Tests for a future article.
acpi-cpufreq schedutil Processor: AMD Ryzen 5 5500U @ 2.10GHz (6 Cores / 12 Threads), Motherboard: LENOVO LNVNB161216 (GLCN22WW BIOS), Chipset: AMD Renoir Root Complex, Memory: 6GB, Disk: 256GB SAMSUNG MZALQ256HBJD-00BL2, Graphics: AMD Lucienne 2GB (1800/400MHz), Audio: AMD Renoir Radeon HD Audio, Network: Qualcomm Atheros QCA6174 802.11ac
OS: Ubuntu 21.04, Kernel: 5.15.0-pstate4 (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server 1.20.11 + Wayland, OpenGL: 4.6 Mesa 22.0.0-devel (git-9d9de15 2021-11-15 hirsute-oibaf-ppa) (LLVM 13.0.0 DRM 3.42 5.15.0-pstate4), Vulkan: 1.2.197, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,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-build-config=bootstrap-lto-lean --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 -vProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8608102Graphics Notes: GLAMOR - BAR1 / Visible vRAM Size: 2048 MBPython Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + 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
amd-pstate schedutil Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,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-build-config=bootstrap-lto-lean --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 -vProcessor Notes: Scaling Governor: amd-pstate schedutil (Boost: Enabled) - CPU Microcode: 0x8608102Graphics Notes: GLAMOR - BAR1 / Visible vRAM Size: 2048 MBPython Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + 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
amd-pstate performance Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,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-build-config=bootstrap-lto-lean --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 -vProcessor Notes: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0x8608102Graphics Notes: GLAMOR - BAR1 / Visible vRAM Size: 2048 MBPython Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + 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
amd-pstate powersave Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,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-build-config=bootstrap-lto-lean --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 -vProcessor Notes: Scaling Governor: amd-pstate powersave (Boost: Enabled) - CPU Microcode: 0x8608102Graphics Notes: GLAMOR - BAR1 / Visible vRAM Size: 2048 MBPython Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + 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
and-pstate ondemand Changed Processor to AMD Ryzen 5 5500U @ 4.06GHz (6 Cores / 12 Threads) .
Processor Change: Scaling Governor: amd-pstate ondemand (Boost: Enabled) - CPU Microcode: 0x8608102
acpi-cpufreq powersave Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,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-build-config=bootstrap-lto-lean --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 -vProcessor Notes: Scaling Governor: acpi-cpufreq powersave (Boost: Enabled) - CPU Microcode: 0x8608102Graphics Notes: GLAMOR - BAR1 / Visible vRAM Size: 2048 MBPython Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + 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
acpi-cpufreq ondemand Changed Processor to AMD Ryzen 5 5500U @ 2.10GHz (6 Cores / 12 Threads) .
Processor Change: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8608102
TNN TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 60 120 180 240 300 SE +/- 0.10, N = 7 SE +/- 0.14, N = 7 SE +/- 0.12, N = 7 SE +/- 0.67, N = 3 SE +/- 0.08, N = 7 SE +/- 0.75, N = 4 SE +/- 0.16, N = 7 72.16 71.97 72.09 266.16 72.00 208.83 72.03 MIN: 71.36 / MAX: 73.24 MIN: 71.18 / MAX: 73.47 MIN: 71.26 / MAX: 75.92 MIN: 263.6 / MAX: 291.17 MIN: 71.09 / MAX: 73.05 MIN: 205.87 / MAX: 213.29 MIN: 71.19 / MAX: 73.48 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.6 4.4 6.6 amd-pstate schedutil 1.6 4.3 6.6 amd-pstate performance 1.5 4.3 6.6 acpi-cpufreq ondemand 1.5 4.3 6.5 OpenBenchmarking.org Watts, Fewer Is Better TNN 0.3 CPU Power Consumption Monitor 3 6 9 12 15 CPU Temp
Min Avg Max acpi-cpufreq schedutil 40.5 46.7 49.5 amd-pstate schedutil 41.4 47.6 51.5 amd-pstate performance 40.8 46.4 50.3 amd-pstate powersave 37.8 38.2 38.6 and-pstate ondemand 40.4 46.5 50.4 acpi-cpufreq powersave 38.6 39.4 40.1 acpi-cpufreq ondemand 40.8 47.3 50.8 OpenBenchmarking.org Celsius, Fewer Is Better TNN 0.3 CPU Temperature Monitor 15 30 45 60 75
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: DistinctUserID acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 0.9383 1.8766 2.8149 3.7532 4.6915 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 4.15 4.15 4.16 1.13 4.17 1.44 4.14 1. (CXX) g++ options: -O3 -pthread GB/s Per Watt
OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 1.0 Throughput Test: DistinctUserID acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 0.1413 0.2826 0.4239 0.5652 0.7065 0.624 0.628 0.619 0.627 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.5 6.6 7.9 amd-pstate schedutil 1.6 6.6 7.1 amd-pstate performance 1.4 6.7 8.2 acpi-cpufreq ondemand 1.6 6.6 7.2 OpenBenchmarking.org Watts, Fewer Is Better simdjson 1.0 CPU Power Consumption Monitor 3 6 9 12 15 CPU Temp
Min Avg Max acpi-cpufreq schedutil 36.1 50.8 55.6 amd-pstate schedutil 35.3 50.6 55.3 amd-pstate performance 35.9 51.0 55.5 amd-pstate powersave 35.9 36.7 37.3 and-pstate ondemand 37.0 50.9 55.3 acpi-cpufreq powersave 36.1 37.3 37.9 acpi-cpufreq ondemand 36.1 51.0 55.0 OpenBenchmarking.org Celsius, Fewer Is Better simdjson 1.0 CPU Temperature Monitor 15 30 45 60 75
Result
OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: PartialTweets acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 0.846 1.692 2.538 3.384 4.23 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 3.75 3.75 3.76 1.02 3.76 1.30 3.75 1. (CXX) g++ options: -O3 -pthread GB/s Per Watt
OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 1.0 Throughput Test: PartialTweets acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 0.1292 0.2584 0.3876 0.5168 0.646 0.571 0.571 0.562 0.574 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.7 6.6 7.1 amd-pstate schedutil 1.6 6.6 7.3 amd-pstate performance 1.6 6.7 8.0 acpi-cpufreq ondemand 1.6 6.5 7.0 OpenBenchmarking.org Watts, Fewer Is Better simdjson 1.0 CPU Power Consumption Monitor 3 6 9 12 15 CPU Temp
Min Avg Max acpi-cpufreq schedutil 37.8 52.2 57.0 amd-pstate schedutil 37.9 52.1 57.4 amd-pstate performance 39.1 52.1 56.4 amd-pstate powersave 36.8 37.5 38.3 and-pstate ondemand 39.0 51.7 56.6 acpi-cpufreq powersave 37.8 38.6 39.4 acpi-cpufreq ondemand 39.1 51.9 56.1 OpenBenchmarking.org Celsius, Fewer Is Better simdjson 1.0 CPU Temperature Monitor 16 32 48 64 80
LAME MP3 Encoding LAME is an MP3 encoder licensed under the LGPL. This test measures the time required to encode a WAV file to MP3 format. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 7 14 21 28 35 SE +/- 0.002, N = 6 SE +/- 0.005, N = 6 SE +/- 0.004, N = 6 SE +/- 0.002, N = 3 SE +/- 0.002, N = 6 SE +/- 0.254, N = 4 SE +/- 0.002, N = 6 7.814 7.823 7.809 28.678 7.820 23.063 7.944 1. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lncurses -lm CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.6 4.5 6.5 amd-pstate schedutil 0.9 4.4 6.8 amd-pstate performance 1.5 4.3 6.2 acpi-cpufreq ondemand 1.6 4.2 5.8 OpenBenchmarking.org Watts, Fewer Is Better LAME MP3 Encoding 3.100 CPU Power Consumption Monitor 3 6 9 12 15 CPU Temp
Min Avg Max acpi-cpufreq schedutil 35.9 49.8 54.5 amd-pstate schedutil 35.4 49.0 54.5 amd-pstate performance 36.0 47.8 53.4 amd-pstate powersave 36.6 37.3 37.5 and-pstate ondemand 36.0 47.0 52.0 acpi-cpufreq powersave 37.5 38.1 38.6 acpi-cpufreq ondemand 35.8 47.6 52.4 OpenBenchmarking.org Celsius, Fewer Is Better LAME MP3 Encoding 3.100 CPU Temperature Monitor 15 30 45 60 75
RNNoise RNNoise is a recurrent neural network for audio noise reduction developed by Mozilla and Xiph.Org. This test profile is a single-threaded test measuring the time to denoise a sample 26 minute long 16-bit RAW audio file using this recurrent neural network noise suppression library. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better RNNoise 2020-06-28 acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 16 32 48 64 80 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 19.32 19.35 19.36 70.95 19.41 55.76 19.36 1. (CC) gcc options: -O2 -pedantic -fvisibility=hidden CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.6 5.4 6.8 amd-pstate schedutil 1.7 5.5 7.9 amd-pstate performance 1.6 5.9 7.8 acpi-cpufreq ondemand 1.7 5.4 6.7 OpenBenchmarking.org Watts, Fewer Is Better RNNoise 2020-06-28 CPU Power Consumption Monitor 3 6 9 12 15 CPU Temp
Min Avg Max acpi-cpufreq schedutil 35.5 48.1 54.5 amd-pstate schedutil 34.6 47.0 53.4 amd-pstate performance 35.8 49.5 54.1 amd-pstate powersave 35.6 36.9 37.3 and-pstate ondemand 35.4 47.9 53.6 acpi-cpufreq powersave 35.5 37.2 37.6 acpi-cpufreq ondemand 37.3 49.2 55.6 OpenBenchmarking.org Celsius, Fewer Is Better RNNoise 2020-06-28 CPU Temperature Monitor 15 30 45 60 75
