AMD Ryzen 7 7800X3D Linux AMD Ryzen 7 7800X3D 8-Core testing with a ASUS ROG CROSSHAIR X670E HERO (9927 BIOS) and AMD Radeon RX 7900 XTX on Ubuntu 23.04 via the Phoronix Test Suite. a: Processor: AMD Ryzen 7 7800X3D 8-Core @ 4.20GHz (8 Cores / 16 Threads), Motherboard: ASUS ROG CROSSHAIR X670E HERO (9927 BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: Western Digital WD_BLACK SN850X 1000GB, Graphics: AMD Radeon RX 7900 XTX (2304/1249MHz), Audio: AMD Device ab30, Monitor: ASUS MG28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411 OS: Ubuntu 23.04, Kernel: 6.2.8-060208-generic (x86_64), Desktop: GNOME Shell 44.0, Display Server: X Server 1.21.1.7 + Wayland, OpenGL: 4.6 Mesa 23.1.0-devel (git-de8b14f 2023-03-24 lunar-oibaf-ppa) (LLVM 15.0.7 DRM 3.49), OpenCL: OpenCL 2.1 AMD-APP (3513.0), Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160 b: Processor: AMD Ryzen 7 7800X3D 8-Core @ 4.20GHz (8 Cores / 16 Threads), Motherboard: ASUS ROG CROSSHAIR X670E HERO (9927 BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: Western Digital WD_BLACK SN850X 1000GB, Graphics: AMD Radeon RX 7900 XTX (2304/1249MHz), Audio: AMD Device ab30, Monitor: ASUS MG28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411 OS: Ubuntu 23.04, Kernel: 6.2.8-060208-generic (x86_64), Desktop: GNOME Shell 44.0, Display Server: X Server 1.21.1.7 + Wayland, OpenGL: 4.6 Mesa 23.1.0-devel (git-de8b14f 2023-03-24 lunar-oibaf-ppa) (LLVM 15.0.7 DRM 3.49), OpenCL: OpenCL 2.1 AMD-APP (3513.0), Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160 OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Mesh Time Seconds < Lower Is Better a . 27.20 |============================================================== b . 29.93 |==================================================================== GNU Radio Test: Five Back to Back FIR Filters MiB/s > Higher Is Better a . 1821.2 |=================================================================== b . 1715.3 |=============================================================== ASKAP 1.0 Test: tConvolve OpenMP - Gridding Million Grid Points Per Second > Higher Is Better a . 8068.36 |================================================================== b . 7607.31 |============================================================== ASKAP 1.0 Test: tConvolve MT - Degridding Million Grid Points Per Second > Higher Is Better a . 2252.83 |================================================================== b . 2159.20 |=============================================================== ACES DGEMM 1.0 Sustained Floating-Point Rate GFLOP/s > Higher Is Better a . 6.112455 |============================================================== b . 6.373565 |================================================================= ASKAP 1.0 Test: tConvolve MPI - Gridding Mpix/sec > Higher Is Better a . 10495.8 |=============================================================== b . 10933.2 |================================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 5.51978 |================================================================== b . 5.32498 |================================================================ Renaissance 0.14 Test: ALS Movie Lens ms < Lower Is Better a . 5903.6 |=================================================================== b . 5716.0 |================================================================= ASKAP 1.0 Test: tConvolve MPI - Degridding Mpix/sec > Higher Is Better a . 8464.38 |================================================================== b . 8199.86 |================================================================ Renaissance 0.14 Test: Akka Unbalanced Cobwebbed Tree ms < Lower Is Better a . 5680.7 |================================================================= b . 5860.4 |=================================================================== Renaissance 0.14 Test: Apache Spark Bayes ms < Lower Is Better a . 900.0 |==================================================================== b . 873.8 |================================================================== ASKAP 1.0 Test: tConvolve MT - Gridding Million Grid Points Per Second > Higher Is Better a . 1914.65 |================================================================== b . 1861.93 |================================================================ GNU Radio Test: FM Deemphasis Filter MiB/s > Higher Is Better a . 1113.8 |================================================================= b . 1141.3 |=================================================================== Apache HTTP Server 2.4.56 Concurrent Requests: 200 Requests Per Second > Higher Is Better a . 193855.44 |================================================================ b . 189635.84 |=============================================================== Renaissance 0.14 Test: Finagle HTTP Requests ms < Lower Is Better a . 1879.6 |=================================================================== b . 1843.8 |================================================================== ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run Queries Per Minute, Geo Mean > Higher Is Better a . 278.90 |=================================================================== b . 273.75 |================================================================== ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run Queries Per Minute, Geo Mean > Higher Is Better a . 274.60 |=================================================================== b . 270.69 |================================================================== Apache HTTP Server 2.4.56 Concurrent Requests: 500 Requests Per Second > Higher Is Better a . 185789.30 |================================================================ b . 183386.87 |=============================================================== Apache HTTP Server 2.4.56 Concurrent Requests: 100 Requests Per Second > Higher Is Better a . 179311.78 |=============================================================== b . 181582.13 |================================================================ Renaissance 0.14 Test: Genetic Algorithm Using Jenetics + Futures ms < Lower Is Better a . 953.8 |==================================================================== b . 942.4 |=================================================================== GNU Radio Test: IIR Filter MiB/s > Higher Is Better a . 500.9 |=================================================================== b . 506.6 |==================================================================== Renaissance 0.14 Test: Apache Spark PageRank ms < Lower Is Better a . 1787.6 |================================================================== b . 1807.0 |=================================================================== Numenta Anomaly Benchmark 1.1 Detector: Relative Entropy Seconds < Lower Is Better a . 9.848 |=================================================================== b . 9.948 |==================================================================== Numenta Anomaly Benchmark 1.1 Detector: Windowed Gaussian Seconds < Lower Is Better a . 5.654 |==================================================================== b . 5.599 |=================================================================== Numenta Anomaly Benchmark 1.1 Detector: Earthgecko Skyline Seconds < Lower Is Better a . 61.73 |=================================================================== b . 