Ubuntu 21.10 EPYC Milan
AMD EPYC 74F3 24-Core testing with a ASRockRack ROME2D16-2T (P3.10 BIOS) and ASPEED on Ubuntu 21.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2110124-TJ-UBUNTU21153&grs.
Stress-NG
Test: IO_uring
Stress-NG
Test: System V Message Passing
Stress-NG
Test: Socket Activity
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 250 - Mode: Read Write
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 500 - Mode: Read Write
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency
Stress-NG
Test: Context Switching
nginx
Concurrent Requests: 20
Stress-NG
Test: MMAP
Apache HTTP Server
Concurrent Requests: 20
nginx
Concurrent Requests: 100
nginx
Concurrent Requests: 200
nginx
Concurrent Requests: 500
nginx
Concurrent Requests: 1000
libavif avifenc
Encoder Speed: 10
Apache HTTP Server
Concurrent Requests: 100
LeelaChessZero
Backend: BLAS
MariaDB
Clients: 512
Redis
Test: GET
Stress-NG
Test: MEMFD
PlaidML
FP16: No - Mode: Inference - Network: VGG19 - Device: CPU
NAS Parallel Benchmarks
Test / Class: CG.C
JPEG XL libjxl
Input: JPEG - Encode Speed: 7
PlaidML
FP16: No - Mode: Inference - Network: VGG16 - Device: CPU
NCNN
Target: CPU-v3-v3 - Model: mobilenet-v3
Mobile Neural Network
Model: MobileNetV2_224
Mobile Neural Network
Model: squeezenetv1.1
NCNN
Target: CPU - Model: resnet50
libavif avifenc
Encoder Speed: 10, Lossless
JPEG XL libjxl
Input: JPEG - Encode Speed: 5
NCNN
Target: CPU - Model: resnet18
NCNN
Target: CPU - Model: mobilenet
Apache HTTP Server
Concurrent Requests: 1000
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 500 - Mode: Read Only
Stress-NG
Test: Forking
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency
Apache HTTP Server
Concurrent Requests: 200
Xcompact3d Incompact3d
Input: input.i3d 129 Cells Per Direction
Apache HTTP Server
Concurrent Requests: 500
NCNN
Target: CPU - Model: yolov4-tiny
Mobile Neural Network
Model: SqueezeNetV1.0
NCNN
Target: CPU - Model: googlenet
NAS Parallel Benchmarks
Test / Class: MG.C
JPEG XL libjxl
Input: PNG - Encode Speed: 7
JPEG XL libjxl
Input: PNG - Encode Speed: 5
NCNN
Target: CPU - Model: efficientnet-b0
JPEG XL libjxl
Input: JPEG - Encode Speed: 8
Apache HTTP Server
Concurrent Requests: 1
Cpuminer-Opt
Algorithm: Blake-2 S
NCNN
Target: CPU - Model: vgg16
libavif avifenc
Encoder Speed: 6
ONNX Runtime
Model: shufflenet-v2-10 - Device: OpenMP CPU
VP9 libvpx Encoding
Speed: Speed 5 - Input: Bosphorus 4K
TensorFlow Lite
Model: NASNet Mobile
OSPray
Demo: NASA Streamlines - Renderer: SciVis
NCNN
Target: CPU - Model: squeezenet_ssd
NCNN
Target: CPU - Model: regnety_400m
NAS Parallel Benchmarks
Test / Class: SP.C
LAMMPS Molecular Dynamics Simulator
Model: Rhodopsin Protein
NAS Parallel Benchmarks
Test / Class: SP.B
NAS Parallel Benchmarks
Test / Class: LU.C
Cpuminer-Opt
Algorithm: Garlicoin
Stress-NG
Test: Matrix Math
ONNX Runtime
Model: fcn-resnet101-11 - Device: OpenMP CPU
