8490h april 2 x Intel Xeon Platinum 8490H testing with a Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS) and ASPEED on Ubuntu 22.04 via the Phoronix Test Suite. a: Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads), Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS), Chipset: Intel Device 1bce, Memory: 16 x 64 GB 4800MT/s Samsung M321R8GA0BB0-CQKEG, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96, Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T OS: Ubuntu 22.04, Kernel: 6.2.0-060200rc7daily20230208-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3, Vulkan: 1.2.204, Compiler: GCC 11.3.0 + Clang 14.0.0-1ubuntu1, File-System: ext4, Screen Resolution: 1920x1080 b: Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads), Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS), Chipset: Intel Device 1bce, Memory: 16 x 64 GB 4800MT/s Samsung M321R8GA0BB0-CQKEG, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96, Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T OS: Ubuntu 22.04, Kernel: 6.2.0-060200rc7daily20230208-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3, Vulkan: 1.2.204, Compiler: GCC 11.3.0 + Clang 14.0.0-1ubuntu1, File-System: ext4, Screen Resolution: 1920x1080 c: Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads), Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS), Chipset: Intel Device 1bce, Memory: 16 x 64 GB 4800MT/s Samsung M321R8GA0BB0-CQKEG, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96, Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T OS: Ubuntu 22.04, Kernel: 6.2.0-060200rc7daily20230208-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3, Vulkan: 1.2.204, Compiler: GCC 11.3.0 + Clang 14.0.0-1ubuntu1, File-System: ext4, Screen Resolution: 1920x1080 d: Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads), Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS), Chipset: Intel Device 1bce, Memory: 16 x 64 GB 4800MT/s Samsung M321R8GA0BB0-CQKEG, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96, Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T OS: Ubuntu 22.04, Kernel: 6.2.0-060200rc7daily20230208-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3, Vulkan: 1.2.204, Compiler: GCC 11.3.0 + Clang 14.0.0-1ubuntu1, File-System: ext4, Screen Resolution: 1920x1080 e: Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads), Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS), Chipset: Intel Device 1bce, Memory: 16 x 64 GB 4800MT/s Samsung M321R8GA0BB0-CQKEG, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96, Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T OS: Ubuntu 22.04, Kernel: 6.2.0-060200rc7daily20230208-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3, Vulkan: 1.2.204, Compiler: GCC 11.3.0 + Clang 14.0.0-1ubuntu1, File-System: ext4, Screen Resolution: 1920x1080 srsRAN Project 23.3 Test: Downlink Processor Benchmark Mbps > Higher Is Better a . 326.5 |==================================================================== b . 324.2 |=================================================================== c . 326.7 |==================================================================== d . 320.8 |=================================================================== e . 324.1 |=================================================================== srsRAN Project 23.3 Test: PUSCH Processor Benchmark, Throughput Total Mbps > Higher Is Better a . 7122.4 |=================================================================== b . 6898.6 |================================================================= c . 6547.4 |============================================================== d . 7079.5 |=================================================================== e . 6774.5 |================================================================ srsRAN Project 23.3 Test: PUSCH Processor Benchmark, Throughput Thread Mbps > Higher Is Better a . 29.9 |===================================================================== b . 29.8 |===================================================================== c . 29.7 |===================================================================== d . 28.8 |================================================================== e . 28.9 |=================================================================== VVenC 1.8 Video Input: Bosphorus 4K - Video Preset: Fast Frames Per Second > Higher Is Better a . 6.308 |=================================================================== b . 6.332 |=================================================================== c . 6.314 |=================================================================== d . 6.443 |==================================================================== e . 6.388 |=================================================================== VVenC 1.8 Video Input: Bosphorus 4K - Video Preset: Faster Frames Per Second > Higher Is Better a . 10.065 |=================================================================== b . 10.055 |=================================================================== c . 9.967 |================================================================== d . 9.956 |================================================================== e . 10.067 |=================================================================== VVenC 1.8 Video Input: Bosphorus 1080p - Video Preset: Fast Frames Per Second > Higher Is Better a . 17.15 |=================================================================== b . 17.40 |==================================================================== c . 17.24 |=================================================================== d . 17.21 |=================================================================== e . 16.79 |================================================================== VVenC 1.8 Video Input: Bosphorus 1080p - Video Preset: Faster Frames Per Second > Higher Is Better a . 28.66 |=============================================================== b . 30.99 |==================================================================== c . 30.21 |================================================================== d . 27.62 |============================================================= e . 30.37 |=================================================================== oneDNN 3.1 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 3.56759 |================================================================= b . 3.05000 |======================================================= c . 3.63585 |================================================================== d . 3.50485 |================================================================ e . 3.44677 |=============================================================== oneDNN 3.1 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 2.49757 |=========================================================== b . 2.67699 |=============================================================== c . 2.52848 |=========================================================== d . 2.37479 |======================================================== e . 2.80869 |================================================================== oneDNN 3.1 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 5.19379 |================================================================ b . 4.62478 |========================================================= c . 5.30769 |================================================================== d . 4.87548 |============================================================ e . 5.34755 |================================================================== oneDNN 3.1 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.872476 |================================================= b . 0.978428 |======================================================= c . 1.153320 |================================================================= d . 0.981361 |======================================================= e . 0.989308 |======================================================== oneDNN 3.1 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 5.88472 |================================================================== b . 5.38734 |============================================================ c . 5.42071 |============================================================= d . 4.97718 |======================================================== e . 5.55800 |============================================================== oneDNN 3.1 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 3.16779 |================================================================== b . 