patch testing by Michael Larabel.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2102055-HA-EPYC7F52L26 EPYC Ondemand vs. Performance vs. Schedutil Linux 5.11 - Phoronix Test Suite EPYC Ondemand vs. Performance vs. Schedutil Linux 5.11 patch testing by Michael Larabel.
HTML result view exported from: https://openbenchmarking.org/result/2102055-HA-EPYC7F52L26&grr .
EPYC Ondemand vs. Performance vs. Schedutil Linux 5.11 Processor Motherboard Chipset Memory Disk Graphics Monitor OS Kernel Desktop Display Server Display Driver Compiler File-System Screen Resolution Ondemand Schedutil Performance AMD EPYC 7F52 16-Core @ 3.91GHz (16 Cores / 32 Threads) Supermicro H11DSi-NT v2.00 (2.1 BIOS) AMD Starship/Matisse 8 x 8192 MB DDR4-3200MT/s HMA81GR7CJR8N-XN 280GB INTEL SSDPE21D280GA ASPEED VE228 Ubuntu 20.04 5.11.0-rc6-phx (x86_64) 20210203 GNOME Shell 3.36.1 X Server 1.20.7 aspeed GCC 9.3.0 ext4 1920x1080 1024x768 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - Ondemand: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8301034 - Schedutil: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301034 - Performance: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x8301034 Python Details - Python 2.7.18rc1 + Python 3.8.2 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
EPYC Ondemand vs. Performance vs. Schedutil Linux 5.11 blender: Barbershop - CPU-Only openvkl: vklBenchmark ospray: San Miguel - Path Tracer rodinia: OpenMP LavaMD dav1d: Chimera 1080p 10-bit rodinia: OpenMP HotSpot3D rodinia: OpenMP Leukocyte build-gdb: Time To Compile blender: BMW27 - CPU-Only build-godot: Time To Compile tensorflow-lite: Inception V4 compress-rar: Linux Source Tree Archiving To RAR tensorflow-lite: Inception ResNet V2 luxcorerender: DLSC luxcorerender: Rainbow Colors and Prism tensorflow-lite: SqueezeNet tensorflow-lite: NASNet Mobile tensorflow-lite: Mobilenet Quant tensorflow-lite: Mobilenet Float john-the-ripper: MD5 graphics-magick: Sharpen graphics-magick: Enhanced graphics-magick: Noise-Gaussian graphics-magick: Rotate graphics-magick: Resizing graphics-magick: Swirl graphics-magick: HWB Color Space hugin: Panorama Photo Assistant + Stitching Time clomp: Static OMP Speedup ospray: San Miguel - SciVis ospray: NASA Streamlines - Path Tracer john-the-ripper: Blowfish x265: Bosphorus 4K pennant: sedovbig kvazaar: Bosphorus 4K - Very Fast redis: SET ocrmypdf: Processing 60 Page PDF Document dav1d: Chimera 1080p svt-av1: Enc Mode 4 - 1080p pennant: leblancbig redis: GET dav1d: Summer Nature 4K oidn: Memorial rodinia: OpenMP Streamcluster rodinia: OpenMP CFD Solver kvazaar: Bosphorus 4K - Ultra Fast x265: Bosphorus 1080p svt-av1: Enc Mode 8 - 1080p ospray: NASA Streamlines - SciVis kvazaar: Bosphorus 1080p - Very Fast dav1d: Summer Nature 1080p kvazaar: Bosphorus 1080p - Ultra Fast x264: H.264 Video Encoding Ondemand Schedutil Performance 357.57 219 1.86 126.389 119.13 90.042 89.269 95.492 83.66 84.472 1504413 74.983 1351440 3.15 3.48 107260 126878 70655.1 69039.3 1719667 236 376 421 638 1582 922 1271 50.654 49.7 24.39 7.09 26298 21.65 25.61074 25.35 1308179.83 19.546 625.43 5.244 16.02967 1545026.54 254.29 14.19 13.769 13.243 46.86 65.47 41.023 33.33 87.16 592.34 155.97 172.64 357.49 217 1.87 125.977 92.21 91.310 90.431 89.606 83.57 83.313 1503093 76.921 1350653 3.19 3.57 107294 125981 70760.6 69012.9 1721000 236 376 421 639 1587 923 1121 50.464 50.3 24.39 7.11 26310 21.05 25.59670 26.27 1313860.03 19.483 536.65 5.379 15.99347 1599356.29 246.86 14.26 13.754 13.247 47.63 55.07 43.040 33.33 86.89 488.95 153.01 172.60 356.90 223 1.87 125.881 131.74 92.087 89.709 83.709 83.73 83.164 1503297 67.676 1350667 3.18 3.51 107390 126203 70739.1 68976.9 1721333 237 377 420 629 1609 928 1239 50.408 50.7 24.39 7.11 26323 21.50 25.54257 26.39 1318380.42 19.281 713.18 5.431 15.90980 1604323.00 264.98 14.23 13.705 13.331 47.80 68.48 42.823 33.33 92.22 668.50 161.97 176.54 OpenBenchmarking.org
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Barbershop - Compute: CPU-Only Ondemand Schedutil Performance 80 160 240 320 400 SE +/- 0.51, N = 3 SE +/- 0.45, N = 3 SE +/- 0.68, N = 3 357.57 357.49 356.90
OpenVKL Benchmark: vklBenchmark OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmark Ondemand Schedutil Performance 50 100 150 200 250 SE +/- 0.58, N = 3 SE +/- 0.88, N = 3 219 217 223 MIN: 1 / MAX: 776 MIN: 1 / MAX: 786 MIN: 1 / MAX: 785