FLAC Audio Encoding This test times how long it takes to encode a sample WAV file to FLAC format ten times. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.3 WAV To FLAC acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 13 26 39 52 65 SE +/- 0.02, N = 5 SE +/- 0.02, N = 5 SE +/- 0.01, N = 5 SE +/- 0.02, N = 5 SE +/- 0.02, N = 5 SE +/- 0.03, N = 5 SE +/- 0.01, N = 5 15.64 15.67 15.61 55.73 15.64 43.97 15.65 1. (CXX) g++ options: -fvisibility=hidden -logg -lm CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.6 5.5 7.2 amd-pstate schedutil 1.6 5.6 7.9 amd-pstate performance 1.5 5.7 7.9 acpi-cpufreq ondemand 1.5 5.5 6.8 OpenBenchmarking.org Watts, Fewer Is Better FLAC Audio Encoding 1.3.3 CPU Power Consumption Monitor 3 6 9 12 15 CPU Temp
Min Avg Max acpi-cpufreq schedutil 38.0 50.1 54.9 amd-pstate schedutil 41.5 52.2 59.6 amd-pstate performance 39.1 51.9 56.6 amd-pstate powersave 38.4 39.4 41.0 and-pstate ondemand 38.6 51.0 55.1 acpi-cpufreq powersave 39.0 40.2 41.8 acpi-cpufreq ondemand 38.9 51.7 57.1 OpenBenchmarking.org Celsius, Fewer Is Better FLAC Audio Encoding 1.3.3 CPU Temperature Monitor 16 32 48 64 80
TNN TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 3K 6K 9K 12K 15K SE +/- 2.05, N = 3 SE +/- 4.37, N = 3 SE +/- 2.24, N = 3 SE +/- 12.34, N = 3 SE +/- 4.56, N = 3 SE +/- 12.43, N = 3 SE +/- 0.75, N = 3 3426.63 3528.58 3426.68 11839.89 3492.01 9345.10 3451.96 MIN: 3363.01 / MAX: 3497.13 MIN: 3466.42 / MAX: 3605.75 MIN: 3364.54 / MAX: 3501.99 MIN: 11621.01 / MAX: 12087.79 MIN: 3413.89 / MAX: 3600.41 MIN: 9169.3 / MAX: 10402.14 MIN: 3380.15 / MAX: 3532.28 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.6 14.4 16.0 amd-pstate schedutil 1.6 14.8 16.3 amd-pstate performance 1.5 14.6 16.6 acpi-cpufreq ondemand 1.6 14.3 15.8 OpenBenchmarking.org Watts, Fewer Is Better TNN 0.3 CPU Power Consumption Monitor 5 10 15 20 25 CPU Temp
Min Avg Max acpi-cpufreq schedutil 37.4 61.3 64.0 amd-pstate schedutil 38.4 61.0 62.1 amd-pstate performance 39.9 60.8 63.4 amd-pstate powersave 35.9 40.3 40.8 and-pstate ondemand 39.6 60.5 62.9 acpi-cpufreq powersave 36.1 42.1 43.1 acpi-cpufreq ondemand 39.9 61.0 64.0 OpenBenchmarking.org Celsius, Fewer Is Better TNN 0.3 CPU Temperature Monitor 20 40 60 80 100
Git This test measures the time needed to carry out some sample Git operations on an example, static repository that happens to be a copy of the GNOME GTK tool-kit repository. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Git Time To Complete Common Git Commands acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 40 80 120 160 200 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.50, N = 3 SE +/- 0.06, N = 3 SE +/- 0.19, N = 3 SE +/- 0.12, N = 3 52.79 52.87 52.87 177.01 53.10 140.45 52.96 1. git version 2.30.2 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.7 6.0 7.9 amd-pstate schedutil 1.6 6.0 7.7 amd-pstate performance 1.6 6.0 7.6 acpi-cpufreq ondemand 1.7 5.9 7.6 OpenBenchmarking.org Watts, Fewer Is Better Git CPU Power Consumption Monitor 3 6 9 12 15 CPU Temp
Min Avg Max acpi-cpufreq schedutil 44.4 50.5 54.8 amd-pstate schedutil 43.3 51.1 55.5 amd-pstate performance 43.9 50.2 52.0 amd-pstate powersave 36.9 39.0 39.5 and-pstate ondemand 43.9 50.8 55.5 acpi-cpufreq powersave 36.9 39.4 40.0 acpi-cpufreq ondemand 45.0 52.0 53.6 OpenBenchmarking.org Celsius, Fewer Is Better Git CPU Temperature Monitor 15 30 45 60 75
Selenium This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Score, More Is Better Selenium Benchmark: Jetstream 2 - Browser: Google Chrome acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 30 60 90 120 150 SE +/- 0.16, N = 3 SE +/- 0.25, N = 3 SE +/- 0.22, N = 3 SE +/- 0.14, N = 3 SE +/- 0.87, N = 3 SE +/- 0.14, N = 3 SE +/- 0.60, N = 3 138.00 122.73 157.44 47.57 142.24 59.91 149.58 1. chrome 96.0.4664.45 Score Per Watt
OpenBenchmarking.org Score Per Watt, More Is Better Selenium Benchmark: Jetstream 2 - Browser: Google Chrome acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 5 10 15 20 25 19.12 17.69 19.82 20.42 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.5 7.2 24.3 amd-pstate schedutil 1.5 6.9 24.3 amd-pstate performance 1.6 7.9 24.2 acpi-cpufreq ondemand 1.7 7.3 24.1 OpenBenchmarking.org Watts, Fewer Is Better Selenium CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max acpi-cpufreq schedutil 38.6 51.2 62.3 amd-pstate schedutil 38.6 50.6 63.8 amd-pstate performance 38.5 50.9 64.4 amd-pstate powersave 37.0 38.3 41.1 and-pstate ondemand 38.5 50.8 64.0 acpi-cpufreq powersave 38.0 39.5 42.3 acpi-cpufreq ondemand 39.5 50.6 65.9 OpenBenchmarking.org Celsius, Fewer Is Better Selenium CPU Temperature Monitor 20 40 60 80 100
DDraceNetwork This is a test of DDraceNetwork, an open-source cooperative platformer. OpenGL 3.3 is used for rendering, with fallbacks for older OpenGL versions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better DDraceNetwork 15.3.1 Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: Multeasymap acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 90 180 270 360 450 SE +/- 2.80, N = 3 SE +/- 1.92, N = 3 SE +/- 3.30, N = 8 SE +/- 0.50, N = 3 SE +/- 0.29, N = 3 SE +/- 1.37, N = 3 SE +/- 2.79, N = 3 368.05 258.24 398.00 120.76 295.32 150.03 357.76 1. (CXX) g++ options: -O3 -lrt -pthread -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0
Hugin Hugin is an open-source, cross-platform panorama photo stitcher software package. This test profile times how long it takes to run the assistant and panorama photo stitching on a set of images. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Hugin Panorama Photo Assistant + Stitching Time acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 40 80 120 160 200 SE +/- 0.34, N = 3 SE +/- 0.17, N = 3 SE +/- 0.68, N = 3 SE +/- 0.52, N = 3 SE +/- 0.72, N = 3 SE +/- 0.15, N = 3 SE +/- 0.13, N = 3 58.87 59.14 59.35 191.68 59.56 151.75 58.89 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.6 13.5 25.2 amd-pstate schedutil 1.6 13.9 25.1 amd-pstate performance 0.8 13.9 25.2 acpi-cpufreq ondemand 1.6 13.8 25.1 OpenBenchmarking.org Watts, Fewer Is Better Hugin CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max acpi-cpufreq schedutil 44.0 60.4 64.4 amd-pstate schedutil 43.8 59.5 64.0 amd-pstate performance 44.9 60.9 64.1 amd-pstate powersave 38.3 42.1 44.1 and-pstate ondemand 43.5 60.4 64.5 acpi-cpufreq powersave 38.3 42.2 45.1 acpi-cpufreq ondemand 44.4 61.0 68.8 OpenBenchmarking.org Celsius, Fewer Is Better Hugin CPU Temperature Monitor 20 40 60 80 100
Selenium This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Runs / Minute, More Is Better Selenium Benchmark: StyleBench - Browser: Google Chrome acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 8 16 24 32 40 SE +/- 0.15, N = 3 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.12, N = 3 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 36.1 35.8 35.9 11.8 33.9 14.8 36.3 1. chrome 96.0.4664.45 Runs / Minute Per Watt
OpenBenchmarking.org Runs / Minute Per Watt, More Is Better Selenium Benchmark: StyleBench - Browser: Google Chrome acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 1.2614 2.5228 3.7842 5.0456 6.307 5.606 5.458 5.301 5.458 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.5 6.4 9.2 amd-pstate schedutil 1.6 6.6 9.6 amd-pstate performance 1.5 6.8 9.8 acpi-cpufreq ondemand 1.6 6.7 8.8 OpenBenchmarking.org Watts, Fewer Is Better Selenium CPU Power Consumption Monitor 4.42 8.84 13.26 17.68 22.1 CPU Temp
Min Avg Max acpi-cpufreq schedutil 36.8 49.5 56.1 amd-pstate schedutil 35.3 49.5 56.0 amd-pstate performance 34.9 49.1 56.6 amd-pstate powersave 37.1 38.9 39.4 and-pstate ondemand 37.8 49.4 56.3 acpi-cpufreq powersave 37.9 40.1 40.8 acpi-cpufreq ondemand 34.9 49.0 55.8 OpenBenchmarking.org Celsius, Fewer Is Better Selenium CPU Temperature Monitor 16 32 48 64 80
Node.js V8 Web Tooling Benchmark Running the V8 project's Web-Tooling-Benchmark under Node.js. The Web-Tooling-Benchmark stresses JavaScript-related workloads common to web developers like Babel and TypeScript and Babylon. This test profile can test the system's JavaScript performance with Node.js. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org runs/s, More Is Better Node.js V8 Web Tooling Benchmark acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 9.51 9.40 9.80 3.19 9.33 4.00 9.53 runs/s Per Watt
OpenBenchmarking.org runs/s Per Watt, More Is Better Node.js V8 Web Tooling Benchmark acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 0.2714 0.5428 0.8142 1.0856 1.357 1.206 1.205 1.193 1.201 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.7 7.9 10.9 amd-pstate schedutil 1.6 7.8 10.7 amd-pstate performance 1.4 8.2 11.3 acpi-cpufreq ondemand 1.6 7.9 10.8 OpenBenchmarking.org Watts, Fewer Is Better Node.js V8 Web Tooling Benchmark CPU Power Consumption Monitor 4 8 12 16 20 CPU Temp
