Xeon Gold Cascade Lake Refresh LTS Linux Benchmarks
Intel Xeon Gold 6226R testing with a Supermicro X11SPL-F v1.02 (3.1 BIOS) and ASPEED on Ubuntu 20.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2212171-PTS-XEONGOLD08&grs.
Stress-NG
Test: Context Switching
Stress-NG
Test: System V Message Passing
Stress-NG
Test: MEMFD
Stress-NG
Test: Malloc
Stress-NG
Test: NUMA
ctx_clock
Context Switch Time
PostgreSQL
Scaling Factor: 100 - Clients: 500 - Mode: Read Only
PostgreSQL
Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency
Stress-NG
Test: MMAP
Stress-NG
Test: Mutex
Stress-NG
Test: SENDFILE
PostgreSQL
Scaling Factor: 100 - Clients: 250 - Mode: Read Only
PostgreSQL
Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency
JPEG XL Decoding libjxl
CPU Threads: All
PostgreSQL
Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency
PostgreSQL
Scaling Factor: 100 - Clients: 500 - Mode: Read Write
GraphicsMagick
Operation: Rotate
Dragonflydb
Clients: 50 - Set To Get Ratio: 1:5
PostgreSQL
Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency
PostgreSQL
Scaling Factor: 100 - Clients: 100 - Mode: Read Only
Stress-NG
Test: Forking
GraphicsMagick
Operation: HWB Color Space
Stress-NG
Test: IO_uring
Dragonflydb
Clients: 200 - Set To Get Ratio: 1:5
Dragonflydb
Clients: 200 - Set To Get Ratio: 1:1
Dragonflydb
Clients: 50 - Set To Get Ratio: 5:1
EnCodec
Target Bandwidth: 6 kbps
Facebook RocksDB
Test: Random Fill Sync
Dragonflydb
Clients: 200 - Set To Get Ratio: 5:1
EnCodec
Target Bandwidth: 1.5 kbps
EnCodec
Target Bandwidth: 24 kbps
EnCodec
Target Bandwidth: 3 kbps
Facebook RocksDB
Test: Sequential Fill
oneDNN
Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU
AOM AV1
Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K
PostgreSQL
Scaling Factor: 100 - Clients: 250 - Mode: Read Write
PostgreSQL
Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency
Stargate Digital Audio Workstation
Sample Rate: 192000 - Buffer Size: 1024
JPEG XL libjxl
Input: PNG - Quality: 90
Facebook RocksDB
Test: Update Random
JPEG XL libjxl
Input: JPEG - Quality: 80
JPEG XL libjxl
Input: JPEG - Quality: 90
AOM AV1
Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K
Facebook RocksDB
Test: Random Fill
C-Blosc
Test: blosclz shuffle
JPEG XL Decoding libjxl
CPU Threads: 1
AOM AV1
Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K
PostgreSQL
Scaling Factor: 100 - Clients: 100 - Mode: Read Write
PostgreSQL
Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency
JPEG XL libjxl
Input: PNG - Quality: 80
spaCy
Model: en_core_web_trf
libavif avifenc
Encoder Speed: 10, Lossless
Stargate Digital Audio Workstation
Sample Rate: 44100 - Buffer Size: 512
GraphicsMagick
Operation: Noise-Gaussian
ClickHouse
100M Rows Web Analytics Dataset, Second Run
NCNN
Target: CPU - Model: blazeface
C-Blosc
Test: blosclz bitshuffle
Facebook RocksDB
Test: Read While Writing
ClickHouse
100M Rows Web Analytics Dataset, First Run / Cold Cache
Timed Linux Kernel Compilation
Build: defconfig
Neural Magic DeepSparse
Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream
Neural Magic DeepSparse
Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream
Stargate Digital Audio Workstation
Sample Rate: 96000 - Buffer Size: 512
Stress-NG
Test: Semaphores
Stargate Digital Audio Workstation
Sample Rate: 192000 - Buffer Size: 512
Mobile Neural Network
Model: resnet-v2-50
Timed Linux Kernel Compilation
Build: allmodconfig
Stargate Digital Audio Workstation
Sample Rate: 44100 - Buffer Size: 1024
NCNN
Target: CPU - Model: resnet50
Mobile Neural Network
Model: MobileNetV2_224
Mobile Neural Network
Model: squeezenetv1.1
Numenta Anomaly Benchmark
Detector: KNN CAD
GraphicsMagick
Operation: Resizing
Neural Magic DeepSparse
Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream
Neural Magic DeepSparse
Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream
Timed Erlang/OTP Compilation
Time To Compile
oneDNN
Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU
Neural Magic DeepSparse
Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream
OSPRay Studio
Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer
NCNN
Target: CPU - Model: yolov4-tiny
GraphicsMagick
Operation: Swirl
Timed Godot Game Engine Compilation
Time To Compile
NCNN
Target: CPU - Model: squeezenet_ssd
srsRAN
Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM
SVT-AV1
Encoder Mode: Preset 12 - Input: Bosphorus 1080p
Stargate Digital Audio Workstation
Sample Rate: 96000 - Buffer Size: 1024
Neural Magic DeepSparse
Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream
Neural Magic DeepSparse
Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream
OpenVINO
Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU
OpenVINO
Model: Vehicle Detection FP16 - Device: CPU
OpenVINO
Model: Vehicle Detection FP16 - Device: CPU
JPEG XL libjxl
Input: JPEG - Quality: 100
Stargate Digital Audio Workstation
Sample Rate: 480000 - Buffer Size: 512
JPEG XL libjxl
Input: PNG - Quality: 100
Numenta Anomaly Benchmark
Detector: Relative Entropy
SVT-AV1
Encoder Mode: Preset 13 - Input: Bosphorus 4K
NCNN
Target: CPU - Model: mobilenet
libavif avifenc
Encoder Speed: 6, Lossless
OpenVINO
Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU
Stress-NG
Test: Memory Copying
Stargate Digital Audio Workstation
Sample Rate: 480000 - Buffer Size: 1024
Timed CPython Compilation
Build Configuration: Default
libavif avifenc
Encoder Speed: 6
Mobile Neural Network
Model: nasnet
7-Zip Compression
Test: Compression Rating
NCNN
Target: CPU - Model: FastestDet
Mobile Neural Network
Model: SqueezeNetV1.0
srsRAN
Test: OFDM_Test
Mobile Neural Network
Model: inception-v3
OSPRay Studio
Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer
TensorFlow
Device: CPU - Batch Size: 16 - Model: GoogLeNet
OSPRay Studio
Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer
Neural Magic DeepSparse
Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream
Mobile Neural Network
Model: mobilenet-v1-1.0
Cpuminer-Opt
Algorithm: Myriad-Groestl
Timed Node.js Compilation
Time To Compile
Neural Magic DeepSparse
Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream
OpenVINO
Model: Machine Translation EN To DE FP16 - Device: CPU
OpenVINO
Model: Machine Translation EN To DE FP16 - Device: CPU
FLAC Audio Encoding
WAV To FLAC
Numenta Anomaly Benchmark
Detector: Bayesian Changepoint
SVT-AV1
Encoder Mode: Preset 13 - Input: Bosphorus 1080p
GraphicsMagick
Operation: Enhanced
OpenVINO
Model: Vehicle Detection FP16-INT8 - Device: CPU
Neural Magic DeepSparse
Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream
OSPRay Studio
Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer
Timed PHP Compilation
Time To Compile
NCNN
Target: CPU - Model: shufflenet-v2
OpenVINO
Model: Person Vehicle Bike Detection FP16 - Device: CPU
NCNN
Target: CPU - Model: mnasnet
OpenVINO
Model: Person Vehicle Bike Detection FP16 - Device: CPU
Neural Magic DeepSparse
Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream
ClickHouse
100M Rows Web Analytics Dataset, Third Run
OpenVINO
Model: Vehicle Detection FP16-INT8 - Device: CPU
TensorFlow
Device: CPU - Batch Size: 32 - Model: GoogLeNet
miniBUDE
Implementation: OpenMP - Input Deck: BM1
miniBUDE
Implementation: OpenMP - Input Deck: BM1
Cpuminer-Opt
Algorithm: Ringcoin
Cpuminer-Opt
Algorithm: Blake-2 S
miniBUDE
Implementation: OpenMP - Input Deck: BM2
miniBUDE
Implementation: OpenMP - Input Deck: BM2
TensorFlow
Device: CPU - Batch Size: 16 - Model: ResNet-50
oneDNN
Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU
Neural Magic DeepSparse
Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream
srsRAN
Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM
AOM AV1
Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K
srsRAN
Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM
GraphicsMagick
Operation: Sharpen
OpenFOAM
Input: drivaerFastback, Small Mesh Size - Execution Time
NCNN
