================================================== b . 131.59 |=================================================================== Stress-NG 0.14.06 Test: Matrix Math Bogo Ops/s > Higher Is Better a . 124052.48 |================================================================ b . 123275.06 |================================================================ srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM eNb Mb/s > Higher Is Better a . 320.8 |==================================================================== b . 318.8 |==================================================================== AOM AV1 3.5 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 22.89 |==================================================================== b . 22.75 |==================================================================== Numenta Anomaly Benchmark 1.1 Detector: Contextual Anomaly Detector OSE Seconds < Lower Is Better a . 50.62 |==================================================================== b . 50.91 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Only TPS > Higher Is Better a . 930850 |=================================================================== b . 925569 |=================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Only - Average Latency ms < Lower Is Better a . 0.537 |==================================================================== b . 0.540 |==================================================================== SVT-AV1 1.4 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 36.59 |==================================================================== b . 36.39 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 1 - Mode: Read Only TPS > Higher Is Better a . 21981 |==================================================================== b . 21860 |==================================================================== GraphicsMagick 1.3.38 Operation: Resizing Iterations Per Minute > Higher Is Better a . 1092 |===================================================================== b . 1098 |===================================================================== Cpuminer-Opt 3.20.3 Algorithm: Quad SHA-256, Pyrite kH/s > Higher Is Better a . 401450 |=================================================================== b . 403630 |=================================================================== OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer ms < Lower Is Better a . 78464 |==================================================================== b . 78883 |==================================================================== Cpuminer-Opt 3.20.3 Algorithm: scrypt kH/s > Higher Is Better a . 951.15 |=================================================================== b . 946.10 |=================================================================== OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer ms < Lower Is Better a . 65864 |==================================================================== b . 66209 |==================================================================== OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer ms < Lower Is Better a . 122216 |=================================================================== b . 122843 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 99.33 |==================================================================== b . 99.83 |==================================================================== OSPRay Studio 0.11 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer ms < Lower Is Better a . 14608 |==================================================================== b . 14535 |==================================================================== OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU FPS > Higher Is Better a . 4.03 |===================================================================== b . 4.01 |===================================================================== OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Execution Time Seconds < Lower Is Better a . 96.03 |==================================================================== b . 95.55 |==================================================================== Stress-NG 0.14.06 Test: MMAP Bogo Ops/s > Higher Is Better a . 564.44 |=================================================================== b . 561.69 |=================================================================== OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 1395.73 |================================================================== b . 1388.97 |================================================================== Blender 3.4 Blend File: Pabellon Barcelona - Compute: CPU-Only Seconds < Lower Is Better a . 192.12 |=================================================================== b . 191.19 |=================================================================== OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 6.42 |===================================================================== b . 6.45 |===================================================================== Timed CPython Compilation 3.10.6 Build Configuration: Default Seconds < Lower Is Better a . 19.74 |==================================================================== b . 19.84 |==================================================================== oneDNN 2.7 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1.37489 |================================================================== b . 1.38109 |================================================================== OpenRadioss 2022.10.13 Model: Rubber O-Ring Seal Installation Seconds < Lower Is Better a . 114.39 |=================================================================== b . 114.90 |=================================================================== AOM AV1 3.5 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 9.12 |===================================================================== b . 9.08 |===================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 180.90 |=================================================================== b . 180.12 |=================================================================== Stress-NG 0.14.06 Test: MEMFD Bogo Ops/s > Higher Is Better a . 1021.04 |================================================================== b . 1016.64 |================================================================== Cpuminer-Opt 3.20.3 Algorithm: LBC, LBRY Credits kH/s > Higher Is Better a . 182930 |=================================================================== b . 183720 |=================================================================== Facebook RocksDB 7.5.3 Test: Read Random Write Random Op/s > Higher Is Better a . 2545133 |================================================================== b . 2534266 |================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 4.69 |===================================================================== b . 4.71 |===================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 50 - Mode: Read Only TPS > Higher Is Better a . 675675 |=================================================================== b . 672851 |=================================================================== Stress-NG 0.14.06 Test: Forking Bogo Ops/s > Higher Is Better a . 41988.02 |================================================================= b . 42163.36 |================================================================= TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: GoogLeNet images/sec > Higher Is Better a . 