sched/core Git testing for what will be in Linux 5.18. Benchmarks by Michael Larabel for a future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2202208-NE-AMDEPYCLI02
AMD EPYC Linux 5.18 Sched-Core Testing
sched/core Git testing for what will be in Linux 5.18. Benchmarks by Michael Larabel for a future article.
,,"sched-core Git","Linux 5.17 Git"
Processor,,2 x AMD EPYC 75F3 32-Core @ 2.95GHz (64 Cores / 128 Threads),2 x AMD EPYC 75F3 32-Core @ 2.95GHz (64 Cores / 128 Threads)
Motherboard,,ASRockRack ROME2D16-2T (P3.10 BIOS),ASRockRack ROME2D16-2T (P3.10 BIOS)
Chipset,,AMD Starship/Matisse,AMD Starship/Matisse
Memory,,128GB,128GB
Disk,,1000GB Western Digital WD_BLACK SN850 1TB,1000GB Western Digital WD_BLACK SN850 1TB
Graphics,,ASPEED,ASPEED
Audio,,AMD Starship/Matisse,AMD Starship/Matisse
Network,,2 x Intel 10G X550T,2 x Intel 10G X550T
OS,,Ubuntu 21.10,Ubuntu 21.10
Kernel,,5.17.0-rc1-sched-core-phx (x86_64),5.17.0-051700rc4daily20220219-generic (x86_64)
Desktop,,GNOME Shell 40.5,GNOME Shell 40.5
Display Server,,X Server,X Server
Vulkan,,1.1.182,1.1.182
Compiler,,GCC 11.2.0,GCC 11.2.0
File-System,,ext4,ext4
Screen Resolution,,1920x1080,1920x1080
,,"sched-core Git","Linux 5.17 Git"
"OpenVKL - Benchmark: vklBenchmark ISPC (Items / Sec)",HIB,157,156
"OpenVKL - Benchmark: vklBenchmark Scalar (Items / Sec)",HIB,103,102
"ASKAP - Test: tConvolve MT - Degridding (Million Grid Points/sec)",HIB,9964.11,9328.17
"ASKAP - Test: tConvolve MT - Gridding (Million Grid Points/sec)",HIB,6438.42,4987.40
"MariaDB - Clients: 512 (Queries/sec)",HIB,286,273
"MariaDB - Clients: 256 (Queries/sec)",HIB,288,271
"Java Gradle Build - Gradle Build: Reactor (sec)",LIB,329.553,335.244
"Facebook RocksDB - Test: Sequential Fill (Op/s)",HIB,228657,183816
"MariaDB - Clients: 128 (Queries/sec)",HIB,344,312
"NWChem - Input: C240 Buckyball (sec)",LIB,1846.4,1839.3
"MariaDB - Clients: 64 (Queries/sec)",HIB,705,644
"PostgreSQL pgbench - Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency (ms)",LIB,1.412,2.027
"PostgreSQL pgbench - Scaling Factor: 100 - Clients: 50 - Mode: Read Write (TPS)",HIB,35760,24965
"LeelaChessZero - Backend: Eigen (Nodes/s)",HIB,7292,7102
"MariaDB - Clients: 32 (Queries/sec)",HIB,1555,1321
"PostgreSQL pgbench - Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency (ms)",LIB,2.001,2.229
"PostgreSQL pgbench - Scaling Factor: 100 - Clients: 100 - Mode: Read Write (TPS)",HIB,49992,44919
"PostgreSQL pgbench - Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency (ms)",LIB,0.144,0.152
"PostgreSQL pgbench - Scaling Factor: 100 - Clients: 250 - Mode: Read Only (TPS)",HIB,1736309,1646094
"PostgreSQL pgbench - Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency (ms)",LIB,0.046,0.076
"PostgreSQL pgbench - Scaling Factor: 100 - Clients: 50 - Mode: Read Only (TPS)",HIB,1089131,658289
"Graph500 - Scale: 26 (sssp max_TEPS)",HIB,307481000,319022000
"Graph500 - Scale: 26 (sssp median_TEPS)",HIB,256666000,259326000
"Graph500 - Scale: 26 (bfs max_TEPS)",HIB,553141000,568087000
"Graph500 - Scale: 26 (bfs median_TEPS)",HIB,522116000,548799000