OSPray Demo: San Miguel - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: Path Tracer Ondemand Schedutil Performance 0.4208 0.8416 1.2624 1.6832 2.104 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.86 1.87 1.87 MIN: 1.85 / MAX: 1.88 MIN: 1.85 / MAX: 1.88 MIN: 1.86 / MAX: 1.88
Rodinia Test: OpenMP LavaMD OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP LavaMD Ondemand Schedutil Performance 30 60 90 120 150 SE +/- 0.25, N = 3 SE +/- 0.27, N = 3 SE +/- 0.28, N = 3 126.39 125.98 125.88 1. (CXX) g++ options: -O2 -lOpenCL
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better dav1d 0.8.1 Video Input: Chimera 1080p 10-bit Ondemand Schedutil Performance 30 60 90 120 150 SE +/- 0.19, N = 3 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 119.13 92.21 131.74 MIN: 78.3 / MAX: 259.88 MIN: 59.88 / MAX: 204.44 MIN: 85.18 / MAX: 277.62 1. (CC) gcc options: -pthread
Rodinia Test: OpenMP HotSpot3D OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP HotSpot3D Ondemand Schedutil Performance 20 40 60 80 100 SE +/- 0.08, N = 3 SE +/- 0.24, N = 3 SE +/- 0.46, N = 3 90.04 91.31 92.09 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP Leukocyte OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Leukocyte Ondemand Schedutil Performance 20 40 60 80 100 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 0.29, N = 3 89.27 90.43 89.71 1. (CXX) g++ options: -O2 -lOpenCL
Timed GDB GNU Debugger Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GDB GNU Debugger Compilation 9.1 Time To Compile Ondemand Schedutil Performance 20 40 60 80 100 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 SE +/- 0.08, N = 3 95.49 89.61 83.71
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: BMW27 - Compute: CPU-Only Ondemand Schedutil Performance 20 40 60 80 100 SE +/- 0.38, N = 3 SE +/- 0.25, N = 3 SE +/- 0.50, N = 3 83.66 83.57 83.73
Timed Godot Game Engine Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 3.2.3 Time To Compile Ondemand Schedutil Performance 20 40 60 80 100 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 84.47 83.31 83.16
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 Ondemand Schedutil Performance 300K 600K 900K 1200K 1500K SE +/- 385.24, N = 3 SE +/- 262.95, N = 3 SE +/- 236.24, N = 3 1504413 1503093 1503297
RAR Compression Linux Source Tree Archiving To RAR OpenBenchmarking.org Seconds, Fewer Is Better RAR Compression 5.6.1 Linux Source Tree Archiving To RAR Ondemand Schedutil Performance 20 40 60 80 100 SE +/- 0.18, N = 3 SE +/- 0.41, N = 3 SE +/- 0.24, N = 3 74.98 76.92 67.68
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 Ondemand Schedutil Performance 300K 600K 900K 1200K 1500K SE +/- 365.29, N = 3 SE +/- 394.05, N = 3 SE +/- 483.75, N = 3 1351440 1350653 1350667
LuxCoreRender Scene: DLSC OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.3 Scene: DLSC Ondemand Schedutil Performance 0.7178 1.4356 2.1534 2.8712 3.589 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 3.15 3.19 3.18 MIN: 3.06 / MAX: 3.29 MIN: 3.04 / MAX: 3.41 MIN: 3.05 / MAX: 3.39
LuxCoreRender Scene: Rainbow Colors and Prism OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.3 Scene: Rainbow Colors and Prism Ondemand Schedutil Performance 0.8033 1.6066 2.4099 3.2132 4.0165 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 3.48 3.57 3.51 MIN: 3.44 / MAX: 3.5 MIN: 3.48 / MAX: 3.6 MIN: 3.48 / MAX: 3.55
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet Ondemand Schedutil Performance 20K 40K 60K 80K 100K SE +/- 84.90, N = 3 SE +/- 80.49, N = 3 SE +/- 43.47, N = 3 107260 107294 107390
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: NASNet Mobile Ondemand Schedutil Performance 30K 60K 90K 120K 150K SE +/- 136.25, N = 3 SE +/- 40.55, N = 3 SE +/- 287.23, N = 3 126878 125981 126203
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Quant Ondemand Schedutil Performance 15K 30K 45K 60K 75K SE +/- 45.84, N = 3 SE +/- 30.64, N = 3 SE +/- 30.62, N = 3 70655.1 70760.6 70739.1
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float Ondemand Schedutil Performance 15K 30K 45K 60K 75K SE +/- 42.21, N = 3 SE +/- 21.41, N = 3 SE +/- 36.63, N = 3 69039.3 69012.9 68976.9