46.37 |==================================================================== b . 46.18 |==================================================================== NCNN 20220729 Target: CPU - Model: vision_transformer ms < Lower Is Better a . 173.64 |=================================================================== b . 172.93 |=================================================================== LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: 20k Atoms ns/day > Higher Is Better a . 15.75 |==================================================================== b . 15.68 |==================================================================== srsRAN 22.04.1 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM eNb Mb/s > Higher Is Better a . 100.3 |==================================================================== b . 99.9 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Only TPS > Higher Is Better a . 869450 |=================================================================== b . 866030 |=================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: VGG-16 images/sec > Higher Is Better a . 10.22 |==================================================================== b . 10.18 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Only - Average Latency ms < Lower Is Better a . 0.255 |==================================================================== b . 0.256 |==================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: ResNet-50 images/sec > Higher Is Better a . 17.90 |==================================================================== b . 17.97 |==================================================================== OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Mesh Time Seconds < Lower Is Better a . 34.01 |==================================================================== b . 33.88 |==================================================================== oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 9.85430 |================================================================== b . 9.81832 |================================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 18.41 |==================================================================== b . 18.35 |==================================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 54.26 |==================================================================== b . 54.45 |==================================================================== Timed Node.js Compilation 18.8 Time To Compile Seconds < Lower Is Better a . 275.44 |=================================================================== b . 276.40 |=================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency ms < Lower Is Better a . 0.575 |==================================================================== b . 0.577 |==================================================================== libavif avifenc 0.11 Encoder Speed: 6 Seconds < Lower Is Better a . 5.298 |==================================================================== b . 5.280 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Only TPS > Higher Is Better a . 979407 |=================================================================== b . 976093 |=================================================================== spaCy 3.4.1 Model: en_core_web_lg tokens/sec > Higher Is Better a . 10874 |==================================================================== b . 10838 |==================================================================== nekRS 22.0 Input: TurboPipe Periodic FLOP/s > Higher Is Better a . 124608000000 |============================================================= b . 124198000000 |============================================================= Timed Linux Kernel Compilation 6.1 Build: allmodconfig Seconds < Lower Is Better a . 543.75 |=================================================================== b . 545.45 |=================================================================== srsRAN 22.04.1 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM UE Mb/s > Higher Is Better a . 65.7 |===================================================================== b . 65.5 |===================================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 18.62 |==================================================================== b . 18.67 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Only TPS > Higher Is Better a . 968554 |=================================================================== b . 971447 |=================================================================== Stress-NG 0.14.06 Test: Mutex Bogo Ops/s > Higher Is Better a . 17168753.52 |============================================================== b . 17219955.71 |============================================================== OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU FPS > Higher Is Better a . 21846.45 |================================================================= b . 21782.56 |================================================================= Cpuminer-Opt 3.20.3 Algorithm: Magi kH/s > Higher Is Better a . 701.91 |=================================================================== b . 703.92 |=================================================================== 7-Zip Compression 22.01 Test: Decompression Rating MIPS > Higher Is Better a . 158350 |=================================================================== b . 157899 |=================================================================== oneDNN 2.7 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 2.80983 |================================================================== b . 2.81784 |================================================================== OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU ms < Lower Is Better a . 2199.69 |================================================================== b . 2205.86 |================================================================== Blender 3.4 Blend File: Fishy Cat - Compute: CPU-Only Seconds < Lower Is Better a . 75.80 |==================================================================== b . 75.59 |==================================================================== OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU ms < Lower Is Better a . 51.00 |==================================================================== b . 50.86 |==================================================================== Stress-NG 0.14.06 Test: Semaphores Bogo Ops/s > Higher Is Better a . 4585186.59 |=============================================================== b . 4572788.09 |=============================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 963.81 |=================================================================== b . 966.40 |=================================================================== oneDNN 2.7 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1.25783 |================================================================== b . 1.25446 |================================================================== Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 5:1 Ops/sec > Higher Is Better a . 959933.80 |================================================================ b . 962500.62 |================================================================ AOM AV1 3.5 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 46.50 |==================================================================== b . 