Ubuntu 22.10 Early Xeon Comparison Benchmarkss
2 x Intel Xeon Platinum 8380 testing of Linux distros by Michael Larabel for a future article.
HTML result view exported from: https://openbenchmarking.org/result/2209058-NE-LINUX488963&grs.
Stress-NG
Test: NUMA
Zstd Compression
Compression Level: 3, Long Mode - Compression Speed
Zstd Compression
Compression Level: 8, Long Mode - Compression Speed
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 500 - Mode: Read Write
Apache Spark
Row Count: 40000000 - Partitions: 500 - SHA-512 Benchmark Time
DaCapo Benchmark
Java Test: H2
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 250 - Mode: Read Write
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency
C-Blosc
Test: blosclz shuffle
C-Blosc
Test: blosclz bitshuffle
Dragonflydb
Clients: 50 - Set To Get Ratio: 1:5
Dragonflydb
Clients: 50 - Set To Get Ratio: 1:1
Dragonflydb
Clients: 50 - Set To Get Ratio: 5:1
Natron
Input: Spaceship
Stress-NG
Test: Context Switching
Renaissance
Test: Savina Reactors.IO
ONNX Runtime
Model: super-resolution-10 - Device: CPU - Executor: Parallel
Renaissance
Test: Apache Spark Bayes
Renaissance
Test: Random Forest
Renaissance
Test: ALS Movie Lens
Stress-NG
Test: Semaphores
OpenVINO
Model: Vehicle Detection FP16 - Device: CPU
VP9 libvpx Encoding
Speed: Speed 0 - Input: Bosphorus 4K
SVT-AV1
Encoder Mode: Preset 12 - Input: Bosphorus 4K
OpenVINO
Model: Person Detection FP16 - Device: CPU
OpenVINO
Model: Person Detection FP32 - Device: CPU
OpenVINO
Model: Face Detection FP16 - Device: CPU
Timed LLVM Compilation
Build System: Ninja
GraphicsMagick
Operation: Noise-Gaussian
SVT-AV1
Encoder Mode: Preset 10 - Input: Bosphorus 4K
OpenVINO
Model: Vehicle Detection FP16-INT8 - Device: CPU
OpenVINO
Model: Face Detection FP16-INT8 - Device: CPU
SVT-AV1
Encoder Mode: Preset 8 - Input: Bosphorus 4K
libavif avifenc
Encoder Speed: 6
OpenVINO
Model: Machine Translation EN To DE FP16 - Device: CPU
SVT-AV1
Encoder Mode: Preset 4 - Input: Bosphorus 4K
ClickHouse
100M Rows Web Analytics Dataset, First Run / Cold Cache
ClickHouse
100M Rows Web Analytics Dataset, Second Run
libavif avifenc
Encoder Speed: 6, Lossless
ClickHouse
100M Rows Web Analytics Dataset, Third Run
libavif avifenc
Encoder Speed: 10, Lossless
SVT-HEVC
Tuning: 10 - Input: Bosphorus 4K
SVT-HEVC
Tuning: 7 - Input: Bosphorus 4K
OSPRay
Benchmark: particle_volume/pathtracer/real_time
Redis
Test: GET - Parallel Connections: 50
SVT-VP9
Tuning: Visual Quality Optimized - Input: Bosphorus 4K
SVT-VP9
Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4K
GraphicsMagick
Operation: Rotate
SVT-VP9
Tuning: VMAF Optimized - Input: Bosphorus 4K
7-Zip Compression
Test: Compression Rating
GraphicsMagick
Operation: Sharpen
TNN
Target: CPU - Model: DenseNet
GraphicsMagick
Operation: Swirl
Node.js V8 Web Tooling Benchmark
Stress-NG
Test: IO_uring
Zstd Compression
Compression Level: 19, Long Mode - Compression Speed
Zstd Compression
Compression Level: 3 - Compression Speed
Zstd Compression
Compression Level: 19 - Compression Speed
Redis
Test: GET - Parallel Connections: 1000
Stress-NG
Test: Memory Copying
Unpacking The Linux Kernel
linux-5.19.tar.xz
libavif avifenc
Encoder Speed: 2
Stress-NG
Test: Malloc
WebP Image Encode
Encode Settings: Quality 100, Lossless
Stress-NG
Test: Glibc C String Functions
Timed Linux Kernel Compilation
Build: defconfig
ONNX Runtime
Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel
Timed GDB GNU Debugger Compilation
Time To Compile
Stress-NG
Test: MMAP