62.24 |==================================================================== Renaissance 0.14 Test: Savina Reactors.IO ms < Lower Is Better a . 3153.6 |=================================================================== b . 3128.9 |================================================================== Numenta Anomaly Benchmark 1.1 Detector: Bayesian Changepoint Seconds < Lower Is Better a . 17.33 |==================================================================== b . 17.20 |=================================================================== 7-Zip Compression 22.01 Test: Compression Rating MIPS > Higher Is Better a . 112513 |================================================================== b . 113370 |=================================================================== Renaissance 0.14 Test: Scala Dotty ms < Lower Is Better a . 439.9 |==================================================================== b . 436.6 |=================================================================== Memcached 1.6.19 Set To Get Ratio: 1:5 Ops/sec > Higher Is Better a . 3272684.62 |=============================================================== b . 3250299.72 |=============================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 7.66355 |================================================================== b . 7.71613 |================================================================== Numenta Anomaly Benchmark 1.1 Detector: Contextual Anomaly Detector OSE Seconds < Lower Is Better a . 25.46 |==================================================================== b . 25.29 |==================================================================== Memcached 1.6.19 Set To Get Ratio: 1:10 Ops/sec > Higher Is Better a . 2921694.2 |================================================================ b . 2902278.7 |================================================================ CloverLeaf Lagrangian-Eulerian Hydrodynamics Seconds < Lower Is Better a . 39.39 |==================================================================== b . 39.15 |==================================================================== Apache HTTP Server 2.4.56 Concurrent Requests: 1000 Requests Per Second > Higher Is Better a . 182530.28 |================================================================ b . 183626.22 |================================================================ oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 4.74584 |================================================================== b . 4.71913 |================================================================== Renaissance 0.14 Test: Apache Spark ALS ms < Lower Is Better a . 1931.2 |=================================================================== b . 1941.4 |=================================================================== GNU Radio Test: FIR Filter MiB/s > Higher Is Better a . 1391.1 |=================================================================== b . 1398.4 |=================================================================== OpenFOAM 10 Input: drivaerFastback, Medium Mesh Size - Mesh Time Seconds < Lower Is Better a . 222.26 |=================================================================== b . 223.41 |=================================================================== Renaissance 0.14 Test: Random Forest ms < Lower Is Better a . 402.3 |==================================================================== b . 400.5 |==================================================================== oneDNN 3.1 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.365467 |================================================================= b . 0.367087 |================================================================= Memcached 1.6.19 Set To Get Ratio: 1:100 Ops/sec > Higher Is Better a . 2841542.11 |=============================================================== b . 2829008.81 |=============================================================== Timed Godot Game Engine Compilation 4.0 Time To Compile Seconds < Lower Is Better a . 300.00 |=================================================================== b . 298.68 |=================================================================== Xmrig 6.18.1 Variant: Monero - Hash Count: 1M H/s > Higher Is Better a . 9490.8 |=================================================================== b . 9531.3 |=================================================================== ASTC Encoder 4.0 Preset: Thorough MT/s > Higher Is Better a . 7.8220 |=================================================================== b . 7.8537 |=================================================================== 7-Zip Compression 22.01 Test: Decompression Rating MIPS > Higher Is Better a . 87240 |==================================================================== b . 86914 |==================================================================== GNU Radio Test: Signal Source (Cosine) MiB/s > Higher Is Better a . 5454.6 |=================================================================== b . 5472.7 |=================================================================== oneDNN 3.1 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 3.33782 |================================================================== b . 3.34819 |================================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1.01001 |================================================================== b . 1.00696 |================================================================== oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 5.16302 |================================================================== b . 5.14851 |================================================================== nginx 1.23.2 Connections: 1000 Requests Per Second > Higher Is Better a . 93560.28 |================================================================= b . 93822.98 |================================================================= nginx 1.23.2 Connections: 500 Requests Per Second > Higher Is Better a . 96954.32 |================================================================= b . 96692.89 |================================================================= TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: ResNet-50 images/sec > Higher Is Better a . 33.57 |==================================================================== b . 33.66 |==================================================================== OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Execution Time Seconds < Lower Is Better a . 169.70 |=================================================================== b . 170.15 |=================================================================== Build2 0.15 Time To Compile Seconds < Lower Is Better a . 119.41 |=================================================================== b . 119.16 |=================================================================== GNU Radio Test: Hilbert Transform MiB/s > Higher Is Better a . 704.4 |==================================================================== b . 702.9 |==================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: GoogLeNet images/sec > Higher Is Better a . 96.41 |==================================================================== b . 96.61 |==================================================================== oneDNN 3.1 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 1.21056 |================================================================== b . 