"TensorFlow Lite - Model: Inception V4 (us)",LIB,815904,912019
"Darmstadt Automotive Parallel Heterogeneous Suite - Backend: OpenMP - Kernel: Points2Image (Test Cases/min)",HIB,11963.768989834,10961.13
"Timed Gem5 Compilation - Time To Compile (sec)",LIB,167.719,165.614
"BRL-CAD - VGR Performance Metric (VGR Performance Metric)",HIB,857076,865080
"TensorFlow Lite - Model: Mobilenet Quant (us)",LIB,30978.4,31535.2
"TNN - Target: CPU - Model: DenseNet (ms)",LIB,2848.366,2847.410
"LuxCoreRender - Scene: Danish Mood - Acceleration: CPU (M samples/sec)",HIB,6.05,6.05
"Timed Linux Kernel Compilation - Build: allmodconfig (sec)",LIB,185.399,188.268
"Facebook RocksDB - Test: Update Random (Op/s)",HIB,253758,227357
"TensorFlow Lite - Model: Mobilenet Float (us)",LIB,29946.3,37448.7
"Facebook RocksDB - Test: Read While Writing (Op/s)",HIB,9855545,9728767
"Timed LLVM Compilation - Build System: Unix Makefiles (sec)",LIB,171.384,172.766
"High Performance Conjugate Gradient - (GFLOP/s)",HIB,35.5011,35.4365
"OpenFOAM - Input: Motorbike 60M (sec)",LIB,114.41,114.35
"TensorFlow Lite - Model: Inception ResNet V2 (us)",LIB,727002,932541
"MariaDB - Clients: 16 (Queries/sec)",HIB,2869,2582
"PostgreSQL pgbench - Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency (ms)",LIB,0.267,0.295
"PostgreSQL pgbench - Scaling Factor: 100 - Clients: 500 - Mode: Read Only (TPS)",HIB,1873697,1697490
"PostgreSQL pgbench - Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency (ms)",LIB,0.068,0.087
"PostgreSQL pgbench - Scaling Factor: 100 - Clients: 100 - Mode: Read Only (TPS)",HIB,1465660,1144931
"Timed LLVM Compilation - Build System: Ninja (sec)",LIB,115.760,117.319
"Timed Node.js Compilation - Time To Compile (sec)",LIB,109.710,111.355
"Timed MrBayes Analysis - Primate Phylogeny Analysis (sec)",LIB,99.416,104.865
"Sysbench - Test: CPU (Events/sec)",HIB,308160.07,303171.90
"AOM AV1 - Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K (FPS)",HIB,7.52,7.39
"MariaDB - Clients: 8 (Queries/sec)",HIB,3311,2799
"LuxCoreRender - Scene: LuxCore Benchmark - Acceleration: CPU (M samples/sec)",HIB,6.20,5.36
"LuxCoreRender - Scene: DLSC - Acceleration: CPU (M samples/sec)",HIB,10.07,10.04
"Facebook RocksDB - Test: Random Fill Sync (Op/s)",HIB,100674,86513
"QMCPACK - Input: simple-H2O (Execution Time - sec)",LIB,28.666,29.424
"Facebook RocksDB - Test: Random Fill (Op/s)",HIB,222391,186142
"Facebook RocksDB - Test: Read Random Write Random (Op/s)",HIB,3459011,2888939
"Facebook RocksDB - Test: Random Read (Op/s)",HIB,431189394,427390652
"ASKAP - Test: tConvolve OpenMP - Degridding (Million Grid Points/sec)",HIB,3995.35,3951.56
"ASKAP - Test: tConvolve OpenMP - Gridding (Million Grid Points/sec)",HIB,3718.65,3681.81
"Build2 - Time To Compile (sec)",LIB,50.452,50.730
"OSPray - Demo: San Miguel - Renderer: Path Tracer (FPS)",HIB,7.52,7.48
"Timed Godot Game Engine Compilation - Time To Compile (sec)",LIB,45.341,45.352
"GROMACS - Implementation: MPI CPU - Input: water_GMX50_bare (Ns/Day)",HIB,7.516,7.430