46.38 |==================================================================== OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU FPS > Higher Is Better a . 704.60 |=================================================================== b . 706.42 |=================================================================== GraphicsMagick 1.3.38 Operation: Noise-Gaussian Iterations Per Minute > Higher Is Better a . 392 |====================================================================== b . 391 |====================================================================== OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU FPS > Higher Is Better a . 4.04 |===================================================================== b . 4.03 |===================================================================== Cpuminer-Opt 3.20.3 Algorithm: Garlicoin kH/s > Higher Is Better a . 12910 |==================================================================== b . 12940 |==================================================================== OSPRay Studio 0.11 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer ms < Lower Is Better a . 888 |====================================================================== b . 890 |====================================================================== oneDNN 2.7 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 5.70137 |================================================================== b . 5.71409 |================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 197.13 |=================================================================== b . 196.70 |=================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: GoogLeNet images/sec > Higher Is Better a . 61.69 |==================================================================== b . 61.82 |==================================================================== OpenRadioss 2022.10.13 Model: Bumper Beam Seconds < Lower Is Better a . 125.04 |=================================================================== b . 124.78 |=================================================================== oneDNN 2.7 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 9.61455 |================================================================== b . 9.63450 |================================================================== 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 . 23.90 |==================================================================== b . 23.95 |==================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: ResNet-50 images/sec > Higher Is Better a . 14.77 |==================================================================== b . 14.74 |==================================================================== oneDNN 2.7 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.693146 |================================================================= b . 0.694553 |================================================================= 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 . 41.81 |==================================================================== b . 41.72 |==================================================================== OSPRay Studio 0.11 Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer ms < Lower Is Better a . 3617 |===================================================================== b . 3624 |===================================================================== Mobile Neural Network 2.1 Model: squeezenetv1.1 ms < Lower Is Better a . 4.677 |==================================================================== b . 4.686 |==================================================================== memtier_benchmark 1.4 Protocol: Redis - Clients: 50 - Set To Get Ratio: 10:1 Ops/sec > Higher Is Better a . 1501800.97 |=============================================================== b . 1504675.76 |=============================================================== oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.568809 |================================================================= b . 0.567734 |================================================================= Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 14.89 |==================================================================== b . 14.92 |==================================================================== ASTC Encoder 4.0 Preset: Thorough MT/s > Higher Is Better a . 18.06 |==================================================================== b . 18.09 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 67.09 |==================================================================== b . 66.97 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Calculate Pi Benchmark Seconds < Lower Is Better a . 66.06 |==================================================================== b . 65.95 |==================================================================== Y-Cruncher 0.7.10.9513 Pi Digits To Calculate: 1B Seconds < Lower Is Better a . 22.39 |==================================================================== b . 22.43 |==================================================================== OpenFOAM 10 Input: drivaerFastback, Medium Mesh Size - Execution Time Seconds < Lower Is Better a . 899.70 |=================================================================== b . 898.34 |=================================================================== OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 13.17 |==================================================================== b . 13.19 |==================================================================== OpenRadioss 2022.10.13 Model: INIVOL and Fluid Structure Interaction Drop Container Seconds < Lower Is Better a . 275.47 |=================================================================== b . 275.88 |=================================================================== OSPRay Studio 0.11 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer ms < Lower Is Better a . 17367 |==================================================================== b . 17342 |==================================================================== OpenVINO 2022.2.dev Model: Face Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 347.32 |=================================================================== b . 347.82 |=================================================================== OSPRay Studio 0.11 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer ms < Lower Is Better a . 14186 |==================================================================== b . 14166 |==================================================================== Cpuminer-Opt 3.20.3 Algorithm: Skeincoin kH/s > Higher Is Better a . 253670 |=================================================================== b . 253330 |=================================================================== Stress-NG 0.14.06 Test: Vector Math Bogo Ops/s > Higher Is Better a . 103156.98 |================================================================ b . 103019.74 |================================================================ Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 113.75 |=================================================================== b . 113.89 |=================================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 8.7764 |=================================================================== b . 8.7659 |=================================================================== OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer ms < Lower Is Better a . 