John The Ripper Test: MD5 OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: MD5 Ondemand Schedutil Performance 400K 800K 1200K 1600K 2000K SE +/- 3179.80, N = 3 SE +/- 3000.00, N = 3 SE +/- 2962.73, N = 3 1719667 1721000 1721333 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Sharpen Ondemand Schedutil Performance 50 100 150 200 250 236 236 237 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Enhanced OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Enhanced Ondemand Schedutil Performance 80 160 240 320 400 SE +/- 0.33, N = 3 376 376 377 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Noise-Gaussian OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Noise-Gaussian Ondemand Schedutil Performance 90 180 270 360 450 SE +/- 0.67, N = 3 SE +/- 0.58, N = 3 SE +/- 0.67, N = 3 421 421 420 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Rotate OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Rotate Ondemand Schedutil Performance 140 280 420 560 700 SE +/- 4.70, N = 3 SE +/- 4.18, N = 3 SE +/- 4.18, N = 3 638 639 629 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Resizing Ondemand Schedutil Performance 300 600 900 1200 1500 SE +/- 5.49, N = 3 SE +/- 18.52, N = 3 SE +/- 1.20, N = 3 1582 1587 1609 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Swirl OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Swirl Ondemand Schedutil Performance 200 400 600 800 1000 SE +/- 0.88, N = 3 922 923 928 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: HWB Color Space Ondemand Schedutil Performance 300 600 900 1200 1500 SE +/- 2.52, N = 3 SE +/- 2.40, N = 3 SE +/- 3.67, N = 3 1271 1121 1239 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Hugin Panorama Photo Assistant + Stitching Time OpenBenchmarking.org Seconds, Fewer Is Better Hugin Panorama Photo Assistant + Stitching Time Ondemand Schedutil Performance 11 22 33 44 55 SE +/- 0.33, N = 3 SE +/- 0.17, N = 3 SE +/- 0.29, N = 3 50.65 50.46 50.41
CLOMP Static OMP Speedup OpenBenchmarking.org Speedup, More Is Better CLOMP 1.2 Static OMP Speedup Ondemand Schedutil Performance 11 22 33 44 55 SE +/- 0.25, N = 3 SE +/- 0.33, N = 3 SE +/- 0.43, N = 3 49.7 50.3 50.7 1. (CC) gcc options: -fopenmp -O3 -lm
OSPray Demo: San Miguel - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: SciVis Ondemand Schedutil Performance 6 12 18 24 30 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 24.39 24.39 24.39 MIN: 23.26 / MAX: 26.32 MIN: 23.26 / MAX: 26.32 MIN: 23.26 / MAX: 26.32
OSPray Demo: NASA Streamlines - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: NASA Streamlines - Renderer: Path Tracer Ondemand Schedutil Performance 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 7.09 7.11 7.11 MIN: 6.99 / MAX: 7.19 MIN: 6.99 / MAX: 7.19 MIN: 6.99 / MAX: 7.25
John The Ripper Test: Blowfish OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: Blowfish Ondemand Schedutil Performance 6K 12K 18K 24K 30K SE +/- 22.67, N = 3 SE +/- 22.45, N = 3 SE +/- 23.97, N = 3 26298 26310 26323 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
x265 Video Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 4K Ondemand Schedutil Performance 5 10 15 20 25 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 SE +/- 0.15, N = 3 21.65 21.05 21.50 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Pennant Test: sedovbig OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: sedovbig Ondemand Schedutil Performance 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 25.61 25.60 25.54 1. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi
Kvazaar Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Very Fast Ondemand Schedutil Performance 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 25.35 26.27 26.39 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Redis Test: SET OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: SET Ondemand Schedutil Performance 300K 600K 900K 1200K 1500K SE +/- 3347.62, N = 3 SE +/- 16949.35, N = 4 SE +/- 17244.90, N = 3 1308179.83 1313860.03 1318380.42 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OCRMyPDF Processing 60 Page PDF Document OpenBenchmarking.org Seconds, Fewer Is Better OCRMyPDF 9.6.0+dfsg Processing 60 Page PDF Document Ondemand Schedutil Performance 5 10 15 20 25 SE +/- 0.04, N = 3 SE +/- 0.11, N = 3 SE +/- 0.04, N = 3 19.55 19.48 19.28