"Coremark - CoreMark Size 666 - Iterations Per Second (Iterations/Sec)",HIB,2736834.863102,2717033.096319
"Aircrack-ng - (k/s)",HIB,273924.125,273790.052
"Xmrig - Variant: Monero - Hash Count: 1M (H/s)",HIB,36203.1,36372.2
"libavif avifenc - Encoder Speed: 6 (sec)",LIB,9.614,9.775
"x265 - Video Input: Bosphorus 4K (FPS)",HIB,22.05,21.69
"ASKAP - Test: tConvolve MPI - Gridding (Mpix/sec)",HIB,46663.5,45986.4
"ASKAP - Test: tConvolve MPI - Degridding (Mpix/sec)",HIB,40632.4,40378.5
"Xmrig - Variant: Wownero - Hash Count: 1M (H/s)",HIB,39612.4,39553.5
"libavif avifenc - Encoder Speed: 6, Lossless (sec)",LIB,24.994,25.294
"libavif avifenc - Encoder Speed: 2 (sec)",LIB,24.235,24.611
"Stockfish - Total Time (Nodes/s)",HIB,184953949,183690000
"Tachyon - Total Time (sec)",LIB,21.2039,21.4500
"Timed Linux Kernel Compilation - Build: defconfig (sec)",LIB,20.685,20.909
"Liquid-DSP - Threads: 128 - Buffer Length: 256 - Filter Length: 57 (samples/s)",HIB,4044766667,4034700000
"Liquid-DSP - Threads: 32 - Buffer Length: 256 - Filter Length: 57 (samples/s)",HIB,1960966667,1937933333
"Liquid-DSP - Threads: 64 - Buffer Length: 256 - Filter Length: 57 (samples/s)",HIB,3584033333,3575533333
"Liquid-DSP - Threads: 16 - Buffer Length: 256 - Filter Length: 57 (samples/s)",HIB,1032200000,1000010000
"NAMD - ATPase Simulation - 327,506 Atoms (days/ns)",LIB,0.30407,0.30440
"NAS Parallel Benchmarks - Test / Class: SP.C (Mop/s)",HIB,85627.45,85540.27
"TNN - Target: CPU - Model: SqueezeNet v1.1 (ms)",LIB,251.895,252.050
"SVT-AV1 - Encoder Mode: Preset 12 - Input: Bosphorus 4K (FPS)",HIB,168.882,164.300
"Timed Mesa Compilation - Time To Compile (sec)",LIB,16.616,16.550
"NAS Parallel Benchmarks - Test / Class: BT.C (Mop/s)",HIB,188042.60,188668.84
"Kvazaar - Video Input: Bosphorus 4K - Video Preset: Ultra Fast (FPS)",HIB,49.95,48.91
"Parallel BZIP2 Compression - FreeBSD-13.0-RELEASE-amd64-memstick.img Compression (sec)",LIB,2.312,2.372
"POV-Ray - Trace Time (sec)",LIB,8.519,8.501
"OSPray - Demo: NASA Streamlines - Renderer: Path Tracer (FPS)",HIB,25.64,25
"Embree - Binary: Pathtracer ISPC - Model: Crown (FPS)",HIB,67.4315,67.3577
"SVT-AV1 - Encoder Mode: Preset 8 - Input: Bosphorus 4K (FPS)",HIB,97.969,97.915
"SVT-AV1 - Encoder Mode: Preset 10 - Input: Bosphorus 4K (FPS)",HIB,151.694,147.552
"SVT-HEVC - Tuning: 10 - Input: Bosphorus 1080p (FPS)",HIB,541.93,529.84
"NAS Parallel Benchmarks - Test / Class: LU.C (Mop/s)",HIB,258749.91,258716.32
"Pennant - Test: sedovbig (Hydro Cycle Time - sec)",LIB,7.552118,7.624752
"DaCapo Benchmark - Java Test: Jython (msec)",LIB,3805,3819
"LAMMPS Molecular Dynamics Simulator - Model: Rhodopsin Protein (ns/day)",HIB,26.966,26.192
"Pennant - Test: leblancbig (Hydro Cycle Time - sec)",LIB,4.269532,4.348101
"NAS Parallel Benchmarks - Test / Class: FT.C (Mop/s)",HIB,88217.14,86712.24
"TNN - Target: CPU - Model: SqueezeNet v2 (ms)",LIB,60.879,62.187
"Primesieve - 1e12 Prime Number Generation (sec)",LIB,3.364,3.358
"NAS Parallel Benchmarks - Test / Class: MG.C (Mop/s)",HIB,83495.69,82787.80
"NAS Parallel Benchmarks - Test / Class: EP.C (Mop/s)",HIB,6073.49,6106.26