146883 |=================================================================== b . 147053 |=================================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 50.95 |==================================================================== b . 51.01 |==================================================================== WebP Image Encode 1.2.4 Encode Settings: Quality 100 MP/s > Higher Is Better a . 8.92 |===================================================================== b . 8.91 |===================================================================== OSPRay Studio 0.11 Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer ms < Lower Is Better a . 125037 |=================================================================== b . 125174 |=================================================================== OSPRay Studio 0.11 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer ms < Lower Is Better a . 914 |====================================================================== b . 915 |====================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: VGG-16 images/sec > Higher Is Better a . 9.16 |===================================================================== b . 9.15 |===================================================================== OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 2717.47 |================================================================== b . 2714.67 |================================================================== oneDNN 2.7 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 3.79612 |================================================================== b . 3.80003 |================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: AlexNet images/sec > Higher Is Better a . 79.17 |==================================================================== b . 79.09 |==================================================================== Stress-NG 0.14.06 Test: Malloc Bogo Ops/s > Higher Is Better a . 109293721.23 |============================================================= b . 109184164.47 |============================================================= oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 7.47846 |================================================================== b . 7.48562 |================================================================== Cpuminer-Opt 3.20.3 Algorithm: x25x kH/s > Higher Is Better a . 1252.09 |================================================================== b . 1253.15 |================================================================== srsRAN 22.04.1 Test: OFDM_Test Samples / Second > Higher Is Better a . 119900000 |================================================================ b . 120000000 |================================================================ Redis 7.0.4 Test: SET - Parallel Connections: 50 Requests Per Second > Higher Is Better a . 2242796.0 |================================================================ b . 2244608.5 |================================================================ Timed Linux Kernel Compilation 6.1 Build: defconfig Seconds < Lower Is Better a . 52.65 |==================================================================== b . 52.69 |==================================================================== NCNN 20220729 Target: CPU - Model: resnet50 ms < Lower Is Better a . 26.10 |==================================================================== b . 26.12 |==================================================================== Redis 7.0.4 Test: SET - Parallel Connections: 1000 Requests Per Second > Higher Is Better a . 2202580.5 |================================================================ b . 2204248.0 |================================================================ oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 1380.95 |================================================================== b . 1379.94 |================================================================== SVT-AV1 1.4 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 227.23 |=================================================================== b . 227.06 |=================================================================== oneDNN 2.7 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 1.72077 |================================================================== b . 1.71954 |================================================================== Cpuminer-Opt 3.20.3 Algorithm: Triple SHA-256, Onecoin kH/s > Higher Is Better a . 598720 |=================================================================== b . 598300 |=================================================================== OSPRay Studio 0.11 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer ms < Lower Is Better a . 29041 |==================================================================== b . 29061 |==================================================================== Blender 3.4 Blend File: Barbershop - Compute: CPU-Only Seconds < Lower Is Better a . 592.36 |=================================================================== b . 591.97 |=================================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 352.86 |=================================================================== b . 352.63 |=================================================================== Unpacking The Linux Kernel 5.19 linux-5.19.tar.xz Seconds < Lower Is Better a . 8.579 |==================================================================== b . 8.584 |==================================================================== ASTC Encoder 4.0 Preset: Fast MT/s > Higher Is Better a . 364.55 |=================================================================== b . 364.35 |=================================================================== ASTC Encoder 4.0 Preset: Exhaustive MT/s > Higher Is Better a . 1.8422 |=================================================================== b . 1.8432 |=================================================================== OSPRay Studio 0.11 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer ms < Lower Is Better a . 28318 |==================================================================== b . 28332 |==================================================================== OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer ms < Lower Is Better a . 4309 |===================================================================== b . 4311 |===================================================================== CockroachDB 22.2 Workload: MoVR - Concurrency: 128 ops/s > Higher Is Better a . 226.3 |==================================================================== b . 226.4 |==================================================================== oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.235557 |================================================================= b . 0.235658 |================================================================= oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 6.94903 |================================================================== b . 6.94611 |================================================================== OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU ms < Lower Is Better a . 1283.20 |================================================================== b . 1283.73 |================================================================== OSPRay Studio 0.11 Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer ms < Lower Is Better a . 