Target: CPU - Model: efficientnet-b0
OSPRay Studio
Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer
srsRAN
Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM
OpenVINO
Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU
libavif avifenc
Encoder Speed: 2
Mobile Neural Network
Model: mobilenetV3
NCNN
Target: CPU - Model: googlenet
SVT-AV1
Encoder Mode: Preset 4 - Input: Bosphorus 4K
OpenRadioss
Model: Bumper Beam
Xmrig
Variant: Monero - Hash Count: 1M
OpenVINO
Model: Person Detection FP16 - Device: CPU
BRL-CAD
VGR Performance Metric
Numenta Anomaly Benchmark
Detector: Earthgecko Skyline
Neural Magic DeepSparse
Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream
oneDNN
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU
SVT-AV1
Encoder Mode: Preset 4 - Input: Bosphorus 1080p
srsRAN
Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM
SVT-AV1
Encoder Mode: Preset 8 - Input: Bosphorus 4K
NCNN
Target: CPU - Model: regnety_400m
Stress-NG
Test: Atomic
Cpuminer-Opt
Algorithm: LBC, LBRY Credits
SVT-AV1
Encoder Mode: Preset 12 - Input: Bosphorus 4K
OpenFOAM
Input: drivaerFastback, Medium Mesh Size - Execution Time
Neural Magic DeepSparse
Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream
OpenVINO
Model: Weld Porosity Detection FP16 - Device: CPU
WebP Image Encode
Encode Settings: Quality 100, Lossless
srsRAN
Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM
srsRAN
Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM
Neural Magic DeepSparse
Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream
OpenVINO
Model: Weld Porosity Detection FP16 - Device: CPU
OpenFOAM
Input: drivaerFastback, Small Mesh Size - Mesh Time
WebP Image Encode
Encode Settings: Quality 100
OpenVINO
Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU
spaCy
Model: en_core_web_lg
Cpuminer-Opt
Algorithm: Quad SHA-256, Pyrite
oneDNN
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU
NCNN
Target: CPU-v2-v2 - Model: mobilenet-v2
OpenRadioss
Model: Rubber O-Ring Seal Installation
OpenRadioss
Model: INIVOL and Fluid Structure Interaction Drop Container
WebP Image Encode
Encode Settings: Quality 100, Highest Compression
Y-Cruncher
Pi Digits To Calculate: 500M
OpenVINO
Model: Person Detection FP16 - Device: CPU
Cpuminer-Opt
Algorithm: Triple SHA-256, Onecoin
oneDNN
Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU
Stress-NG
Test: CPU Stress
nekRS
Input: TurboPipe Periodic
OpenVINO
Model: Person Detection FP32 - Device: CPU
Numenta Anomaly Benchmark
Detector: Windowed Gaussian
OpenVINO
Model: Person Detection FP32 - Device: CPU
NCNN
Target: CPU - Model: vision_transformer
oneDNN
Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU
OpenFOAM
Input: drivaerFastback, Medium Mesh Size - Mesh Time
Cpuminer-Opt
Algorithm: Skeincoin
TensorFlow
Device: CPU - Batch Size: 64 - Model: GoogLeNet
Cpuminer-Opt
Algorithm: Deepcoin
Stress-NG
Test: Glibc C String Functions
Timed CPython Compilation
Build Configuration: Released Build, PGO + LTO Optimized
Blender
Blend File: Classroom - Compute: CPU-Only
oneDNN
Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU
oneDNN
Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU
srsRAN
Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM
LAMMPS Molecular Dynamics Simulator
Model: Rhodopsin Protein
SVT-AV1
Encoder Mode: Preset 8 - Input: Bosphorus 1080p
Cpuminer-Opt
Algorithm: x25x
Y-Cruncher
Pi Digits To Calculate: 1B
TensorFlow
Device: CPU - Batch Size: 32 - Model: ResNet-50
Neural Magic DeepSparse
Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream
Neural Magic DeepSparse
Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream
oneDNN
Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU
Cpuminer-Opt
Algorithm: scrypt
Xmrig
Variant: Wownero - Hash Count: 1M
Cpuminer-Opt
Algorithm: Magi
TensorFlow
Device: CPU - Batch Size: 64 - Model: AlexNet
TensorFlow
Device: CPU - Batch Size: 64 - Model: ResNet-50
Neural Magic DeepSparse
Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream
Facebook RocksDB
Test: Random Read
OpenVINO
Model: Face Detection FP16-INT8 - Device: CPU
NCNN
Target: CPU - Model: alexnet
TensorFlow
Device: CPU - Batch Size: 16 - Model: AlexNet
7-Zip Compression
Test: Decompression Rating
Cpuminer-Opt
Algorithm: Garlicoin
Neural Magic DeepSparse
Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream
oneDNN
Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU
oneDNN
Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU
OpenVINO
Model: Face Detection FP16-INT8 - Device: CPU
Blender
Blend File: BMW27 - Compute: CPU-Only
srsRAN
Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM
Neural Magic DeepSparse
Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream
TensorFlow
Device: CPU - Batch Size: 256 - Model: ResNet-50
Stress-NG
Test: Glibc Qsort Data Sorting
Neural Magic DeepSparse
Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream
Neural Magic DeepSparse
Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream
Numenta Anomaly Benchmark
Detector: Contextual Anomaly Detector OSE
Neural Magic DeepSparse
Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream
LAMMPS Molecular Dynamics Simulator
Model: 20k Atoms
Neural Magic DeepSparse
Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream
OSPRay Studio
Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer
OSPRay Studio
Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer
libavif avifenc
Encoder Speed: 0
OSPRay Studio
Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer
TensorFlow
Device: CPU - Batch Size: 256 - Model: AlexNet
OpenRadioss
Model: Bird Strike on Windshield
WebP Image Encode
Encode Settings: Default
OSPRay Studio
Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer
TensorFlow
Device: CPU - Batch Size: 256 - Model: GoogLeNet
Facebook RocksDB
Test: Read Random Write Random
TensorFlow
Device: CPU - Batch Size: 32 - Model: AlexNet
Primesieve
Length: 1e13
oneDNN
Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU
oneDNN
Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU
ASTC Encoder
Preset: Thorough
OpenVINO
Model: Face Detection FP16 - Device: CPU
Blender
Blend File: Pabellon Barcelona - Compute: CPU-Only
srsRAN
Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM
oneDNN
Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU
OSPRay Studio
Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer
Primesieve
Length: 1e12
oneDNN
Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU
OSPRay Studio
Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer
Stress-NG
Test: Vector Math
OpenVINO
Model: Weld Porosity Detection FP16-INT8 - Device: CPU
OSPRay Studio
Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer
OpenRadioss
Model: Cell Phone Drop Test
OSPRay Studio
Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer
Blender
Blend File: Barbershop - Compute: CPU-Only
OpenVINO
Model: Weld Porosity Detection FP16-INT8 - Device: CPU
ASTC Encoder
Preset: Medium
OSPRay Studio
Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer
Stress-NG
Test: Crypto
OpenVINO
Model: Face Detection FP16 - Device: CPU
ASTC Encoder
Preset: Exhaustive
ASTC Encoder
Preset: Fast
Stress-NG
Test: Matrix Math
OSPRay Studio
Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer
Blender
Blend File: Fishy Cat - Compute: CPU-Only
OSPRay Studio
Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer
OSPRay Studio
Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer
OSPRay Studio
Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer
Stress-NG
Test: x86_64 RdRand
Aircrack-ng
Natron
Input: Spaceship
NCNN
Target: CPU-v3-v3 - Model: mobilenet-v3
WebP Image Encode
Encode Settings: Quality 100, Lossless, Highest Compression
NCNN
Target: CPU - Model: resnet18
NCNN
Target: CPU - Model: vgg16
Stress-NG
Test: Socket Activity
Stress-NG
Test: CPU Cache
Stress-NG
Test: Futex
Dragonflydb
Clients: 50 - Set To Get Ratio: 1:1
Phoronix Test Suite v10.8.4