NCNN
Target: CPU - Model: mnasnet
PostgreSQL pgbench
Scaling Factor: 1000 - Clients: 500 - Mode: Read Only
PostgreSQL pgbench
Scaling Factor: 1000 - Clients: 500 - Mode: Read Only - Average Latency
Facebook RocksDB
Test: Read Random Write Random
LuxCoreRender
Scene: Danish Mood - Acceleration: CPU
NCNN
Target: CPU-v2-v2 - Model: mobilenet-v2
Stress-NG
Test: SENDFILE
Rodinia
Test: OpenMP Streamcluster
JPEG XL libjxl
Input: PNG - Encode Speed: 8
libavif avifenc
Encoder Speed: 2
Stress-NG
Test: NUMA
PlaidML
FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU
ONNX Runtime
Model: yolov4 - Device: OpenMP CPU
Facebook RocksDB
Test: Update Random
LeelaChessZero
Backend: Eigen
7-Zip Compression
Compress Speed Test
libavif avifenc
Encoder Speed: 6, Lossless
Chaos Group V-RAY
Mode: CPU
Rodinia
Test: OpenMP CFD Solver
Xcompact3d Incompact3d
Input: input.i3d 193 Cells Per Direction
TensorFlow Lite
Model: Mobilenet Quant
NAS Parallel Benchmarks
Test / Class: FT.C
PostgreSQL pgbench
Scaling Factor: 1000 - Clients: 250 - Mode: Read Only - Average Latency
PostgreSQL pgbench
Scaling Factor: 1000 - Clients: 250 - Mode: Read Only
OpenFOAM
Input: Motorbike 60M
oneDNN
Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU
NCNN
Target: CPU - Model: shufflenet-v2
LuxCoreRender
Scene: LuxCore Benchmark - Acceleration: CPU
TTSIOD 3D Renderer
Phong Rendering With Soft-Shadow Mapping
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 250 - Mode: Read Only
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency
TNN
Target: CPU - Model: SqueezeNet v2
Intel Open Image Denoise
Run: RT.ldr_alb_nrm.3840x2160
GROMACS
Implementation: MPI CPU - Input: water_GMX50_bare
oneDNN
Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU
Rodinia
Test: OpenMP LavaMD
SVT-AV1
Encoder Mode: Preset 8 - Input: Bosphorus 4K
AOM AV1
Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K
Cpuminer-Opt
Algorithm: Myriad-Groestl
SecureMark
Benchmark: SecureMark-TLS
NAS Parallel Benchmarks
Test / Class: IS.D
Mobile Neural Network
Model: mobilenet-v1-1.0
x265
Video Input: Bosphorus 1080p
Mobile Neural Network
Model: inception-v3
x265
Video Input: Bosphorus 4K
Stress-NG
Test: CPU Stress
Embree
Binary: Pathtracer ISPC - Model: Crown
TensorFlow Lite
Model: Mobilenet Float
TensorFlow Lite
Model: SqueezeNet
LAMMPS Molecular Dynamics Simulator
Model: 20k Atoms
Stress-NG
Test: Atomic
Timed Linux Kernel Compilation
Time To Compile
SVT-HEVC
Tuning: 7 - Input: Bosphorus 1080p
Cpuminer-Opt
Algorithm: x25x
AOM AV1
Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K
Embree
Binary: Pathtracer - Model: Asian Dragon
Facebook RocksDB
Test: Random Fill
Cpuminer-Opt
Algorithm: Deepcoin
TNN
Target: CPU - Model: MobileNet v2
Xmrig
Variant: Monero - Hash Count: 1M
LuxCoreRender
Scene: DLSC - Acceleration: CPU
SVT-HEVC
Tuning: 10 - Input: Bosphorus 1080p
Embree
Binary: Pathtracer - Model: Crown
Stress-NG
Test: Glibc C String Functions