67352 |==================================================================== b . 67325 |==================================================================== OpenVINO 2022.2.dev Model: Face Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 25.83 |==================================================================== b . 25.82 |==================================================================== Blender 3.4 Blend File: BMW27 - Compute: CPU-Only Seconds < Lower Is Better a . 55.54 |==================================================================== b . 55.56 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 963.57 |=================================================================== b . 963.91 |=================================================================== Cpuminer-Opt 3.20.3 Algorithm: Deepcoin kH/s > Higher Is Better a . 28150 |==================================================================== b . 28140 |==================================================================== OpenRadioss 2022.10.13 Model: Cell Phone Drop Test Seconds < Lower Is Better a . 57.28 |==================================================================== b . 57.26 |==================================================================== OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU ms < Lower Is Better a . 2192.85 |================================================================== b . 2193.51 |================================================================== Timed CPython Compilation 3.10.6 Build Configuration: Released Build, PGO + LTO Optimized Seconds < Lower Is Better a . 382.19 |=================================================================== b . 382.30 |=================================================================== OSPRay Studio 0.11 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer ms < Lower Is Better a . 34647 |==================================================================== b . 34637 |==================================================================== OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer ms < Lower Is Better a . 3528 |===================================================================== b . 3529 |===================================================================== oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1380.06 |================================================================== b . 1380.45 |================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 91.19 |==================================================================== b . 91.21 |==================================================================== Stress-NG 0.14.06 Test: x86_64 RdRand Bogo Ops/s > Higher Is Better a . 503507.78 |================================================================ b . 503602.92 |================================================================ PostgreSQL 15 Scaling Factor: 100 - Clients: 50 - Mode: Read Only TPS > Higher Is Better a . 652544 |=================================================================== b . 652647 |=================================================================== libavif avifenc 0.11 Encoder Speed: 10, Lossless Seconds < Lower Is Better a . 7.053 |==================================================================== b . 7.052 |==================================================================== Stress-NG 0.14.06 Test: Crypto Bogo Ops/s > Higher Is Better a . 34685.11 |================================================================= b . 34689.96 |================================================================= OpenFOAM 10 Input: drivaerFastback, Medium Mesh Size - Mesh Time Seconds < Lower Is Better a . 187.22 |=================================================================== b . 187.20 |=================================================================== CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 512 ops/s > Higher Is Better a . 96569.8 |================================================================== b . 96577.9 |================================================================== Numenta Anomaly Benchmark 1.1 Detector: Relative Entropy Seconds < Lower Is Better a . 13.36 |==================================================================== b . 13.36 |==================================================================== Natron 2.4.3 Input: Spaceship FPS > Higher Is Better a . 3.7 |====================================================================== b . 3.7 |====================================================================== OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU ms < Lower Is Better a . 1.64 |===================================================================== b . 1.64 |===================================================================== OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU FPS > Higher Is Better a . 6.94 |===================================================================== b . 6.94 |===================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency ms < Lower Is Better a . 0.077 |==================================================================== b . 0.077 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Only - Average Latency ms < Lower Is Better a . 0.103 |==================================================================== b . 0.103 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average Latency ms < Lower Is Better a . 0.074 |==================================================================== b . 0.074 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 5.07 |===================================================================== b . 5.07 |===================================================================== OSPRay Studio 0.11 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer ms < Lower Is Better a . 1085 |===================================================================== b . 1085 |===================================================================== AOM AV1 3.5 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 10.53 |==================================================================== b . 10.53 |==================================================================== AOM AV1 3.5 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 0.27 |===================================================================== b . 0.27 |===================================================================== WebP2 Image Encode 20220823 Encode Settings: Quality 100, Lossless Compression MP/s > Higher Is Better a . 0.03 |===================================================================== b . 0.03 |===================================================================== WebP2 Image Encode 20220823 Encode Settings: Quality 95, Compression Effort 7 MP/s > Higher Is Better a . 0.13 |===================================================================== b . 0.13 |===================================================================== WebP Image Encode 1.2.4 Encode Settings: Quality 100, Lossless, Highest Compression MP/s > Higher Is Better a . 0.44 |===================================================================== b . 0.44 |===================================================================== WebP Image Encode 1.2.4 Encode Settings: Quality 100, Highest Compression MP/s > Higher Is Better a . 3.03 |===================================================================== b . 3.03 |===================================================================== Stress-NG 0.14.06 Test: IO_uring