Min Avg Max acpi-cpufreq schedutil 41.0 50.8 54.1 amd-pstate schedutil 36.5 50.2 55.5 amd-pstate performance 38.5 51.1 54.9 amd-pstate powersave 37.3 39.2 39.6 and-pstate ondemand 40.0 50.6 53.5 acpi-cpufreq powersave 37.8 39.9 40.6 acpi-cpufreq ondemand 39.4 50.9 55.5 OpenBenchmarking.org Celsius, Fewer Is Better Node.js V8 Web Tooling Benchmark CPU Temperature Monitor 15 30 45 60 75
OCRMyPDF OCRMyPDF is an optical character recognition (OCR) text layer to scanned PDF files, producing new PDFs with the text now selectable/searchable/copy-paste capable. OCRMyPDF leverages the Tesseract OCR engine and is written in Python. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better OCRMyPDF 10.3.1+dfsg Processing 60 Page PDF Document acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 20 40 60 80 100 SE +/- 0.13, N = 3 SE +/- 0.18, N = 3 SE +/- 0.16, N = 3 SE +/- 0.28, N = 3 SE +/- 0.04, N = 3 SE +/- 0.16, N = 3 SE +/- 0.14, N = 3 28.32 28.55 28.49 86.82 28.85 68.30 28.59 CPU Power Consumption
Min Avg Max amd-pstate schedutil 1.6 15.8 25.2 amd-pstate performance 1.6 16.0 25.1 acpi-cpufreq ondemand 0.9 15.9 25.1 OpenBenchmarking.org Watts, Fewer Is Better OCRMyPDF 10.3.1+dfsg CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max amd-pstate schedutil 38.6 59.4 67.3 amd-pstate performance 40.3 60.5 66.6 amd-pstate powersave 36.9 42.6 46.5 and-pstate ondemand 40.0 60.1 66.4 acpi-cpufreq powersave 37.6 43.5 47.3 acpi-cpufreq ondemand 39.9 60.2 68.1 OpenBenchmarking.org Celsius, Fewer Is Better OCRMyPDF 10.3.1+dfsg CPU Temperature Monitor 20 40 60 80 100
Selenium This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Runs Per Minute, More Is Better Selenium Benchmark: Speedometer - Browser: Google Chrome acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 30 60 90 120 150 SE +/- 0.33, N = 3 SE +/- 0.81, N = 3 SE +/- 0.16, N = 3 SE +/- 1.29, N = 3 SE +/- 0.16, N = 3 SE +/- 0.88, N = 3 150.00 143.00 156.40 51.41 145.40 64.35 153.00 1. chrome 96.0.4664.45 Runs Per Minute Per Watt
OpenBenchmarking.org Runs Per Minute Per Watt, More Is Better Selenium Benchmark: Speedometer - Browser: Google Chrome acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 5 10 15 20 25 22.51 21.98 22.28 22.18 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.6 6.7 10.1 amd-pstate schedutil 1.5 6.5 10.3 amd-pstate performance 1.5 7.0 10.4 acpi-cpufreq ondemand 1.7 6.9 10.6 OpenBenchmarking.org Watts, Fewer Is Better Selenium CPU Power Consumption Monitor 4 8 12 16 20 CPU Temp
Min Avg Max acpi-cpufreq schedutil 34.4 47.7 54.4 amd-pstate schedutil 36.3 47.7 54.1 amd-pstate performance 35.8 47.9 54.5 amd-pstate powersave 34.5 37.6 39.4 and-pstate ondemand 34.1 47.5 54.0 acpi-cpufreq powersave 34.6 38.6 40.5 acpi-cpufreq ondemand 31.6 46.8 55.3 OpenBenchmarking.org Celsius, Fewer Is Better Selenium CPU Temperature Monitor 15 30 45 60 75
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.2 Preset: Thorough acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 10 20 30 40 50 SE +/- 0.13, N = 3 SE +/- 0.12, N = 3 SE +/- 0.13, N = 3 SE +/- 0.04, N = 3 SE +/- 0.16, N = 3 SE +/- 0.02, N = 3 SE +/- 0.14, N = 3 14.85 14.97 14.92 44.24 14.76 34.78 14.84 1. (CXX) g++ options: -O3 -flto -pthread CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.7 16.4 25.1 amd-pstate schedutil 1.7 16.5 25.1 amd-pstate performance 1.6 16.8 25.1 acpi-cpufreq ondemand 1.6 16.5 25.1 OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 3.2 CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max acpi-cpufreq schedutil 37.6 61.9 68.1 amd-pstate schedutil 40.1 62.2 68.5 amd-pstate performance 37.8 62.3 68.5 amd-pstate powersave 38.5 42.9 45.9 and-pstate ondemand 40.4 61.6 67.5 acpi-cpufreq powersave 36.3 43.0 47.1 acpi-cpufreq ondemand 39.8 62.0 68.1 OpenBenchmarking.org Celsius, Fewer Is Better ASTC Encoder 3.2 CPU Temperature Monitor 20 40 60 80 100
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: blazeface acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 1.2825 2.565 3.8475 5.13 6.4125 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.14, N = 3 SE +/- 0.04, N = 3 1.96 1.97 1.98 5.70 1.97 4.75 1.96 MIN: 1.86 / MAX: 2.3 MIN: 1.88 / MAX: 2.41 MIN: 1.87 / MAX: 2.71 MIN: 5.56 / MAX: 6.12 MIN: 1.87 / MAX: 2.51 MIN: 4.52 / MAX: 5.36 MIN: 1.83 / MAX: 2.17 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Result
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: regnety_400m acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 7 14 21 28 35 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 SE +/- 0.11, N = 3 SE +/- 0.33, N = 3 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 SE +/- 0.12, N = 3 11.49 11.54 11.52 31.55 11.52 25.52 11.52 MIN: 11.19 / MAX: 12.01 MIN: 11.23 / MAX: 15.01 MIN: 11.19 / MAX: 15.36 MIN: 30.82 / MAX: 275.88 MIN: 11.22 / MAX: 12.96 MIN: 25.16 / MAX: 33.02 MIN: 11.16 / MAX: 12.84 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.6 17.9 25.7 amd-pstate schedutil 1.7 17.9 26.7 amd-pstate performance 1.6 17.9 25.9 acpi-cpufreq ondemand 1.4 18.0 25.6 OpenBenchmarking.org Watts, Fewer Is Better NCNN 20210720 CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max acpi-cpufreq schedutil 36.0 58.6 65.1 amd-pstate schedutil 37.9 57.9 65.8 amd-pstate performance 34.5 58.0 65.9 amd-pstate powersave 36.4 42.6 46.0 and-pstate ondemand 35.9 58.4 63.1 acpi-cpufreq powersave 36.9 43.1 46.1 acpi-cpufreq ondemand 36.3 58.5 65.0 OpenBenchmarking.org Celsius, Fewer Is Better NCNN 20210720 CPU Temperature Monitor 20 40 60 80 100
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 8 - Input: Bosphorus 1080p acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 8 16 24 32 40 SE +/- 0.13, N = 3 SE +/- 0.09, N = 3 SE +/- 0.35, N = 3 SE +/- 0.01, N = 3 SE +/- 0.13, N = 3 SE +/- 0.02, N = 3 SE +/- 0.21, N = 3 32.02 28.70 32.89 12.00 29.53 15.06 31.99 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 8 - Input: Bosphorus 1080p acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 0.4174 0.8348 1.2522 1.6696 2.087 1.833 1.742 1.855 1.812 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.6 17.5 23.1 amd-pstate schedutil 1.7 16.5 23.6 amd-pstate performance 1.7 17.7 23.4 acpi-cpufreq ondemand 1.7 17.7 23.6 OpenBenchmarking.org Watts, Fewer Is Better SVT-AV1 0.8.7 CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max acpi-cpufreq schedutil 41.0 60.4 65.4 amd-pstate schedutil 40.3 58.9 64.4 amd-pstate performance 41.4 60.5 65.8 amd-pstate powersave 37.4 42.6 45.4 and-pstate ondemand 41.5 60.1 65.4 acpi-cpufreq powersave 39.9 43.6 46.8 acpi-cpufreq ondemand 41.6 60.9 66.0 OpenBenchmarking.org Celsius, Fewer Is Better SVT-AV1 0.8.7 CPU Temperature Monitor 20 40 60 80 100
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.2 Preset: Exhaustive acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 90 180 270 360 450 SE +/- 0.32, N = 3 SE +/- 0.27, N = 3 SE +/- 0.42, N = 3 SE +/- 0.06, N = 3 SE +/- 0.43, N = 3 SE +/- 0.07, N = 3 SE +/- 0.40, N = 3 147.61 147.84 147.49 402.34 147.15 316.49 147.53 1. (CXX) g++ options: -O3 -flto -pthread CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.6 17.8 25.1 amd-pstate schedutil 1.7 17.8 25.1 amd-pstate performance 1.6 17.7 25.1 acpi-cpufreq ondemand 1.7 17.7 25.1 OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 3.2 CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max acpi-cpufreq schedutil 41.3 59.8 66.0 amd-pstate schedutil 41.0 59.5 66.5 amd-pstate performance 41.0 59.7 66.1 amd-pstate powersave 36.4 43.2 46.0 and-pstate ondemand 42.0 60.2 66.5 acpi-cpufreq powersave 39.1 44.1 47.1 acpi-cpufreq ondemand 41.5 60.2 66.8 OpenBenchmarking.org Celsius, Fewer Is Better ASTC Encoder 3.2 CPU Temperature Monitor 20 40 60 80 100
Zstd Compression This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19 - Decompression Speed acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 500 1000 1500 2000 2500 SE +/- 1.18, N = 3 SE +/- 3.99, N = 3 SE +/- 2.11, N = 3 SE +/- 1.44, N = 3 SE +/- 6.04, N = 3 SE +/- 0.50, N = 3 SE +/- 3.69, N = 3 2440.8 2431.5 2437.8 904.0 2428.6 1107.6 2438.5 1. *** zstd command line interface 64-bits v1.4.8, by Yann Collet *** MB/s Per Watt
OpenBenchmarking.org MB/s Per Watt, More Is Better Zstd Compression Compression Level: 19 - Decompression Speed acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 40 80 120 160 200 168.78 168.84 165.60 169.45 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.7 14.5 25.0 amd-pstate schedutil 1.7 14.4 25.0 amd-pstate performance 1.5 14.7 24.9 acpi-cpufreq ondemand 1.0 14.4 24.8 OpenBenchmarking.org Watts, Fewer Is Better Zstd Compression CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max acpi-cpufreq schedutil 42.1 57.8 69.0 amd-pstate schedutil 40.9 56.7 67.4 amd-pstate performance 41.4 58.0 70.4 amd-pstate powersave 36.4 41.4 44.3 and-pstate ondemand 43.5 57.6 68.5 acpi-cpufreq powersave 36.9 41.6 45.1 acpi-cpufreq ondemand 44.0 58.2 70.5 OpenBenchmarking.org Celsius, Fewer Is Better Zstd Compression CPU Temperature Monitor 20 40 60 80 100
Selenium This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.