Apache HTTP Server
Concurrent Requests: 1000
Mobile Neural Network
Model: MobileNetV2_224
Stress-NG
Test: Matrix Math
Apache Spark
Row Count: 40000000 - Partitions: 500 - Calculate Pi Benchmark
ASTC Encoder
Preset: Medium
Stress-NG
Test: Crypto
OpenVINO
Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU
Redis
Test: SET - Parallel Connections: 50
ONNX Runtime
Model: bertsquad-12 - Device: CPU - Executor: Standard
ONNX Runtime
Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard
WebP Image Encode
Encode Settings: Quality 100, Lossless, Highest Compression
libavif avifenc
Encoder Speed: 0
WebP Image Encode
Encode Settings: Quality 100, Highest Compression
ASTC Encoder
Preset: Thorough
GraphicsMagick
Operation: Enhanced
oneDNN
Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU
Stress-NG
Test: SENDFILE
Zstd Compression
Compression Level: 3 - Decompression Speed
TNN
Target: CPU - Model: SqueezeNet v2
nginx
Concurrent Requests: 1000
ASTC Encoder
Preset: Exhaustive
Zstd Compression
Compression Level: 3, Long Mode - Decompression Speed
OpenVINO
Model: Machine Translation EN To DE FP16 - Device: CPU
OpenVINO
Model: Weld Porosity Detection FP16-INT8 - Device: CPU
OpenVINO
Model: Weld Porosity Detection FP16-INT8 - Device: CPU
Stress-NG
Test: MEMFD
Zstd Compression
Compression Level: 8 - Decompression Speed
Zstd Compression
Compression Level: 8, Long Mode - Decompression Speed
Stress-NG
Test: Forking
OSPRay
Benchmark: gravity_spheres_volume/dim_512/ao/real_time
OpenVINO
Model: Vehicle Detection FP16 - Device: CPU
Renaissance
Test: In-Memory Database Shootout
OSPRay
Benchmark: gravity_spheres_volume/dim_512/scivis/real_time
Mobile Neural Network
Model: mobilenetV3
Zstd Compression
Compression Level: 19 - Decompression Speed
OpenVINO
Model: Person Detection FP16 - Device: CPU
GROMACS
Implementation: MPI CPU - Input: water_GMX50_bare
OpenVINO
Model: Person Detection FP32 - Device: CPU
simdjson
Throughput Test: PartialTweets
7-Zip Compression
Test: Decompression Rating
Zstd Compression
Compression Level: 19, Long Mode - Decompression Speed
TNN
Target: CPU - Model: SqueezeNet v1.1
ONNX Runtime
Model: bertsquad-12 - Device: CPU - Executor: Parallel
ASTC Encoder
Preset: Fast
Blender
Blend File: Fishy Cat - Compute: CPU-Only
Stress-NG
Test: Vector Math
Stress-NG
Test: Glibc Qsort Data Sorting
OSPRay Studio
Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer
Mobile Neural Network
Model: inception-v3
simdjson
Throughput Test: LargeRandom
OSPRay Studio
Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer
Blender
Blend File: BMW27 - Compute: CPU-Only
OSPRay Studio
Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer
OSPRay Studio
Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer
simdjson
Throughput Test: Kostya
ONNX Runtime
Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel
OSPRay Studio
Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer
OSPRay Studio
Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer
Blender
Blend File: Barbershop - Compute: CPU-Only
OpenVINO
Model: Face Detection FP16 - Device: CPU
Stress-NG
Test: CPU Stress
Mobile Neural Network
Model: resnet-v2-50
Blender
Blend File: Pabellon Barcelona - Compute: CPU-Only
OpenVINO
Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU
simdjson
Throughput Test: TopTweet
Blender
Blend File: Classroom - Compute: CPU-Only
oneDNN
Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU
Stress-NG
Test: CPU Cache
LAMMPS Molecular Dynamics Simulator
Model: 20k Atoms