Stress-NG
Test: Memory Copying
LuxCoreRender
Scene: Orange Juice - Acceleration: CPU
Rodinia
Test: OpenMP Leukocyte
TensorFlow Lite
Model: Inception V4
VP9 libvpx Encoding
Speed: Speed 0 - Input: Bosphorus 4K
Apache Cassandra
Test: Writes
Blender
Blend File: Barbershop - Compute: CPU-Only
Timed Godot Game Engine Compilation
Time To Compile
SVT-VP9
Tuning: VMAF Optimized - Input: Bosphorus 1080p
Timed LLVM Compilation
Build System: Unix Makefiles
TNN
Target: CPU - Model: DenseNet
Timed Node.js Compilation
Time To Compile
Stockfish
Total Time
Cpuminer-Opt
Algorithm: Skeincoin
Xmrig
Variant: Wownero - Hash Count: 1M
Stress-NG
Test: Malloc
TensorFlow Lite
Model: Inception ResNet V2
OpenSSL
Algorithm: SHA256
ASTC Encoder
Preset: Thorough
Cpuminer-Opt
Algorithm: Ringcoin
nginx
Concurrent Requests: 1
Timed LLVM Compilation
Build System: Ninja
OSPray
Demo: San Miguel - Renderer: Path Tracer
Cpuminer-Opt
Algorithm: Triple SHA-256, Onecoin
Sysbench
Test: RAM / Memory
Stress-NG
Test: Semaphores
Cpuminer-Opt
Algorithm: Quad SHA-256, Pyrite
Appleseed
Scene: Emily
simdjson
Throughput Test: PartialTweets
Mobile Neural Network
Model: mobilenetV3
Google SynthMark
Test: VoiceMark_100
simdjson
Throughput Test: DistinctUserID
Blender
Blend File: BMW27 - Compute: CPU-Only
Embree
Binary: Pathtracer ISPC - Model: Asian Dragon
Cpuminer-Opt
Algorithm: Magi
TNN
Target: CPU - Model: SqueezeNet v1.1
AOM AV1
Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K
BRL-CAD
VGR Performance Metric
OpenSSL
Algorithm: RSA4096
Cpuminer-Opt
Algorithm: LBC, LBRY Credits
libavif avifenc
Encoder Speed: 0
Stress-NG
Test: Glibc Qsort Data Sorting
Stress-NG
Test: Vector Math
ASTC Encoder
Preset: Exhaustive
Appleseed
Scene: Material Tester
OpenSSL
Algorithm: RSA4096
OpenFOAM
Input: Motorbike 30M
Stress-NG
Test: Crypto
Sysbench
Test: CPU
Stress-NG
Test: CPU Cache
NAMD
ATPase Simulation - 327,506 Atoms
Natron
Input: Spaceship
OSPray
Demo: Magnetic Reconnection - Renderer: Path Tracer
OSPray
Demo: NASA Streamlines - Renderer: Path Tracer
OSPray
Demo: Magnetic Reconnection - Renderer: SciVis
OSPray
Demo: San Miguel - Renderer: SciVis
simdjson
Throughput Test: LargeRandom
simdjson
Throughput Test: Kostya
ONNX Runtime
Model: super-resolution-10 - Device: OpenMP CPU
ONNX Runtime
Model: bertsquad-10 - Device: OpenMP CPU
NCNN
Target: CPU - Model: alexnet
NCNN
Target: CPU - Model: blazeface
Mobile Neural Network
Model: resnet-v2-50
Redis
Test: SET
PostgreSQL pgbench
Scaling Factor: 1000 - Clients: 500 - Mode: Read Write - Average Latency
PostgreSQL pgbench
Scaling Factor: 1000 - Clients: 500 - Mode: Read Write
PostgreSQL pgbench
Scaling Factor: 1000 - Clients: 250 - Mode: Read Write - Average Latency
PostgreSQL pgbench
Scaling Factor: 1000 - Clients: 250 - Mode: Read Write
LuxCoreRender
Scene: Rainbow Colors and Prism - Acceleration: CPU
Rodinia
Test: OpenMP HotSpot3D
Phoronix Test Suite v10.8.4