3.04638 |=============================================================== c . 2.91381 |============================================================= d . 2.83754 |=========================================================== e . 3.02188 |=============================================================== oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 0.408711 |================================================================= b . 0.402983 |================================================================ c . 0.405677 |================================================================= d . 0.408416 |================================================================= e . 0.400325 |================================================================ oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 14.27 |================================================================== b . 14.63 |==================================================================== c . 14.54 |==================================================================== d . 14.49 |=================================================================== e . 14.22 |================================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 0.724413 |================================================================= b . 0.718746 |================================================================ c . 0.716419 |================================================================ d . 0.711306 |================================================================ e . 0.712248 |================================================================ oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.239960 |==================================== b . 0.314427 |=============================================== c . 0.433523 |================================================================= d . 0.296152 |============================================ e . 0.305503 |============================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.434658 |================================================================= b . 0.410029 |============================================================= c . 0.397435 |=========================================================== d . 0.391957 |=========================================================== e . 0.413735 |============================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.228971 |================================================================= b . 0.225197 |================================================================ c . 0.219341 |============================================================== d . 0.225742 |================================================================ e . 0.219348 |============================================================== oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 1216.99 |================================================================== b . 1155.77 |=============================================================== c . 1209.39 |================================================================== d . 1182.32 |================================================================ e . 1120.64 |============================================================= oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 881.23 |=================================================================== b . 840.96 |================================================================ c . 852.58 |================================================================= d . 731.10 |======================================================== e . 848.65 |================================================================= oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1304.57 |================================================================== b . 1232.87 |============================================================== c . 1081.70 |======================================================= d . 1205.38 |============================================================= e . 1200.19 |============================================================= oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 0.228741 |================================================================= b . 0.223142 |=============================================================== c . 0.217420 |============================================================== d . 0.219490 |============================================================== e . 0.222020 |=============================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 0.470336 |================================================================= b . 0.451393 |============================================================== c . 0.457893 |=============================================================== d . 0.440410 |============================================================= e . 0.446232 |============================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 0.464269 |================================================================= b . 0.466045 |================================================================= c . 0.457996 |================================================================ d . 0.462589 |================================================================= e . 0.453885 |=============================================================== oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 873.15 |=================================================================== b . 832.34 |================================================================ c . 844.36 |================================================================= d . 832.57 |================================================================ e . 845.73 |================================================================= oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 1205.29 |================================================================= b . 1184.14 |================================================================ c . 1228.77 |================================================================== d . 1184.12 |================================================================ e . 1112.04 |============================================================ oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 861.15 |================================================================ b . 878.49 |================================================================= c . 904.27 |=================================================================== d . 888.73 |================================================================== e . 818.44 |============================================================= TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: AlexNet images/sec > Higher Is Better a . 372.88 |================================================================ b . 386.55 |================================================================== c . 370.67 |=============================================================== d . 391.88 |=================================================================== e . 386.34 |================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: AlexNet images/sec > Higher Is Better a . 531.68 |=============================================================== b . 556.34 |================================================================== c . 557.68 |================================================================== d . 536.63 |================================================================ e . 564.79 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: AlexNet images/sec > Higher Is Better a . 743.73 |================================================================== b . 741.87 |================================================================== c . 751.67 |=================================================================== d . 739.02 |================================================================== e . 745.33 |================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: AlexNet images/sec > Higher Is Better a . 1091.42 |================================================================== b . 1077.57 |================================================================= c . 1063.47 |================================================================ d . 1071.62 |================================================================= e . 1062.06 |================================================================ TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: AlexNet images/sec > Higher Is Better a . 