ONNX Runtime
Model: yolov4 - Device: CPU - Executor: Parallel
OSPRay
Benchmark: particle_volume/scivis/real_time
OpenVINO
Model: Face Detection FP16-INT8 - Device: CPU
OSPRay
Benchmark: particle_volume/ao/real_time
OpenVINO
Model: Weld Porosity Detection FP16 - Device: CPU
ONNX Runtime
Model: GPT-2 - Device: CPU - Executor: Parallel
OpenVINO
Model: Weld Porosity Detection FP16 - Device: CPU
OpenVINO
Model: Vehicle Detection FP16-INT8 - Device: CPU
High Performance Conjugate Gradient
oneDNN
Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU
simdjson
Throughput Test: DistinctUserID
OSPRay
Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time
OpenSSL
OpenSSL
oneDNN
Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU
Stress-NG
Test: x86_64 RdRand
InfluxDB
Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000
NAMD
ATPase Simulation - 327,506 Atoms
Apache Spark
Row Count: 40000000 - Partitions: 500 - Broadcast Inner Join Test Time
Apache Spark
Row Count: 40000000 - Partitions: 500 - Inner Join Test Time
Apache Spark
Row Count: 40000000 - Partitions: 500 - Repartition Test Time
Apache Spark
Row Count: 40000000 - Partitions: 500 - Group By Test Time
ONNX Runtime
Model: super-resolution-10 - Device: CPU - Executor: Standard
ONNX Runtime
Model: fcn-resnet101-11 - Device: CPU - Executor: Standard
ONNX Runtime
Model: yolov4 - Device: CPU - Executor: Standard
ONNX Runtime
Model: GPT-2 - Device: CPU - Executor: Standard
OpenVINO
Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU
OpenVINO
Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU
OpenVINO
Model: Person Vehicle Bike Detection FP16 - Device: CPU
OpenVINO
Model: Person Vehicle Bike Detection FP16 - Device: CPU
TNN
Target: CPU - Model: MobileNet v2
Mobile Neural Network
Model: mobilenet-v1-1.0
Mobile Neural Network
Model: SqueezeNetV1.0
Mobile Neural Network
Model: squeezenetv1.1
Mobile Neural Network
Model: nasnet
Stress-NG
Test: System V Message Passing
Stress-NG
Test: Socket Activity
Stress-NG
Test: Atomic
Stress-NG
Test: Futex
memtier_benchmark
Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:10
memtier_benchmark
Protocol: Redis - Clients: 50 - Set To Get Ratio: 5:1
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 500 - Mode: Read Only
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 250 - Mode: Read Only
TensorFlow Lite
Model: Inception ResNet V2
TensorFlow Lite
Model: Mobilenet Quant
TensorFlow Lite
Model: Mobilenet Float
TensorFlow Lite
Model: NASNet Mobile
TensorFlow Lite
Model: Inception V4
TensorFlow Lite
Model: SqueezeNet
KeyDB
Redis
Test: SET - Parallel Connections: 1000
Redis
Test: SET - Parallel Connections: 500
Redis
Test: GET - Parallel Connections: 500
Apache Spark
Row Count: 40000000 - Partitions: 500 - Calculate Pi Benchmark Using Dataframe
oneDNN
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU
oneDNN
Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU
oneDNN
Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU
oneDNN
Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU
Stockfish
Total Time
x264
Video Input: Bosphorus 4K
GraphicsMagick
Operation: HWB Color Space
GraphicsMagick
Operation: Resizing
Node.js Express HTTP Load Test
Zstd Compression
Compression Level: 8 - Compression Speed
Renaissance
Test: Finagle HTTP Requests
DaCapo Benchmark
Java Test: Jython
WebP Image Encode
Encode Settings: Quality 100
WebP Image Encode
Encode Settings: Default
LAMMPS Molecular Dynamics Simulator
Model: Rhodopsin Protein
Phoronix Test Suite v10.8.5