1.20831 |================================================================== oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 1121.90 |================================================================== b . 1123.68 |================================================================== oneDNN 3.1 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 1.25071 |================================================================== b . 1.25253 |================================================================== ASTC Encoder 4.0 Preset: Medium MT/s > Higher Is Better a . 63.32 |==================================================================== b . 63.23 |==================================================================== OpenFOAM 10 Input: drivaerFastback, Medium Mesh Size - Execution Time Seconds < Lower Is Better a . 2121.75 |================================================================== b . 2118.76 |================================================================== Timed Linux Kernel Compilation 6.1 Build: defconfig Seconds < Lower Is Better a . 80.73 |==================================================================== b . 80.83 |==================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: ResNet-50 images/sec > Higher Is Better a . 32.74 |==================================================================== b . 32.78 |==================================================================== ASTC Encoder 4.0 Preset: Fast MT/s > Higher Is Better a . 181.00 |=================================================================== b . 181.20 |=================================================================== nginx 1.23.2 Connections: 100 Requests Per Second > Higher Is Better a . 97810.40 |================================================================= b . 97914.05 |================================================================= nginx 1.23.2 Connections: 200 Requests Per Second > Higher Is Better a . 98163.47 |================================================================= b . 98262.15 |================================================================= ASTC Encoder 4.0 Preset: Exhaustive MT/s > Higher Is Better a . 0.8299 |=================================================================== b . 0.8305 |=================================================================== oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 2227.52 |================================================================== b . 2229.02 |================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: AlexNet images/sec > Higher Is Better a . 177.73 |=================================================================== b . 177.84 |=================================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 2.47403 |================================================================== b . 2.47255 |================================================================== Pennant 1.0.1 Test: sedovbig Hydro Cycle Time - Seconds < Lower Is Better a . 42.31 |==================================================================== b . 42.34 |==================================================================== Algebraic Multi-Grid Benchmark 1.2 Figure Of Merit > Higher Is Better a . 406211800 |================================================================ b . 406014500 |================================================================ Xmrig 6.18.1 Variant: Wownero - Hash Count: 1M H/s > Higher Is Better a . 10015.9 |================================================================== b . 10011.1 |================================================================== Pennant 1.0.1 Test: leblancbig Hydro Cycle Time - Seconds < Lower Is Better a . 27.26 |==================================================================== b . 27.25 |==================================================================== oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 1121.00 |================================================================== b . 1121.34 |================================================================== oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 2227.01 |================================================================== b . 2227.67 |================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: GoogLeNet images/sec > Higher Is Better a . 101.24 |=================================================================== b . 101.27 |=================================================================== Blender 3.5 Blend File: BMW27 - Compute: CPU-Only Seconds < Lower Is Better a . 104.47 |=================================================================== b . 104.50 |=================================================================== oneDNN 3.1 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.620111 |================================================================= b . 0.619937 |================================================================= Numenta Anomaly Benchmark 1.1 Detector: KNN CAD Seconds < Lower Is Better a . 152.93 |=================================================================== b . 152.88 |=================================================================== oneDNN 3.1 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 3.09967 |================================================================== b . 3.09914 |================================================================== oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1122.76 |================================================================== b . 1122.58 |================================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 4.10260 |================================================================== b . 4.10323 |================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: AlexNet images/sec > Higher Is Better a . 209.51 |=================================================================== b . 209.54 |=================================================================== oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 2.04864 |================================================================== b . 2.04844 |================================================================== ClickHouse 22.12.3.5 100M Rows Hits Dataset, First Run / Cold Cache Queries Per Minute, Geo Mean > Higher Is Better a . 247.77 |=================================================================== b . 247.75 |=================================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.830924 |================================================================= b . 0.830898 |================================================================= oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 2226.82 |================================================================== b . 2226.86 |================================================================== ASKAP 1.0 Test: Hogbom Clean OpenMP Iterations Per Second > Higher Is Better a . 735.29 |=================================================================== b . 735.29 |=================================================================== ASKAP 1.0 Test: tConvolve OpenMP - Degridding Million Grid Points Per Second > Higher Is Better a . 9861.33 |================================================================== b . 9861.33 |================================================================== ASKAP 1.0 Test: tConvolve OpenCL Million Grid Points Per Second > Higher Is Better Renaissance 0.14 Test: In-Memory Database Shootout ms < Lower Is Better