Benchmark: Kraken - Browser: Google Chrome
amd-pstate powersave: NameError: name 'StaleElementReferenceException' is not defined
RawTherapee RawTherapee is a cross-platform, open-source multi-threaded RAW image processing program. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better RawTherapee Total Benchmark Time acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 50 100 150 200 250 SE +/- 0.19, N = 3 SE +/- 0.19, N = 3 SE +/- 0.27, N = 3 SE +/- 0.11, N = 3 SE +/- 0.37, N = 3 SE +/- 0.19, N = 3 SE +/- 0.15, N = 3 85.44 85.36 85.05 218.68 86.60 176.43 85.13 1. RawTherapee, version 5.8, command line. CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.5 16.7 25.0 amd-pstate schedutil 1.5 16.7 23.7 amd-pstate performance 1.5 16.9 23.7 acpi-cpufreq ondemand 1.5 16.8 24.2 OpenBenchmarking.org Watts, Fewer Is Better RawTherapee CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max acpi-cpufreq schedutil 40.0 62.5 67.1 amd-pstate schedutil 39.1 61.3 66.3 amd-pstate performance 41.0 62.5 66.6 amd-pstate powersave 38.1 42.2 44.9 and-pstate ondemand 40.0 61.9 66.8 acpi-cpufreq powersave 38.5 42.5 45.8 acpi-cpufreq ondemand 41.4 62.5 67.1 OpenBenchmarking.org Celsius, Fewer Is Better RawTherapee CPU Temperature Monitor 20 40 60 80 100
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: BMW27 - Compute: CPU-Only acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 160 320 480 640 800 SE +/- 1.34, N = 3 SE +/- 0.89, N = 3 SE +/- 0.64, N = 3 SE +/- 1.28, N = 3 SE +/- 0.32, N = 3 SE +/- 0.15, N = 3 SE +/- 0.13, N = 3 300.58 299.59 298.47 763.62 298.78 602.00 299.75 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.7 18.0 25.1 amd-pstate schedutil 1.7 18.0 25.1 amd-pstate performance 1.7 18.0 25.1 acpi-cpufreq ondemand 1.7 18.0 25.1 OpenBenchmarking.org Watts, Fewer Is Better Blender 2.92 CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max acpi-cpufreq schedutil 41.1 58.8 65.0 amd-pstate schedutil 41.4 58.0 64.6 amd-pstate performance 41.4 58.9 65.4 amd-pstate powersave 36.9 43.4 46.4 and-pstate ondemand 40.8 58.7 64.9 acpi-cpufreq powersave 36.5 44.0 47.4 acpi-cpufreq ondemand 41.3 59.3 65.5 OpenBenchmarking.org Celsius, Fewer Is Better Blender 2.92 CPU Temperature Monitor 20 40 60 80 100
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 8 - Input: Bosphorus 4K acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 3 6 9 12 15 SE +/- 0.046, N = 3 SE +/- 0.055, N = 3 SE +/- 0.055, N = 3 SE +/- 0.008, N = 3 SE +/- 0.045, N = 3 SE +/- 0.014, N = 3 SE +/- 0.054, N = 3 9.277 9.094 9.303 3.657 9.012 4.609 9.166 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 8 - Input: Bosphorus 4K acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 0.1172 0.2344 0.3516 0.4688 0.586 0.520 0.513 0.521 0.516 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.6 17.8 24.6 amd-pstate schedutil 1.5 17.7 25.0 amd-pstate performance 1.6 17.9 24.7 acpi-cpufreq ondemand 1.6 17.8 24.9 OpenBenchmarking.org Watts, Fewer Is Better SVT-AV1 0.8.7 CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max acpi-cpufreq schedutil 42.5 60.1 65.0 amd-pstate schedutil 42.0 59.6 63.8 amd-pstate performance 42.3 59.9 64.8 amd-pstate powersave 39.6 43.6 46.8 and-pstate ondemand 42.6 60.4 65.1 acpi-cpufreq powersave 39.4 43.8 47.5 acpi-cpufreq ondemand 43.0 60.9 66.4 OpenBenchmarking.org Celsius, Fewer Is Better SVT-AV1 0.8.7 CPU Temperature Monitor 20 40 60 80 100
SVT-HEVC This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 15 30 45 60 75 SE +/- 0.20, N = 5 SE +/- 0.27, N = 5 SE +/- 0.30, N = 5 SE +/- 0.16, N = 3 SE +/- 0.20, N = 5 SE +/- 0.05, N = 3 SE +/- 0.27, N = 5 64.89 64.98 64.17 26.11 64.77 32.91 65.10 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 0.8692 1.7384 2.6076 3.4768 4.346 3.842 3.863 3.816 3.827 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.7 16.9 25.3 amd-pstate schedutil 1.7 16.8 25.1 amd-pstate performance 1.6 16.8 25.1 acpi-cpufreq ondemand 1.6 17.0 25.3 OpenBenchmarking.org Watts, Fewer Is Better SVT-HEVC 1.5.0 CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max acpi-cpufreq schedutil 42.4 58.9 63.9 amd-pstate schedutil 42.6 58.6 63.5 amd-pstate performance 42.3 58.5 63.1 amd-pstate powersave 37.8 43.0 46.5 and-pstate ondemand 42.3 58.7 63.8 acpi-cpufreq powersave 38.6 44.5 47.4 acpi-cpufreq ondemand 42.6 59.4 64.3 OpenBenchmarking.org Celsius, Fewer Is Better SVT-HEVC 1.5.0 CPU Temperature Monitor 20 40 60 80 100
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: shufflenet-v2 acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 5.09 5.10 5.10 12.60 5.10 10.48 5.13 MIN: 4.98 / MAX: 6.19 MIN: 4.97 / MAX: 8.89 MIN: 4.98 / MAX: 9.16 MIN: 12.39 / MAX: 37.11 MIN: 4.99 / MAX: 5.79 MIN: 10.22 / MAX: 16.99 MIN: 4.99 / MAX: 13.21 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
SVT-VP9 This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 20 40 60 80 100 SE +/- 0.70, N = 6 SE +/- 0.66, N = 6 SE +/- 0.76, N = 6 SE +/- 0.47, N = 3 SE +/- 0.68, N = 6 SE +/- 0.48, N = 4 SE +/- 0.68, N = 6 82.47 81.86 82.59 33.89 79.42 42.12 82.19 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 1.15 2.3 3.45 4.6 5.75 5.053 5.027 5.111 5.060 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.6 16.3 25.1 amd-pstate schedutil 1.7 16.2 25.1 amd-pstate performance 1.7 16.2 25.1 acpi-cpufreq ondemand 1.6 16.2 25.1 OpenBenchmarking.org Watts, Fewer Is Better SVT-VP9 0.3 CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max acpi-cpufreq schedutil 41.5 57.8 63.5 amd-pstate schedutil 41.8 57.7 62.9 amd-pstate performance 41.8 58.2 63.6 amd-pstate powersave 37.8 42.3 45.9 and-pstate ondemand 42.4 58.5 63.9 acpi-cpufreq powersave 40.0 43.1 46.6 acpi-cpufreq ondemand 43.0 58.6 63.9 OpenBenchmarking.org Celsius, Fewer Is Better SVT-VP9 0.3 CPU Temperature Monitor 20 40 60 80 100
Unvanquished Unvanquished is a modern fork of the Tremulous first person shooter. Unvanquished is powered by the Daemon engine, a combination of the ioquake3 engine with the graphically-beautiful XreaL engine. Unvanquished supports a modern OpenGL 3 renderer and other advanced graphics features for this open-source game. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 1920 x 1080 - Effects Quality: Medium acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 40 80 120 160 200 SE +/- 1.20, N = 3 SE +/- 1.42, N = 3 SE +/- 0.32, N = 3 SE +/- 0.21, N = 3 SE +/- 0.26, N = 3 SE +/- 0.10, N = 3 SE +/- 0.21, N = 3 192.4 130.2 198.3 85.5 125.4 103.6 179.9 Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Unvanquished 0.52.1 Resolution: 1920 x 1080 - Effects Quality: Medium acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 4 8 12 16 20 14.66 13.79 14.49 13.82 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.4 13.1 20.2 amd-pstate schedutil 1.5 9.4 16.8 amd-pstate performance 1.5 13.7 20.7 acpi-cpufreq ondemand 1.1 13.0 19.4 OpenBenchmarking.org Watts, Fewer Is Better Unvanquished 0.52.1 CPU Power Consumption Monitor 6 12 18 24 30 CPU Temp
Min Avg Max acpi-cpufreq schedutil 43.8 52.6 55.8 amd-pstate schedutil 43.0 46.6 52.5 amd-pstate performance 42.6 51.7 55.0 amd-pstate powersave 35.9 39.9 43.0 and-pstate ondemand 42.1 45.1 52.5 acpi-cpufreq powersave 36.0 40.4 43.5 acpi-cpufreq ondemand 43.9 52.0 55.8 OpenBenchmarking.org Celsius, Fewer Is Better Unvanquished 0.52.1 CPU Temperature Monitor 16 32 48 64 80
Timed Linux Kernel Compilation This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.14 Time To Compile acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 80 160 240 320 400 SE +/- 0.46, N = 3 SE +/- 0.41, N = 3 SE +/- 0.43, N = 3 SE +/- 1.53, N = 3 SE +/- 0.85, N = 3 SE +/- 1.33, N = 3 SE +/- 0.58, N = 3 158.39 158.57 157.97 365.76 159.44 294.81 158.93 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.7 17.3 25.0 amd-pstate schedutil 0.9 17.3 25.1 amd-pstate performance 1.6 17.4 25.0 acpi-cpufreq ondemand 0.8 17.3 25.0 OpenBenchmarking.org Watts, Fewer Is Better Timed Linux Kernel Compilation 5.14 CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max acpi-cpufreq schedutil 44.0 57.7 63.5 amd-pstate schedutil 43.5 56.9 62.5 amd-pstate performance 43.9 57.8 63.5 amd-pstate powersave 37.1 42.8 46.5 and-pstate ondemand 44.1 57.3 63.3 acpi-cpufreq powersave 36.9 43.3 47.1 acpi-cpufreq ondemand 44.6 58.2 64.0 OpenBenchmarking.org Celsius, Fewer Is Better Timed Linux Kernel Compilation 5.14 CPU Temperature Monitor 20 40 60 80 100
SVT-HEVC This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 30 60 90 120 150 SE +/- 0.09, N = 7 SE +/- 0.08, N = 7 SE +/- 0.77, N = 7 SE +/- 0.03, N = 5 SE +/- 0.17, N = 7 SE +/- 0.03, N = 5 SE +/- 0.12, N = 7 132.71 132.33 129.42 57.76 131.99 71.51 132.02 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 3 6 9 12 15 9.814 9.844 9.558 9.803 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 0.8 13.5 25.1 amd-pstate schedutil 1.7 13.4 25.3 amd-pstate performance 1.6 13.5 25.1 acpi-cpufreq ondemand 1.6 13.5 25.2 OpenBenchmarking.org Watts, Fewer Is Better SVT-HEVC 1.5.0 CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max acpi-cpufreq schedutil 43.4 55.9 60.3 amd-pstate schedutil 42.8 55.6 60.8 amd-pstate performance 43.3 55.9 60.6 amd-pstate powersave 37.0 42.6 45.5 and-pstate ondemand 43.4 55.9 61.0 acpi-cpufreq powersave 37.1 42.6 46.5 acpi-cpufreq ondemand 43.4 56.1 61.6 OpenBenchmarking.org Celsius, Fewer Is Better SVT-HEVC 1.5.0 CPU Temperature Monitor 20 40 60 80 100
