Linux 5.0 To Linux 5.9 On AMD EPYC
AMD EPYC Linux kernel benchmarks by Michael Larabel for a future article.
HTML result view exported from: https://openbenchmarking.org/result/2009078-FI-KERNELCOM02&rdt&grr.
Memcached mcperf
Method: Set - Connections: 32
Memcached mcperf
Method: Get - Connections: 32
MariaDB
Clients: 512
OpenVKL
Benchmark: vklBenchmark
LevelDB
Benchmark: Sequential Fill
LevelDB
Benchmark: Sequential Fill
LevelDB
Benchmark: Random Delete
BlogBench
Test: Read
Facebook RocksDB
Test: Sequential Fill
AI Benchmark Alpha
Device AI Score
AI Benchmark Alpha
Device Training Score
AI Benchmark Alpha
Device Inference Score
WireGuard + Linux Networking Stack Stress Test
High Performance Conjugate Gradient
BRL-CAD
VGR Performance Metric
Renaissance
Test: Apache Spark ALS
Renaissance
Test: Twitter HTTP Requests
Timed LLVM Compilation
Time To Compile
Renaissance
Test: Genetic Algorithm Using Jenetics + Futures
Renaissance
Test: In-Memory Database Shootout
Open Porous Media
OPM Benchmark: Flow MPI Norne - Threads: 8
MariaDB
Clients: 64
LevelDB
Benchmark: Seek Random
asmFish
1024 Hash Memory, 26 Depth
Geekbench
Test: CPU Multi Core - Horizon Detection
Geekbench
Test: CPU Multi Core - Face Detection
Geekbench
Test: CPU Multi Core
Geekbench
Test: CPU Multi Core - Gaussian Blur
Stress-NG
Test: Context Switching
LevelDB
Benchmark: Random Read
LevelDB
Benchmark: Hot Read
KeyDB
TensorFlow Lite
Model: Mobilenet Float
LevelDB
Benchmark: Random Fill
LevelDB
Benchmark: Random Fill
LevelDB
Benchmark: Overwrite
LevelDB
Benchmark: Overwrite
Timed Linux Kernel Compilation
Time To Compile
dav1d
Video Input: Chimera 1080p 10-bit
Apache Siege
Concurrent Users: 200
SQLite Speedtest
Timed Time - Size 1,000
Apache Siege
Concurrent Users: 250
TensorFlow Lite
Model: Inception V4
TensorFlow Lite
Model: Inception ResNet V2
Stress-NG
Test: Forking
Radiance Benchmark
Test: SMP Parallel
YafaRay
Total Time For Sample Scene
Build2
Time To Compile
Stockfish
Total Time
DeepSpeech
Acceleration: CPU
LuxCoreRender
Scene: DLSC
LuxCoreRender
Scene: Rainbow Colors and Prism
TensorFlow Lite
Model: NASNet Mobile
TensorFlow Lite
Model: SqueezeNet
TensorFlow Lite
Model: Mobilenet Quant
Facebook RocksDB
Test: Random Fill Sync
Facebook RocksDB
Test: Random Fill
Facebook RocksDB
Test: Read While Writing
RawTherapee
Total Benchmark Time
Facebook RocksDB
Test: Random Read
Geekbench
Test: CPU Single Core - Horizon Detection
Geekbench
Test: CPU Single Core - Face Detection
Geekbench
Test: CPU Single Core - Gaussian Blur
Geekbench
Test: CPU Single Core
Flexible IO Tester
Type: Sequential Write - Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory
Flexible IO Tester
Type: Sequential Write - Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory
Hugin
Panorama Photo Assistant + Stitching Time
Memcached mcperf
Method: Set - Connections: 1
Memcached mcperf
Method: Delete - Connections: 1
Redis
Test: SET
Stress-NG
Test: System V Message Passing
PostMark
Disk Transaction Performance
Stress-NG
Test: Glibc Qsort Data Sorting
Redis
Test: LPUSH
Flexible IO Tester
Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory
Flexible IO Tester
Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory
Redis
Test: GET
Memcached mcperf
Method: Get - Connections: 1
Flexible IO Tester
Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory
Flexible IO Tester
Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory
Redis
Test: SADD
Zstd Compression
Compression Level: 19
Apache Siege
Concurrent Users: 100
Coremark
CoreMark Size 666 - Iterations Per Second
Flexible IO Tester
Type: Random Write - Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory
Flexible IO Tester
Type: Random Write - Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory
Flexible IO Tester
Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory
Flexible IO Tester
Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory
Flexible IO Tester
Type: Sequential Read - Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory
Flexible IO Tester
Type: Sequential Read - Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory
Flexible IO Tester
Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory
Flexible IO Tester
Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory
Flexible IO Tester
Type: Random Read - Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory
Flexible IO Tester
Type: Random Read - Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory
Zstd Compression
Compression Level: 3
Stress-NG
Test: CPU Stress
Stress-NG
Test: NUMA
Stress-NG
Test: SENDFILE
Stress-NG
Test: MEMFD
Stress-NG
Test: Socket Activity
Stress-NG
Test: MMAP
Stress-NG
Test: Crypto
Stress-NG
Test: Atomic
Stress-NG
Test: Glibc C String Functions
Stress-NG
Test: Semaphores
NAMD
ATPase Simulation - 327,506 Atoms
PyBench
Total For Average Test Times
Timed Apache Compilation
Time To Compile
Swet
Average
Compile Bench
Test: Compile
OCRMyPDF
Processing 60 Page PDF Document
DaCapo Benchmark
Java Test: Tradebeans
miniFE
Problem Size: Small
dav1d
Video Input: Chimera 1080p
DaCapo Benchmark
Java Test: Tradesoap
SVT-AV1
Encoder Mode: Enc Mode 4 - Input: 1080p
DaCapo Benchmark
Java Test: H2
FS-Mark
Test: 5000 Files, 1MB Size, 4 Threads
dav1d
Video Input: Summer Nature 4K
SVT-AV1
Encoder Mode: Enc Mode 8 - Input: 1080p
DaCapo Benchmark
Java Test: Jython
OSBench
Test: Create Processes
Intel Open Image Denoise
Scene: Memorial
FS-Mark
Test: 4000 Files, 32 Sub Dirs, 1MB Size
SQLite
Threads / Copies: 8
OSBench
Test: Create Files
OSBench
Test: Create Threads
OSBench
Test: Memory Allocations
OSBench
Test: Launch Programs
dav1d
Video Input: Summer Nature 1080p
SQLite
Threads / Copies: 1
FS-Mark
Test: 1000 Files, 1MB Size
LevelDB
Benchmark: Fill Sync
LevelDB
Benchmark: Fill Sync
Compile Bench
Test: Initial Create
BlogBench
Test: Write
Phoronix Test Suite v10.8.5