1227.69 |================================================================== b . 1231.85 |================================================================== c . 1214.36 |================================================================= d . 1225.54 |================================================================== e . 1230.30 |================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: GoogLeNet images/sec > Higher Is Better a . 173.64 |=============================================================== b . 185.78 |=================================================================== c . 176.84 |================================================================ d . 184.80 |=================================================================== e . 185.22 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: ResNet-50 images/sec > Higher Is Better a . 64.28 |=================================================================== b . 64.31 |=================================================================== c . 63.78 |=================================================================== d . 63.97 |=================================================================== e . 64.96 |==================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: GoogLeNet images/sec > Higher Is Better a . 257.33 |================================================================ b . 267.02 |================================================================== c . 265.08 |================================================================== d . 249.74 |============================================================== e . 270.31 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: ResNet-50 images/sec > Higher Is Better a . 83.13 |=================================================================== b . 84.42 |==================================================================== c . 84.98 |==================================================================== d . 84.17 |=================================================================== e . 83.45 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: GoogLeNet images/sec > Higher Is Better a . 348.00 |=================================================================== b . 342.26 |================================================================== c . 334.11 |================================================================ d . 346.11 |=================================================================== e . 346.20 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: ResNet-50 images/sec > Higher Is Better a . 103.48 |================================================================== b . 102.21 |================================================================== c . 104.52 |=================================================================== d . 103.14 |================================================================== e . 102.87 |================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: GoogLeNet images/sec > Higher Is Better a . 444.17 |=================================================================== b . 442.93 |=================================================================== c . 437.97 |================================================================== d . 441.29 |=================================================================== e . 441.44 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: ResNet-50 images/sec > Higher Is Better a . 130.44 |=================================================================== b . 128.89 |================================================================== c . 127.52 |================================================================== d . 128.80 |================================================================== e . 128.23 |================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: GoogLeNet images/sec > Higher Is Better a . 472.26 |=================================================================== b . 465.31 |================================================================== c . 467.33 |================================================================== d . 462.37 |================================================================== e . 469.14 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: ResNet-50 images/sec > Higher Is Better a . 135.88 |=================================================================== b . 134.34 |================================================================== c . 135.22 |=================================================================== d . 134.76 |================================================================== e . 133.90 |================================================================== Blender 3.5 Blend File: BMW27 - Compute: CPU-Only Seconds < Lower Is Better a . 14.03 |=================================================================== b . 14.20 |==================================================================== c . 14.21 |==================================================================== d . 14.04 |=================================================================== e . 14.30 |==================================================================== Blender 3.5 Blend File: Classroom - Compute: CPU-Only Seconds < Lower Is Better a . 36.50 |=================================================================== b . 36.66 |==================================================================== c . 36.79 |==================================================================== d . 36.31 |=================================================================== e . 36.36 |=================================================================== Blender 3.5 Blend File: Fishy Cat - Compute: CPU-Only Seconds < Lower Is Better a . 19.36 |================================================================= b . 19.70 |=================================================================== c . 19.94 |=================================================================== d . 20.13 |==================================================================== e . 19.54 |================================================================== Blender 3.5 Blend File: Barbershop - Compute: CPU-Only Seconds < Lower Is Better a . 147.25 |=================================================================== b . 147.73 |=================================================================== c . 146.59 |================================================================== d . 147.18 |=================================================================== e . 148.11 |=================================================================== Blender 3.5 Blend File: Pabellon Barcelona - Compute: CPU-Only Seconds < Lower Is Better a . 48.81 |==================================================================== b . 47.84 |=================================================================== c . 47.65 |================================================================== d . 47.73 |================================================================== e . 47.43 |================================================================== nginx 1.23.2 Connections: 100 Requests Per Second > Higher Is Better nginx 1.23.2 Connections: 200 Requests Per Second > Higher Is Better nginx 1.23.2 Connections: 500 Requests Per Second > Higher Is Better a . 250533.37 |================================================================ b . 246156.11 |=============================================================== c . 246619.54 |=============================================================== d . 247581.64 |=============================================================== e . 248416.85 |=============================================================== nginx 1.23.2 Connections: 1000 Requests Per Second > Higher Is Better Apache HTTP Server 2.4.56 Concurrent Requests: 100 Requests Per Second > Higher Is Better Apache HTTP Server 2.4.56 Concurrent Requests: 200 Requests Per Second > Higher Is Better Apache HTTP Server 2.4.56 Concurrent Requests: 500 Requests Per Second > Higher Is Better a . 80395.59 |============================================================= b . 83834.81 |================================================================ c . 77777.03 |=========================================================== d . 84694.76 |================================================================ e . 85357.84 |================================================================= Apache HTTP Server 2.4.56 Concurrent Requests: 1000 Requests Per Second > Higher Is Better