Unvanquished Unvanquished is a modern fork of the Tremulous first person shooter. Unvanquished is powered by the Daemon engine, a combination of the ioquake3 engine with the graphically-beautiful XreaL engine. Unvanquished supports a modern OpenGL 3 renderer and other advanced graphics features for this open-source game. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 1920 x 1080 - Effects Quality: High acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 40 80 120 160 200 SE +/- 0.31, N = 3 SE +/- 1.85, N = 12 SE +/- 0.12, N = 3 SE +/- 0.12, N = 3 SE +/- 0.24, N = 3 SE +/- 0.20, N = 3 SE +/- 0.23, N = 3 184.2 120.0 190.6 83.8 122.6 102.0 171.3 Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Unvanquished 0.52.1 Resolution: 1920 x 1080 - Effects Quality: High acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 3 6 9 12 15 12.92 12.39 12.96 12.58 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.6 14.3 21.5 amd-pstate schedutil 1.6 9.7 17.6 amd-pstate performance 1.5 14.7 21.6 acpi-cpufreq ondemand 1.6 13.6 19.9 OpenBenchmarking.org Watts, Fewer Is Better Unvanquished 0.52.1 CPU Power Consumption Monitor 6 12 18 24 30 CPU Temp
Min Avg Max acpi-cpufreq schedutil 43.1 52.5 56.1 amd-pstate schedutil 39.3 46.5 52.9 amd-pstate performance 42.3 52.5 56.4 amd-pstate powersave 35.6 40.0 43.6 and-pstate ondemand 39.3 45.8 52.6 acpi-cpufreq powersave 36.4 40.8 44.0 acpi-cpufreq ondemand 43.0 52.1 56.1 OpenBenchmarking.org Celsius, Fewer Is Better Unvanquished 0.52.1 CPU Temperature Monitor 16 32 48 64 80
Timed Wasmer Compilation This test times how long it takes to compile Wasmer. Wasmer is written in the Rust programming language and is a WebAssembly runtime implementation that supports WASI and EmScripten. This test profile builds Wasmer with the Cranelift and Singlepast compiler features enabled. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed Wasmer Compilation 1.0.2 Time To Compile acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 60 120 180 240 300 SE +/- 0.27, N = 3 SE +/- 0.16, N = 3 SE +/- 0.10, N = 3 SE +/- 1.30, N = 3 SE +/- 0.26, N = 3 SE +/- 1.47, N = 3 SE +/- 0.35, N = 3 115.41 115.83 115.33 257.28 116.28 209.45 115.53 1. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.7 17.7 25.1 amd-pstate schedutil 1.7 17.7 25.1 amd-pstate performance 1.6 17.8 25.1 acpi-cpufreq ondemand 1.6 17.7 25.2 OpenBenchmarking.org Watts, Fewer Is Better Timed Wasmer Compilation 1.0.2 CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max acpi-cpufreq schedutil 42.6 59.4 64.1 amd-pstate schedutil 41.9 58.5 63.0 amd-pstate performance 43.1 59.5 64.1 amd-pstate powersave 36.4 42.8 46.0 and-pstate ondemand 42.5 59.3 64.1 acpi-cpufreq powersave 39.6 43.2 46.6 acpi-cpufreq ondemand 43.3 59.1 64.1 OpenBenchmarking.org Celsius, Fewer Is Better Timed Wasmer Compilation 1.0.2 CPU Temperature Monitor 20 40 60 80 100
Timed Godot Game Engine Compilation This test times how long it takes to compile the Godot Game Engine. Godot is a popular, open-source, cross-platform 2D/3D game engine and is built using the SCons build system and targeting the X11 platform. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 3.2.3 Time To Compile acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 110 220 330 440 550 SE +/- 0.19, N = 3 SE +/- 0.28, N = 3 SE +/- 0.99, N = 3 SE +/- 1.32, N = 3 SE +/- 0.23, N = 3 SE +/- 0.67, N = 3 SE +/- 0.12, N = 3 239.40 239.40 240.38 527.64 240.06 426.74 239.29 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.7 17.1 25.2 amd-pstate schedutil 1.7 17.1 25.1 amd-pstate performance 1.5 17.1 25.2 acpi-cpufreq ondemand 1.7 17.1 25.2 OpenBenchmarking.org Watts, Fewer Is Better Timed Godot Game Engine Compilation 3.2.3 CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max acpi-cpufreq schedutil 44.5 59.3 64.9 amd-pstate schedutil 43.3 58.6 64.3 amd-pstate performance 44.9 59.1 65.1 amd-pstate powersave 37.4 42.8 46.3 and-pstate ondemand 43.9 58.7 64.5 acpi-cpufreq powersave 37.4 43.3 47.0 acpi-cpufreq ondemand 43.8 59.2 65.5 OpenBenchmarking.org Celsius, Fewer Is Better Timed Godot Game Engine Compilation 3.2.3 CPU Temperature Monitor 20 40 60 80 100
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mnasnet acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 3 6 9 12 15 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.19, N = 3 SE +/- 0.07, N = 3 5.69 5.75 5.72 12.49 5.74 10.64 5.71 MIN: 5.47 / MAX: 6.85 MIN: 5.54 / MAX: 6.14 MIN: 5.47 / MAX: 6.04 MIN: 12.28 / MAX: 17.54 MIN: 5.52 / MAX: 9.71 MIN: 10.2 / MAX: 14.45 MIN: 5.48 / MAX: 6.18 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: squeezenet_ssd acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 15 30 45 60 75 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.22, N = 3 SE +/- 0.10, N = 3 SE +/- 0.31, N = 3 SE +/- 0.17, N = 3 31.37 31.53 31.34 68.79 31.54 58.32 31.44 MIN: 30.76 / MAX: 35.56 MIN: 30.72 / MAX: 33.68 MIN: 30.6 / MAX: 39.96 MIN: 67.73 / MAX: 93.53 MIN: 30.73 / MAX: 35.25 MIN: 57.05 / MAX: 76.33 MIN: 30.62 / MAX: 35.06 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
SVT-VP9 This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 20 40 60 80 100 SE +/- 0.13, N = 7 SE +/- 0.09, N = 6 SE +/- 0.11, N = 7 SE +/- 0.03, N = 4 SE +/- 0.12, N = 6 SE +/- 0.03, N = 5 SE +/- 0.06, N = 7 99.80 99.55 99.71 45.50 96.77 55.87 99.65 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 2 4 6 8 10 6.628 6.514 6.612 6.593 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.6 15.1 24.9 amd-pstate schedutil 1.7 15.3 25.0 amd-pstate performance 1.5 15.1 25.0 acpi-cpufreq ondemand 1.6 15.1 24.9 OpenBenchmarking.org Watts, Fewer Is Better SVT-VP9 0.3 CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max acpi-cpufreq schedutil 43.3 57.3 62.1 amd-pstate schedutil 42.9 56.6 61.6 amd-pstate performance 43.5 57.3 62.1 amd-pstate powersave 39.3 42.4 45.6 and-pstate ondemand 43.3 57.1 62.4 acpi-cpufreq powersave 38.9 43.6 46.4 acpi-cpufreq ondemand 43.8 57.7 62.3 OpenBenchmarking.org Celsius, Fewer Is Better SVT-VP9 0.3 CPU Temperature Monitor 20 40 60 80 100
Zstd Compression This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19, Long Mode - Compression Speed acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 4 8 12 16 20 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 14.40 14.40 14.40 6.71 14.40 7.96 14.40 1. *** zstd command line interface 64-bits v1.4.8, by Yann Collet *** MB/s Per Watt
OpenBenchmarking.org MB/s Per Watt, More Is Better Zstd Compression Compression Level: 19, Long Mode - Compression Speed acpi-cpufreq schedutil amd-pstate performance 0.1971 0.3942 0.5913 0.7884 0.9855 0.876 0.875 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.6 16.4 21.2 amd-pstate schedutil 1.7 14.7 21.4 amd-pstate performance 1.6 16.5 21.9 acpi-cpufreq ondemand 1.6 16.4 21.6 OpenBenchmarking.org Watts, Fewer Is Better Zstd Compression CPU Power Consumption Monitor 6 12 18 24 30 CPU Temp
Min Avg Max acpi-cpufreq schedutil 38.6 58.2 65.8 amd-pstate schedutil 38.0 57.2 66.6 amd-pstate performance 39.0 59.4 68.9 amd-pstate powersave 38.5 41.7 45.0 and-pstate ondemand 38.8 58.5 68.1 acpi-cpufreq powersave 37.0 41.7 45.3 acpi-cpufreq ondemand 39.1 59.0 66.3 OpenBenchmarking.org Celsius, Fewer Is Better Zstd Compression CPU Temperature Monitor 20 40 60 80 100
ET: Legacy ETLegacy is an open-source engine evolution of Wolfenstein: Enemy Territory, a World War II era first person shooter that was released for free by Splash Damage using the id Tech 3 engine. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better ET: Legacy 2.78 Resolution: 1920 x 1080 acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 50 100 150 200 250 SE +/- 0.54, N = 3 SE +/- 0.45, N = 3 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 SE +/- 0.73, N = 3 SE +/- 0.15, N = 3 SE +/- 0.78, N = 3 219.9 221.5 222.4 105.0 207.9 127.3 215.4 Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better ET: Legacy 2.78 Resolution: 1920 x 1080 acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 4 8 12 16 20 15.59 15.66 15.50 15.37 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.5 14.1 22.5 amd-pstate schedutil 1.6 14.1 22.5 amd-pstate performance 1.6 14.4 22.8 acpi-cpufreq ondemand 1.7 14.0 21.6 OpenBenchmarking.org Watts, Fewer Is Better ET: Legacy 2.78 CPU Power Consumption Monitor 6 12 18 24 30 CPU Temp
Min Avg Max acpi-cpufreq schedutil 38.1 52.4 56.8 amd-pstate schedutil 40.0 51.3 55.3 amd-pstate performance 39.5 51.8 55.1 amd-pstate powersave 36.6 40.9 44.3 and-pstate ondemand 40.5 50.9 54.9 acpi-cpufreq powersave 37.4 41.9 45.4 acpi-cpufreq ondemand 40.0 51.3 55.5 OpenBenchmarking.org Celsius, Fewer Is Better ET: Legacy 2.78 CPU Temperature Monitor 16 32 48 64 80
Timed Mesa Compilation This test profile times how long it takes to compile Mesa with Meson/Ninja. For minimizing build dependencies and avoid versioning conflicts, test this is just the core Mesa build without LLVM or the extra Gallium3D/Mesa drivers enabled. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed Mesa Compilation 21.0 Time To Compile acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 40 80 120 160 200 SE +/- 0.13, N = 3 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 SE +/- 0.27, N = 3 SE +/- 0.12, N = 3 SE +/- 0.26, N = 3 SE +/- 0.14, N = 3 95.71 95.76 95.72 201.28 95.97 165.68 95.91 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.7 17.2 25.2 amd-pstate schedutil 1.7 17.2 25.1 amd-pstate performance 1.5 17.2 25.1 acpi-cpufreq ondemand 1.7 17.2 25.2 OpenBenchmarking.org Watts, Fewer Is Better Timed Mesa Compilation 21.0 CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max acpi-cpufreq schedutil 40.3 59.2 65.6 amd-pstate schedutil 40.4 58.9 66.4 amd-pstate performance 41.6 59.1 66.1 amd-pstate powersave 37.3 42.8 46.1 and-pstate ondemand 39.6 59.0 65.6 acpi-cpufreq powersave 37.1 43.4 46.9 acpi-cpufreq ondemand 40.8 59.2 65.9 OpenBenchmarking.org Celsius, Fewer Is Better Timed Mesa Compilation 21.0 CPU Temperature Monitor 20 40 60 80 100
