epyc milan x xmas 2 x AMD EPYC 7773X 64-Core testing with a AMD DAYTONA_X (RYM1009B BIOS) and ASPEED on Ubuntu 20.04 via the Phoronix Test Suite. a: Processor: 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 512GB, Disk: 800GB INTEL SSDPF21Q800GB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710 OS: Ubuntu 20.04, Kernel: 6.1.0-rc8-phx (x86_64), Display Server: X Server, Vulkan: 1.1.182, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 1920x1080 b: Processor: 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 512GB, Disk: 800GB INTEL SSDPF21Q800GB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710 OS: Ubuntu 20.04, Kernel: 6.1.0-rc8-phx (x86_64), Display Server: X Server, Vulkan: 1.1.182, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 1920x1080 OpenVKL 1.3.1 Benchmark: vklBenchmark ISPC Items / Sec > Higher Is Better a . 622 |================================================================== b . 664 |====================================================================== OpenVKL 1.3.1 Benchmark: vklBenchmark Scalar Items / Sec > Higher Is Better a . 456 |====================================================================== b . 440 |==================================================================== Timed Linux Kernel Compilation 6.1 Build: defconfig Seconds < Lower Is Better a . 24.03 |==================================================================== b . 23.96 |==================================================================== Timed Linux Kernel Compilation 6.1 Build: allmodconfig Seconds < Lower Is Better a . 177.98 |=================================================================== b . 177.40 |=================================================================== oneDNN 3.0 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 2.29566 |================================================================== b . 2.24618 |================================================================= oneDNN 3.0 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 1.83730 |================================================================== b . 1.83852 |================================================================== oneDNN 3.0 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1.57840 |================================================================== b . 1.57114 |================================================================== oneDNN 3.0 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.967326 |================================================================= b . 0.937745 |=============================================================== oneDNN 3.0 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 0.589938 |================================================================= b . 0.576758 |================================================================ oneDNN 3.0 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 27.48 |==================================================================== b . 27.24 |=================================================================== oneDNN 3.0 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 3.49280 |================================================================= b . 3.54446 |================================================================== oneDNN 3.0 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.583512 |=================================================== b . 0.746936 |================================================================= oneDNN 3.0 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1.03703 |================================================================== b . 1.04002 |================================================================== oneDNN 3.0 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.717443 |================================================================= b . 0.696358 |=============================================================== oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 1579.22 |============================================================= b . 1700.59 |================================================================== oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 1473.67 |================================================================== b . 1176.84 |===================================================== oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1685.58 |================================================================== b . 1680.10 |================================================================== oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1372.40 |============================================================== b . 1471.68 |================================================================== oneDNN 3.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 2.68287 |================================================================== b . 2.66346 |================================================================== oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 1920.66 |================================================================== b . 1863.81 |================================================================ oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 1448.33 |================================================================== b . 1298.93 |=========================================================== oneDNN 3.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 2.56092 |================================================================ b . 2.63047 |================================================================== CockroachDB 22.2 Workload: MoVR - Concurrency: 128 ops/s > Higher Is Better a . 767 |====================================================================== b . 763 |====================================================================== CockroachDB 22.2 Workload: MoVR - Concurrency: 256 ops/s > Higher Is Better a . 764.1 |==================================================================== b . 758.9 |==================================================================== CockroachDB 22.2 Workload: MoVR - Concurrency: 512 ops/s > Higher Is Better a . 772.7 |==================================================================== b . 765.3 |=================================================================== CockroachDB 22.2 Workload: MoVR - Concurrency: 1024 ops/s > Higher Is Better a . 765.6 |==================================================================== b . 768.3 |==================================================================== CockroachDB 22.2 Workload: KV, 10% Reads - Concurrency: 128 ops/s > Higher Is Better a . 49496.0 |================================================================ b . 51045.1 |================================================================== CockroachDB 22.2 Workload: KV, 10% Reads - Concurrency: 256 ops/s > Higher Is Better a . 51117.2 |================================================================== b . 49348.6 |================================================================ CockroachDB 22.2 Workload: KV, 10% Reads - Concurrency: 512 ops/s > Higher Is Better a . 49998.2 |================================================================ b . 51201.0 |================================================================== CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 128 ops/s > Higher Is Better a . 64904.1 |=============================================================== b . 67808.6 |================================================================== CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 256 ops/s > Higher Is Better a . 68275.7 |================================================================= b . 69421.4 |================================================================== CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 512 ops/s > Higher Is Better a . 69331.1 |================================================================== b . 69785.0 |================================================================== CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 128 ops/s > Higher Is Better a . 70821.7 |================================================================= b . 71858.8 |================================================================== CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 256 ops/s > Higher Is Better a . 74632.2 |================================================================== b . 73457.7 |================================================================= CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 512 ops/s > Higher Is Better a . 72451.2 |================================================================= b . 