dav1d Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.8.1 Video Input: Chimera 1080p Ondemand Schedutil Performance 150 300 450 600 750 SE +/- 1.15, N = 3 SE +/- 0.42, N = 3 SE +/- 1.61, N = 3 625.43 536.65 713.18 MIN: 491.48 / MAX: 770.18 MIN: 417.73 / MAX: 665.43 MIN: 554.58 / MAX: 886.76 1. (CC) gcc options: -pthread
SVT-AV1 Encoder Mode: Enc Mode 4 - Input: 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8 Encoder Mode: Enc Mode 4 - Input: 1080p Ondemand Schedutil Performance 1.222 2.444 3.666 4.888 6.11 SE +/- 0.049, N = 3 SE +/- 0.025, N = 3 SE +/- 0.023, N = 3 5.244 5.379 5.431 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
Pennant Test: leblancbig OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: leblancbig Ondemand Schedutil Performance 4 8 12 16 20 SE +/- 0.12, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 16.03 15.99 15.91 1. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi
Redis Test: GET OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: GET Ondemand Schedutil Performance 300K 600K 900K 1200K 1500K SE +/- 12901.14, N = 3 SE +/- 26190.66, N = 3 SE +/- 13020.90, N = 3 1545026.54 1599356.29 1604323.00 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 0.8.1 Video Input: Summer Nature 4K Ondemand Schedutil Performance 60 120 180 240 300 SE +/- 0.06, N = 3 SE +/- 0.18, N = 3 SE +/- 0.38, N = 3 254.29 246.86 264.98 MIN: 211.06 / MAX: 289.79 MIN: 205.59 / MAX: 285.26 MIN: 222.23 / MAX: 302.43 1. (CC) gcc options: -pthread
Intel Open Image Denoise Scene: Memorial OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.2.0 Scene: Memorial Ondemand Schedutil Performance 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 14.19 14.26 14.23
Rodinia Test: OpenMP Streamcluster OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Streamcluster Ondemand Schedutil Performance 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 13.77 13.75 13.71 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP CFD Solver OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP CFD Solver Ondemand Schedutil Performance 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 13.24 13.25 13.33 1. (CXX) g++ options: -O2 -lOpenCL
Kvazaar Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Ondemand Schedutil Performance 11 22 33 44 55 SE +/- 0.14, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 46.86 47.63 47.80 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
x265 Video Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 1080p Ondemand Schedutil Performance 15 30 45 60 75 SE +/- 0.15, N = 3 SE +/- 0.34, N = 3 SE +/- 0.12, N = 3 65.47 55.07 68.48 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
SVT-AV1 Encoder Mode: Enc Mode 8 - Input: 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8 Encoder Mode: Enc Mode 8 - Input: 1080p Ondemand Schedutil Performance 10 20 30 40 50 SE +/- 0.11, N = 3 SE +/- 0.22, N = 3 SE +/- 0.12, N = 3 41.02 43.04 42.82 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OSPray Demo: NASA Streamlines - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: NASA Streamlines - Renderer: SciVis Ondemand Schedutil Performance 8 16 24 32 40 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 33.33 33.33 33.33 MIN: 31.25 / MAX: 34.48 MIN: 31.25 MIN: 31.25 / MAX: 34.48
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Very Fast Ondemand Schedutil Performance 20 40 60 80 100 SE +/- 0.29, N = 3 SE +/- 0.21, N = 3 SE +/- 0.08, N = 3 87.16 86.89 92.22 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
dav1d Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.8.1 Video Input: Summer Nature 1080p Ondemand Schedutil Performance 140 280 420 560 700 SE +/- 2.45, N = 3 SE +/- 1.06, N = 3 SE +/- 0.74, N = 3 592.34 488.95 668.50 MIN: 443.85 / MAX: 644.65 MIN: 390.53 / MAX: 532.25 MIN: 502.68 / MAX: 730.8 1. (CC) gcc options: -pthread
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast Ondemand Schedutil Performance 40 80 120 160 200 SE +/- 0.36, N = 3 SE +/- 0.28, N = 3 SE +/- 0.32, N = 3 155.97 153.01 161.97 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
x264 H.264 Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x264 2019-12-17 H.264 Video Encoding Ondemand Schedutil Performance 40 80 120 160 200 SE +/- 1.12, N = 3 SE +/- 1.39, N = 3 SE +/- 1.40, N = 3 172.64 172.60 176.54 1. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
Phoronix Test Suite v10.8.4