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: efficientnet-b0 acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 5 10 15 20 25 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 SE +/- 0.09, N = 3 SE +/- 0.10, N = 3 SE +/- 0.09, N = 3 SE +/- 0.23, N = 3 SE +/- 0.11, N = 3 10.22 10.31 10.24 20.35 10.24 17.88 10.27 MIN: 9.82 / MAX: 11.13 MIN: 9.89 / MAX: 13.33 MIN: 9.83 / MAX: 13.89 MIN: 19.83 / MAX: 43.54 MIN: 9.82 / MAX: 13.84 MIN: 16.93 / MAX: 38.59 MIN: 9.8 / MAX: 11.88 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Xonotic This is a benchmark of Xonotic, which is a fork of the DarkPlaces-based Nexuiz game. Development began in March of 2010 on the Xonotic game. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better Xonotic 0.8.2 Resolution: 1920 x 1080 - Effects Quality: High acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 50 100 150 200 250 SE +/- 0.15, N = 3 SE +/- 0.51, N = 3 SE +/- 0.22, N = 3 SE +/- 0.12, N = 3 SE +/- 0.51, N = 3 SE +/- 0.14, N = 3 SE +/- 0.68, N = 3 212.82 212.93 213.95 109.47 201.25 130.14 206.28 MIN: 142 / MAX: 326 MIN: 144 / MAX: 338 MIN: 138 / MAX: 325 MIN: 70 / MAX: 231 MIN: 127 / MAX: 320 MIN: 86 / MAX: 260 MIN: 137 / MAX: 327 Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Xonotic 0.8.2 Resolution: 1920 x 1080 - Effects Quality: High acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 3 6 9 12 15 12.97 12.90 13.00 12.57 CPU Power Consumption
Min Avg Max amd-pstate schedutil 1.6 16.5 23.6 amd-pstate performance 1.6 16.5 23.5 acpi-cpufreq ondemand 1.6 16.4 22.6 OpenBenchmarking.org Watts, Fewer Is Better Xonotic 0.8.2 CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max amd-pstate schedutil 41.3 53.9 57.3 amd-pstate performance 41.5 54.1 57.8 amd-pstate powersave 36.0 41.9 45.9 and-pstate ondemand 41.5 52.0 55.4 acpi-cpufreq powersave 37.5 42.5 46.1 acpi-cpufreq ondemand 42.0 54.5 57.5 OpenBenchmarking.org Celsius, Fewer Is Better Xonotic 0.8.2 CPU Temperature Monitor 16 32 48 64 80
yquake2 This is a test of Yamagi Quake II. Yamagi Quake II is an enhanced client for id Software's Quake II with focus on offline and coop gameplay. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better yquake2 8.0 Renderer: Vulkan - Resolution: 1920 x 1080 acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 200 400 600 800 1000 SE +/- 1.40, N = 13 SE +/- 1.69, N = 13 SE +/- 1.09, N = 13 SE +/- 2.08, N = 10 SE +/- 4.53, N = 12 SE +/- 2.78, N = 11 SE +/- 1.65, N = 13 963.5 959.6 964.5 499.7 901.7 617.1 948.4 1. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better yquake2 8.0 Renderer: Vulkan - Resolution: 1920 x 1080 acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 50 100 150 200 250 205.84 206.80 206.42 203.48 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.6 4.7 15.6 amd-pstate schedutil 1.6 4.6 15.1 amd-pstate performance 1.6 4.7 15.7 acpi-cpufreq ondemand 1.7 4.7 15.4 OpenBenchmarking.org Watts, Fewer Is Better yquake2 8.0 CPU Power Consumption Monitor 5 10 15 20 25 CPU Temp
Min Avg Max acpi-cpufreq schedutil 38.1 43.8 47.6 amd-pstate schedutil 37.8 43.7 47.1 amd-pstate performance 38.3 43.6 47.1 amd-pstate powersave 36.3 38.7 41.3 and-pstate ondemand 37.5 41.4 44.4 acpi-cpufreq powersave 37.1 39.8 42.5 acpi-cpufreq ondemand 38.6 42.3 45.5 OpenBenchmarking.org Celsius, Fewer Is Better yquake2 8.0 CPU Temperature Monitor 14 28 42 56 70
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU-v3-v3 - Model: mobilenet-v3 acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 6.56 6.64 6.56 12.44 6.56 10.88 6.61 MIN: 6.35 / MAX: 10.98 MIN: 6.43 / MAX: 7.96 MIN: 6.37 / MAX: 8.06 MIN: 12.16 / MAX: 13.51 MIN: 6.34 / MAX: 7.89 MIN: 10.45 / MAX: 15.31 MIN: 6.27 / MAX: 37.85 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: googlenet acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 10 20 30 40 50 SE +/- 0.19, N = 3 SE +/- 0.18, N = 3 SE +/- 0.21, N = 3 SE +/- 0.09, N = 3 SE +/- 0.22, N = 3 SE +/- 0.45, N = 3 SE +/- 0.24, N = 3 23.60 23.57 23.56 44.21 23.55 38.92 23.60 MIN: 22.57 / MAX: 34.58 MIN: 22.57 / MAX: 27.06 MIN: 22.63 / MAX: 34.25 MIN: 43.69 / MAX: 47.69 MIN: 22.55 / MAX: 26.15 MIN: 37.59 / MAX: 58.52 MIN: 22.58 / MAX: 28.19 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: yolov4-tiny acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 20 40 60 80 100 SE +/- 0.23, N = 3 SE +/- 0.17, N = 3 SE +/- 0.39, N = 3 SE +/- 0.28, N = 3 SE +/- 0.08, N = 3 SE +/- 0.54, N = 3 SE +/- 0.16, N = 3 42.66 42.74 42.55 78.67 42.53 67.95 42.64 MIN: 41.77 / MAX: 46.57 MIN: 41.42 / MAX: 100.7 MIN: 41.73 / MAX: 46.88 MIN: 77.41 / MAX: 102.47 MIN: 41.94 / MAX: 46.7 MIN: 66.64 / MAX: 87.31 MIN: 41.91 / MAX: 46.81 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Xonotic This is a benchmark of Xonotic, which is a fork of the DarkPlaces-based Nexuiz game. Development began in March of 2010 on the Xonotic game. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better Xonotic 0.8.2 Resolution: 1920 x 1080 - Effects Quality: Ultra acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 40 80 120 160 200 SE +/- 0.44, N = 3 SE +/- 0.34, N = 3 SE +/- 0.35, N = 3 SE +/- 0.15, N = 3 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 SE +/- 0.28, N = 3 183.39 184.80 183.85 100.23 176.81 119.43 178.00 MIN: 98 / MAX: 288 MIN: 110 / MAX: 284 MIN: 103 / MAX: 281 MIN: 66 / MAX: 199 MIN: 106 / MAX: 280 MIN: 80 / MAX: 222 MIN: 106 / MAX: 285 Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Xonotic 0.8.2 Resolution: 1920 x 1080 - Effects Quality: Ultra acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 3 6 9 12 15 10.85 10.92 10.85 10.56 CPU Power Consumption
Min Avg Max amd-pstate schedutil 1.6 16.9 24.1 amd-pstate performance 1.5 16.9 23.9 acpi-cpufreq ondemand 1.7 16.8 23.3 OpenBenchmarking.org Watts, Fewer Is Better Xonotic 0.8.2 CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max amd-pstate schedutil 42.0 54.6 57.6 amd-pstate performance 42.3 54.9 57.6 amd-pstate powersave 36.5 42.4 45.3 and-pstate ondemand 42.3 53.7 56.8 acpi-cpufreq powersave 36.6 43.6 46.5 acpi-cpufreq ondemand 43.1 55.1 57.5 OpenBenchmarking.org Celsius, Fewer Is Better Xonotic 0.8.2 CPU Temperature Monitor 16 32 48 64 80
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mobilenet acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 12 24 36 48 60 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 SE +/- 0.01, N = 3 SE +/- 0.15, N = 3 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 SE +/- 0.15, N = 3 27.95 28.28 27.99 51.04 27.98 44.50 27.89 MIN: 26.82 / MAX: 64.15 MIN: 27.53 / MAX: 38.57 MIN: 27.27 / MAX: 31.91 MIN: 49.93 / MAX: 76 MIN: 27.17 / MAX: 38.83 MIN: 43.3 / MAX: 68.27 MIN: 26.85 / MAX: 30.66 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU-v2-v2 - Model: mobilenet-v2 acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.25, N = 3 SE +/- 0.01, N = 3 7.74 7.82 7.75 13.98 7.77 12.41 7.76 MIN: 7.42 / MAX: 11.1 MIN: 7.48 / MAX: 9.18 MIN: 7.41 / MAX: 9.27 MIN: 13.54 / MAX: 16.41 MIN: 7.46 / MAX: 11.03 MIN: 11.73 / MAX: 32.72 MIN: 7.45 / MAX: 9 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Unvanquished Unvanquished is a modern fork of the Tremulous first person shooter. Unvanquished is powered by the Daemon engine, a combination of the ioquake3 engine with the graphically-beautiful XreaL engine. Unvanquished supports a modern OpenGL 3 renderer and other advanced graphics features for this open-source game. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 1920 x 1080 - Effects Quality: Ultra acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 30 60 90 120 150 SE +/- 1.46, N = 3 SE +/- 0.93, N = 15 SE +/- 2.11, N = 3 SE +/- 0.19, N = 3 SE +/- 0.57, N = 3 SE +/- 0.20, N = 3 SE +/- 1.74, N = 3 144.8 120.1 149.2 82.9 119.6 100.4 143.7 Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Unvanquished 0.52.1 Resolution: 1920 x 1080 - Effects Quality: Ultra acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 3 6 9 12 15 9.362 8.771 9.380 9.286 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.6 15.5 23.5 amd-pstate schedutil 1.5 13.7 22.4 amd-pstate performance 1.6 15.9 23.9 acpi-cpufreq ondemand 1.6 15.5 22.4 OpenBenchmarking.org Watts, Fewer Is Better Unvanquished 0.52.1 CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max acpi-cpufreq schedutil 43.6 53.4 56.1 amd-pstate schedutil 39.8 50.4 54.4 amd-pstate performance 43.0 52.9 55.9 amd-pstate powersave 35.9 42.3 46.6 and-pstate ondemand 39.6 49.4 53.9 acpi-cpufreq powersave 36.5 43.7 49.3 acpi-cpufreq ondemand 43.1 53.4 56.1 OpenBenchmarking.org Celsius, Fewer Is Better Unvanquished 0.52.1 CPU Temperature Monitor 16 32 48 64 80
Zstd Compression This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19 - Compression Speed acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.06, N = 3 SE +/- 0.00, N = 3 16.30 16.30 16.40 9.20 16.30 10.60 16.30 1. *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet50 acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 20 40 60 80 100 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.10, N = 3 SE +/- 0.08, N = 3 SE +/- 0.04, N = 3 SE +/- 0.49, N = 3 SE +/- 0.10, N = 3 43.66 43.99 43.76 76.23 44.02 65.97 44.02 MIN: 43.05 / MAX: 47.57 MIN: 43.32 / MAX: 47.81 MIN: 43.23 / MAX: 46.75 MIN: 75.66 / MAX: 87.48 MIN: 43.35 / MAX: 47.86 MIN: 65 / MAX: 85.74 MIN: 43 / MAX: 82.85 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet18 acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 9 18 27 36 45 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.11, N = 3 SE +/- 0.22, N = 3 SE +/- 0.02, N = 3 23.53 23.65 23.53 40.43 23.70 35.82 23.56 MIN: 22.79 / MAX: 27.78 MIN: 22.81 / MAX: 28.23 MIN: 22.73 / MAX: 34.26 MIN: 40.11 / MAX: 44.76 MIN: 22.88 / MAX: 34.52 MIN: 35.13 / MAX: 41.06 MIN: 22.91 / MAX: 27.24 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