73171.5 |================================================================== CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 128 ops/s > Higher Is Better a . 87221.5 |================================================================== b . 75051.9 |========================================================= CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 256 ops/s > Higher Is Better a . 88931.9 |================================================================= b . 90275.6 |================================================================== CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 512 ops/s > Higher Is Better a . 72081.8 |===================================================== b . 89654.1 |================================================================== CockroachDB 22.2 Workload: KV, 10% Reads - Concurrency: 1024 ops/s > Higher Is Better a . 47190.8 |=============================================================== b . 49337.7 |================================================================== CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 1024 ops/s > Higher Is Better a . 64847.1 |================================================================== b . 59441.5 |============================================================ CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 1024 ops/s > Higher Is Better a . 70580.2 |================================================================== b . 70896.9 |================================================================== CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 1024 ops/s > Higher Is Better a . 88959.2 |================================================================== b . 88708.4 |================================================================== OpenVINO 2022.3 Model: Face Detection FP16 - Device: CPU FPS > Higher Is Better a . 22.35 |==================================================================== b . 21.95 |=================================================================== OpenVINO 2022.3 Model: Face Detection FP16 - Device: CPU ms < Lower Is Better a . 1414.79 |================================================================ b . 1448.08 |================================================================== OpenVINO 2022.3 Model: Person Detection FP16 - Device: CPU FPS > Higher Is Better a . 15.55 |==================================================================== b . 15.43 |=================================================================== OpenVINO 2022.3 Model: Person Detection FP16 - Device: CPU ms < Lower Is Better a . 2028.30 |================================================================= b . 2051.22 |================================================================== OpenVINO 2022.3 Model: Person Detection FP32 - Device: CPU FPS > Higher Is Better a . 15.46 |==================================================================== b . 15.51 |==================================================================== OpenVINO 2022.3 Model: Person Detection FP32 - Device: CPU ms < Lower Is Better a . 2047.78 |================================================================== b . 2040.99 |================================================================== OpenVINO 2022.3 Model: Vehicle Detection FP16 - Device: CPU FPS > Higher Is Better a . 2329.23 |================================================================== b . 2337.11 |================================================================== OpenVINO 2022.3 Model: Vehicle Detection FP16 - Device: CPU ms < Lower Is Better a . 13.72 |==================================================================== b . 13.68 |==================================================================== OpenVINO 2022.3 Model: Face Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 55.77 |==================================================================== b . 55.87 |==================================================================== OpenVINO 2022.3 Model: Face Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 571.16 |=================================================================== b . 570.36 |=================================================================== OpenVINO 2022.3 Model: Vehicle Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 3755.03 |================================================================== b . 3756.88 |================================================================== OpenVINO 2022.3 Model: Vehicle Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 8.51 |===================================================================== b . 8.51 |===================================================================== OpenVINO 2022.3 Model: Weld Porosity Detection FP16 - Device: CPU FPS > Higher Is Better a . 2442.86 |================================================================== b . 2442.72 |================================================================== OpenVINO 2022.3 Model: Weld Porosity Detection FP16 - Device: CPU ms < Lower Is Better a . 13.09 |==================================================================== b . 13.09 |==================================================================== OpenVINO 2022.3 Model: Machine Translation EN To DE FP16 - Device: CPU FPS > Higher Is Better a . 278.21 |=================================================================== b . 276.86 |=================================================================== OpenVINO 2022.3 Model: Machine Translation EN To DE FP16 - Device: CPU ms < Lower Is Better a . 114.89 |=================================================================== b . 115.44 |=================================================================== OpenVINO 2022.3 Model: Weld Porosity Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 5753.13 |================================================================== b . 5750.27 |================================================================== OpenVINO 2022.3 Model: Weld Porosity Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 22.23 |==================================================================== b . 22.24 |==================================================================== OpenVINO 2022.3 Model: Person Vehicle Bike Detection FP16 - Device: CPU FPS > Higher Is Better a . 3231.85 |================================================================== b . 3229.45 |================================================================== OpenVINO 2022.3 Model: Person Vehicle Bike Detection FP16 - Device: CPU ms < Lower Is Better a . 9.89 |===================================================================== b . 9.90 |===================================================================== OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU FPS > Higher Is Better a . 76694.48 |================================================================= b . 77006.49 |================================================================= OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU ms < Lower Is Better a . 1.64 |===================================================================== b . 1.64 |===================================================================== OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU FPS > Higher Is Better a . 83051.23 |================================================================= b . 82943.37 |================================================================= OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU ms < Lower Is Better a . 1.52 |===================================================================== b . 1.52 |===================================================================== Numenta Anomaly Benchmark 1.1 Detector: KNN CAD Seconds < Lower Is Better a . 88.69 |=================================================================== b . 89.54 |==================================================================== Numenta Anomaly Benchmark 1.1 Detector: Windowed Gaussian Seconds < Lower Is Better a . 5.491 |==================================================================== b . 5.493 |==================================================================== Numenta Anomaly Benchmark 1.1 Detector: Earthgecko Skyline Seconds < Lower Is Better a . 73.63 |==================================================================== b . 73.31 |==================================================================== Numenta Anomaly Benchmark 1.1 Detector: Contextual Anomaly Detector OSE Seconds < Lower Is Better a . 44.56 |==================================================================== b . 44.29 |====================================================================