DeepSpeech Mozilla DeepSpeech is a speech-to-text engine powered by TensorFlow for machine learning and derived from Baidu's Deep Speech research paper. This test profile times the speech-to-text process for a roughly three minute audio recording. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better DeepSpeech 0.6 Acceleration: CPU acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 30 60 90 120 150 SE +/- 0.17, N = 3 SE +/- 0.64, N = 3 SE +/- 0.10, N = 3 SE +/- 0.43, N = 3 SE +/- 0.48, N = 3 SE +/- 0.77, N = 3 SE +/- 0.18, N = 3 87.05 98.87 72.46 123.61 79.95 106.18 76.35 Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.7 7.1 9.8 amd-pstate schedutil 1.7 5.4 9.7 amd-pstate performance 1.5 9.5 11.1 acpi-cpufreq ondemand 1.6 8.7 9.8 OpenBenchmarking.org Watts, Fewer Is Better DeepSpeech 0.6 CPU Power Consumption Monitor 4 8 12 16 20 Temp
Min Avg Max acpi-cpufreq schedutil 38.3 47.7 53.8 amd-pstate schedutil 39.6 45.3 51.3 amd-pstate performance 37.9 49.5 53.9 amd-pstate powersave 35.1 40.8 43.1 and-pstate ondemand 40.3 49.7 53.4 acpi-cpufreq powersave 35.5 41.5 43.9 acpi-cpufreq ondemand 37.8 49.3 53.8 OpenBenchmarking.org Celsius, Fewer Is Better DeepSpeech 0.6 CPU Temperature Monitor 15 30 45 60 75
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: alexnet acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 7 14 21 28 35 SE +/- 0.01, N = 3 SE +/- 0.19, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.21, N = 3 SE +/- 0.50, N = 3 SE +/- 0.02, N = 3 17.68 17.92 17.72 29.93 17.97 27.08 17.64 MIN: 16.79 / MAX: 28.42 MIN: 16.87 / MAX: 25.81 MIN: 16.92 / MAX: 29.22 MIN: 29.6 / MAX: 53.76 MIN: 16.76 / MAX: 28.69 MIN: 26.01 / MAX: 45.96 MIN: 16.8 / MAX: 21.8 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Xonotic This is a benchmark of Xonotic, which is a fork of the DarkPlaces-based Nexuiz game. Development began in March of 2010 on the Xonotic game. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better Xonotic 0.8.2 Resolution: 1920 x 1080 - Effects Quality: Ultimate acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 30 60 90 120 150 SE +/- 0.20, N = 3 SE +/- 0.59, N = 3 SE +/- 0.44, N = 3 SE +/- 0.07, N = 3 SE +/- 0.56, N = 3 SE +/- 0.13, N = 3 SE +/- 0.14, N = 3 142.35 142.37 142.71 86.07 139.46 101.16 138.98 MIN: 35 / MAX: 247 MIN: 35 / MAX: 244 MIN: 34 / MAX: 248 MIN: 17 / MAX: 173 MIN: 37 / MAX: 253 MIN: 20 / MAX: 197 MIN: 35 / MAX: 241 Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Xonotic 0.8.2 Resolution: 1920 x 1080 - Effects Quality: Ultimate acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 2 4 6 8 10 8.353 8.331 8.342 8.186 CPU Power Consumption
Min Avg Max amd-pstate schedutil 1.5 17.1 23.9 amd-pstate performance 1.6 17.1 24.1 acpi-cpufreq ondemand 1.6 17.0 23.1 OpenBenchmarking.org Watts, Fewer Is Better Xonotic 0.8.2 CPU Power Consumption Monitor 8 16 24 32 40 CPU Temp
Min Avg Max amd-pstate schedutil 42.6 54.9 57.4 amd-pstate performance 42.9 54.9 57.1 amd-pstate powersave 36.5 43.8 47.5 and-pstate ondemand 43.4 54.6 56.9 acpi-cpufreq powersave 37.3 45.1 48.6 acpi-cpufreq ondemand 43.9 55.5 57.6 OpenBenchmarking.org Celsius, Fewer Is Better Xonotic 0.8.2 CPU Temperature Monitor 16 32 48 64 80
DDraceNetwork This is a test of DDraceNetwork, an open-source cooperative platformer. OpenGL 3.3 is used for rendering, with fallbacks for older OpenGL versions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better DDraceNetwork 15.3.1 Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: RaiNyMore2 acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 90 180 270 360 450 SE +/- 4.00, N = 3 SE +/- 3.14, N = 3 SE +/- 3.76, N = 3 SE +/- 3.28, N = 3 SE +/- 3.28, N = 3 SE +/- 8.99, N = 15 SE +/- 2.97, N = 3 376.89 378.90 376.72 406.42 402.36 325.00 401.24 1. (CXX) g++ options: -O3 -lrt -pthread -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0
Meta Performance Per Watts OpenBenchmarking.org Performance Per Watts, More Is Better Meta Performance Per Watts Performance Per Watts acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 20 40 60 80 100 87.18 100.54 82.87 103.30
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: vgg16 acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 30 60 90 120 150 SE +/- 0.03, N = 3 SE +/- 0.16, N = 3 SE +/- 0.05, N = 3 SE +/- 0.15, N = 3 SE +/- 0.13, N = 3 SE +/- 1.29, N = 3 SE +/- 0.40, N = 3 106.88 107.30 106.71 131.95 107.28 123.73 106.82 MIN: 106.31 / MAX: 118.22 MIN: 106.3 / MAX: 117.74 MIN: 105.49 / MAX: 142.17 MIN: 130.81 / MAX: 154.74 MIN: 105.71 / MAX: 144.63 MIN: 121.51 / MAX: 146.63 MIN: 105.57 / MAX: 118.55 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Basemark GPU This is a benchmark of Basemark GPU. For this test profile to work, you must have a valid license/copy of BasemarkGPU in your Phoronix Test Suite download cache. This test profile simply automates the execution of BasemarkGPU and you must already have the Windows .zip or Linux .tar.gz in the download cache. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org FPS, More Is Better Basemark GPU 1.2 Renderer: OpenGL - Resolution: 1920 x 1080 - Graphics Preset: Medium acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 20 40 60 80 100 SE +/- 0.62, N = 3 SE +/- 0.41, N = 3 SE +/- 0.38, N = 3 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 SE +/- 0.15, N = 3 87.82 84.31 98.76 83.58 89.33 91.45 95.81 MIN: 37.72 / MAX: 553.94 MIN: 36.23 / MAX: 589.08 MIN: 38.42 / MAX: 714.09 MIN: 36.24 / MAX: 338.19 MIN: 38.21 / MAX: 518.49 MIN: 38.06 / MAX: 405.95 MIN: 41.61 / MAX: 637.98 FPS Per Watt
OpenBenchmarking.org FPS Per Watt, More Is Better Basemark GPU 1.2 Renderer: OpenGL - Resolution: 1920 x 1080 - Graphics Preset: Medium acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 2 4 6 8 10 7.261 7.091 7.281 7.428 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.5 12.1 15.3 amd-pstate schedutil 1.6 11.9 15.5 amd-pstate performance 1.5 13.6 17.1 acpi-cpufreq ondemand 1.7 12.9 15.7 OpenBenchmarking.org Watts, Fewer Is Better Basemark GPU 1.2 CPU Power Consumption Monitor 5 10 15 20 25 CPU Temp
Min Avg Max acpi-cpufreq schedutil 42.5 47.4 49.1 amd-pstate schedutil 40.6 46.2 47.9 amd-pstate performance 42.8 49.0 51.1 amd-pstate powersave 40.4 45.8 47.5 and-pstate ondemand 42.1 46.9 48.4 acpi-cpufreq powersave 40.4 46.4 49.0 acpi-cpufreq ondemand 42.4 48.2 50.4 OpenBenchmarking.org Celsius, Fewer Is Better Basemark GPU 1.2 CPU Temperature Monitor 15 30 45 60 75
Tesseract Tesseract is a fork of Cube 2 Sauerbraten with numerous graphics and game-play improvements. Tesseract has been in development since 2012 while its first release happened in May of 2014. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better Tesseract 2014-05-12 Resolution: 1920 x 1080 acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 30 60 90 120 150 SE +/- 0.74, N = 3 SE +/- 1.07, N = 3 SE +/- 1.58, N = 4 SE +/- 0.32, N = 3 SE +/- 0.60, N = 3 SE +/- 0.57, N = 3 SE +/- 1.38, N = 3 148.63 146.28 149.52 129.21 150.24 141.13 148.38 Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Tesseract 2014-05-12 Resolution: 1920 x 1080 acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 2 4 6 8 10 8.753 8.779 8.729 8.725 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.6 17.0 21.7 amd-pstate schedutil 1.6 16.7 21.5 amd-pstate performance 1.6 17.1 22.4 acpi-cpufreq ondemand 1.6 17.0 21.7 OpenBenchmarking.org Watts, Fewer Is Better Tesseract 2014-05-12 CPU Power Consumption Monitor 6 12 18 24 30 CPU Temp
Min Avg Max acpi-cpufreq schedutil 41.5 52.2 55.8 amd-pstate schedutil 40.9 50.9 54.5 amd-pstate performance 40.3 51.4 53.6 amd-pstate powersave 36.8 47.1 51.0 and-pstate ondemand 39.9 50.2 53.4 acpi-cpufreq powersave 37.6 48.3 51.5 acpi-cpufreq ondemand 41.3 51.3 55.1 OpenBenchmarking.org Celsius, Fewer Is Better Tesseract 2014-05-12 CPU Temperature Monitor 16 32 48 64 80
Basemark GPU This is a benchmark of Basemark GPU. For this test profile to work, you must have a valid license/copy of BasemarkGPU in your Phoronix Test Suite download cache. This test profile simply automates the execution of BasemarkGPU and you must already have the Windows .zip or Linux .tar.gz in the download cache. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org FPS, More Is Better Basemark GPU 1.2 Renderer: Vulkan - Resolution: 1920 x 1080 - Graphics Preset: Medium acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 30 60 90 120 150 SE +/- 0.92, N = 15 SE +/- 0.47, N = 3 SE +/- 0.91, N = 15 SE +/- 1.03, N = 15 SE +/- 0.91, N = 11 SE +/- 0.99, N = 3 SE +/- 0.17, N = 3 118.27 111.64 118.59 116.22 124.91 120.92 121.13 MIN: 64.71 / MAX: 248.91 MIN: 65.12 / MAX: 224.41 MIN: 64.77 / MAX: 251.47 MIN: 64.46 / MAX: 251.89 MIN: 68.9 / MAX: 249.46 MIN: 70.02 / MAX: 234.51 MIN: 69.82 / MAX: 233.5 FPS Per Watt
OpenBenchmarking.org FPS Per Watt, More Is Better Basemark GPU 1.2 Renderer: Vulkan - Resolution: 1920 x 1080 - Graphics Preset: Medium acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 2 4 6 8 10 7.923 7.480 7.510 7.578 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 0.8 14.9 18.3 amd-pstate schedutil 1.6 14.9 18.0 amd-pstate performance 0.8 15.8 19.2 acpi-cpufreq ondemand 1.7 16.0 19.7 OpenBenchmarking.org Watts, Fewer Is Better Basemark GPU 1.2 CPU Power Consumption Monitor 6 12 18 24 30 CPU Temp
Min Avg Max acpi-cpufreq schedutil 38.1 51.2 53.9 amd-pstate schedutil 41.1 50.2 52.5 amd-pstate performance 38.1 51.8 54.6 amd-pstate powersave 38.6 49.9 52.0 and-pstate ondemand 40.3 50.9 53.4 acpi-cpufreq powersave 39.6 50.2 53.6 acpi-cpufreq ondemand 40.0 51.6 54.8 OpenBenchmarking.org Celsius, Fewer Is Better Basemark GPU 1.2 CPU Temperature Monitor 15 30 45 60 75
Selenium This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.
Benchmark: PSPDFKit WASM - Browser: Google Chrome
amd-pstate powersave: NameError: name 'StaleElementReferenceException' is not defined
acpi-cpufreq powersave: NameError: name 'StaleElementReferenceException' is not defined
yquake2 This is a test of Yamagi Quake II. Yamagi Quake II is an enhanced client for id Software's Quake II with focus on offline and coop gameplay. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better yquake2 8.0 Renderer: OpenGL 3.x - Resolution: 1920 x 1080 acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance amd-pstate powersave and-pstate ondemand acpi-cpufreq powersave acpi-cpufreq ondemand 80 160 240 320 400 SE +/- 0.41, N = 11 SE +/- 0.86, N = 11 SE +/- 0.45, N = 11 SE +/- 0.55, N = 10 SE +/- 0.67, N = 10 SE +/- 0.82, N = 10 SE +/- 0.52, N = 11 370.2 368.3 367.7 357.4 368.1 364.8 367.8 1. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better yquake2 8.0 Renderer: OpenGL 3.x - Resolution: 1920 x 1080 acpi-cpufreq schedutil amd-pstate schedutil amd-pstate performance acpi-cpufreq ondemand 11 22 33 44 55 47.62 47.57 47.17 46.89 CPU Power Consumption
Min Avg Max acpi-cpufreq schedutil 1.6 7.8 19.8 amd-pstate schedutil 1.6 7.7 19.8 amd-pstate performance 1.6 7.8 20.1 acpi-cpufreq ondemand 1.7 7.8 19.6 OpenBenchmarking.org Watts, Fewer Is Better yquake2 8.0 CPU Power Consumption Monitor 6 12 18 24 30 CPU Temp
Min Avg Max acpi-cpufreq schedutil 43.5 44.9 46.6 amd-pstate schedutil 42.4 44.0 45.1 amd-pstate performance 43.1 44.5 46.0 amd-pstate powersave 40.4 41.8 43.4 and-pstate ondemand 41.8 43.1 44.6 acpi-cpufreq powersave 41.4 42.8 44.6 acpi-cpufreq ondemand 43.4 44.7 46.1 OpenBenchmarking.org Celsius, Fewer Is Better yquake2 8.0 CPU Temperature Monitor 14 28 42 56 70
libavif avifenc This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.
Encoder Speed: 10
acpi-cpufreq schedutil: The test quit with a non-zero exit status.
amd-pstate performance: The test quit with a non-zero exit status.
amd-pstate powersave: The test quit with a non-zero exit status.
and-pstate ondemand: The test quit with a non-zero exit status.
acpi-cpufreq powersave: The test quit with a non-zero exit status.
Encoder Speed: 6
acpi-cpufreq schedutil: The test quit with a non-zero exit status.
amd-pstate performance: The test quit with a non-zero exit status.
amd-pstate powersave: The test quit with a non-zero exit status.
and-pstate ondemand: The test quit with a non-zero exit status.
acpi-cpufreq powersave: The test quit with a non-zero exit status.
Encoder Speed: 6, Lossless
acpi-cpufreq schedutil: The test quit with a non-zero exit status.
amd-pstate performance: The test quit with a non-zero exit status.
amd-pstate powersave: The test quit with a non-zero exit status.
and-pstate ondemand: The test quit with a non-zero exit status.
acpi-cpufreq powersave: The test quit with a non-zero exit status.
acpi-cpufreq ondemand: The test quit with a non-zero exit status.
acpi-cpufreq schedutil Processor: AMD Ryzen 5 5500U @ 2.10GHz (6 Cores / 12 Threads), Motherboard: LENOVO LNVNB161216 (GLCN22WW BIOS), Chipset: AMD Renoir Root Complex, Memory: 6GB, Disk: 256GB SAMSUNG MZALQ256HBJD-00BL2, Graphics: AMD Lucienne 2GB (1800/400MHz), Audio: AMD Renoir Radeon HD Audio, Network: Qualcomm Atheros QCA6174 802.11ac
OS: Ubuntu 21.04, Kernel: 5.15.0-pstate4 (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server 1.20.11 + Wayland, OpenGL: 4.6 Mesa 22.0.0-devel (git-9d9de15 2021-11-15 hirsute-oibaf-ppa) (LLVM 13.0.0 DRM 3.42 5.15.0-pstate4), Vulkan: 1.2.197, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,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-build-config=bootstrap-lto-lean --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 -vProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8608102Graphics Notes: GLAMOR - BAR1 / Visible vRAM Size: 2048 MBPython Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + 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
Testing initiated at 19 November 2021 15:45 by user pts.
amd-pstate schedutil Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,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-build-config=bootstrap-lto-lean --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 -vProcessor Notes: Scaling Governor: amd-pstate schedutil (Boost: Enabled) - CPU Microcode: 0x8608102Graphics Notes: GLAMOR - BAR1 / Visible vRAM Size: 2048 MBPython Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + 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
Testing initiated at 19 November 2021 19:35 by user pts.
amd-pstate performance Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,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-build-config=bootstrap-lto-lean --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 -vProcessor Notes: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0x8608102Graphics Notes: GLAMOR - BAR1 / Visible vRAM Size: 2048 MBPython Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + 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
Testing initiated at 20 November 2021 04:31 by user pts.
amd-pstate powersave Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,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-build-config=bootstrap-lto-lean --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 -vProcessor Notes: Scaling Governor: amd-pstate powersave (Boost: Enabled) - CPU Microcode: 0x8608102Graphics Notes: GLAMOR - BAR1 / Visible vRAM Size: 2048 MBPython Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + 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
Testing initiated at 20 November 2021 08:42 by user pts.
and-pstate ondemand Processor: AMD Ryzen 5 5500U @ 4.06GHz (6 Cores / 12 Threads), Motherboard: LENOVO LNVNB161216 (GLCN22WW BIOS), Chipset: AMD Renoir Root Complex, Memory: 6GB, Disk: 256GB SAMSUNG MZALQ256HBJD-00BL2, Graphics: AMD Lucienne 2GB (1800/400MHz), Audio: AMD Renoir Radeon HD Audio, Network: Qualcomm Atheros QCA6174 802.11ac
OS: Ubuntu 21.04, Kernel: 5.15.0-pstate4 (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server 1.20.11 + Wayland, OpenGL: 4.6 Mesa 22.0.0-devel (git-9d9de15 2021-11-15 hirsute-oibaf-ppa) (LLVM 13.0.0 DRM 3.42 5.15.0-pstate4), Vulkan: 1.2.197, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,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-build-config=bootstrap-lto-lean --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 -vProcessor Notes: Scaling Governor: amd-pstate ondemand (Boost: Enabled) - CPU Microcode: 0x8608102Graphics Notes: GLAMOR - BAR1 / Visible vRAM Size: 2048 MBPython Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + 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
Testing initiated at 20 November 2021 16:51 by user pts.
acpi-cpufreq powersave Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,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-build-config=bootstrap-lto-lean --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 -vProcessor Notes: Scaling Governor: acpi-cpufreq powersave (Boost: Enabled) - CPU Microcode: 0x8608102Graphics Notes: GLAMOR - BAR1 / Visible vRAM Size: 2048 MBPython Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + 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
Testing initiated at 20 November 2021 21:11 by user pts.
acpi-cpufreq ondemand Processor: AMD Ryzen 5 5500U @ 2.10GHz (6 Cores / 12 Threads), Motherboard: LENOVO LNVNB161216 (GLCN22WW BIOS), Chipset: AMD Renoir Root Complex, Memory: 6GB, Disk: 256GB SAMSUNG MZALQ256HBJD-00BL2, Graphics: AMD Lucienne 2GB (1800/400MHz), Audio: AMD Renoir Radeon HD Audio, Network: Qualcomm Atheros QCA6174 802.11ac
OS: Ubuntu 21.04, Kernel: 5.15.0-pstate4 (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server 1.20.11 + Wayland, OpenGL: 4.6 Mesa 22.0.0-devel (git-9d9de15 2021-11-15 hirsute-oibaf-ppa) (LLVM 13.0.0 DRM 3.42 5.15.0-pstate4), Vulkan: 1.2.197, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,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-build-config=bootstrap-lto-lean --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 -vProcessor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8608102Graphics Notes: GLAMOR - BAR1 / Visible vRAM Size: 2048 MBPython Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + 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
Testing initiated at 21 November 2021 04:26 by user pts.