AMD P-State Linux 6.3 Testing

Benchmarks by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2302279-NE-AMDPSTATE10
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

C++ Boost Tests 2 Tests
Timed Code Compilation 4 Tests
C/C++ Compiler Tests 9 Tests
Compression Tests 2 Tests
CPU Massive 13 Tests
Creator Workloads 14 Tests
Database Test Suite 3 Tests
Encoding 7 Tests
Game Development 3 Tests
HPC - High Performance Computing 7 Tests
Machine Learning 3 Tests
Molecular Dynamics 4 Tests
MPI Benchmarks 2 Tests
Multi-Core 20 Tests
NVIDIA GPU Compute 2 Tests
Intel oneAPI 4 Tests
OpenMPI Tests 3 Tests
Programmer / Developer System Benchmarks 6 Tests
Python Tests 8 Tests
Renderers 2 Tests
Scientific Computing 4 Tests
Server 5 Tests
Server CPU Tests 9 Tests
Single-Threaded 3 Tests
Video Encoding 6 Tests
Common Workstation Benchmarks 3 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Additional Graphs

Show Perf Per Clock Calculation Graphs Where Applicable

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
amd_pstate_epp powersave balance_performance
February 21 2023
  12 Hours, 18 Minutes
amd_pstate_epp performance balance_performance
February 22 2023
  10 Hours, 43 Minutes
amd_pstate_epp powersave power
February 22 2023
  12 Hours, 39 Minutes
amd_pstate_epp performance performance
February 23 2023
  9 Hours, 52 Minutes
amd_pstate schedutil
February 23 2023
  17 Hours, 34 Minutes
amd_pstate performance
February 24 2023
  11 Hours, 43 Minutes
amd_pstate powersave
February 24 2023
  1 Day, 8 Hours, 2 Minutes
amd_pstate ondemand
February 25 2023
  13 Hours, 38 Minutes
acpi_cpufreq schedutil
February 26 2023
  13 Hours, 7 Minutes
acpi_cpufreq ondemand
February 26 2023
  11 Hours, 42 Minutes
acpi_cpufreq performance
February 27 2023
  10 Hours, 14 Minutes
Invert Hiding All Results Option
  14 Hours, 8 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

amd_pstate_epp powersave balance_performance

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: amd_pstate_epp powersave (EPP: balance_performance) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

amd_pstate_epp performance balance_performance

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: amd_pstate_epp performance (EPP: performance) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

amd_pstate_epp powersave power

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: amd_pstate_epp powersave (EPP: power) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

amd_pstate_epp performance performance

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: amd_pstate_epp performance (EPP: performance) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

amd_pstate schedutil

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: amd-pstate schedutil (Boost: Enabled) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

amd_pstate performance

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

amd_pstate powersave

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: amd-pstate powersave (Boost: Enabled) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

amd_pstate ondemand

Processor: 2 x AMD EPYC 7773X 64-Core @ 3.53GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 512GB, Disk: 800GB INTEL SSDPF21Q800GB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 22.04, Kernel: 6.2.0-phx (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.3, Vulkan: 1.3.224, Compiler: GCC 11.3.0 + LLVM 14.0.0, File-System: ext4, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: amd-pstate ondemand (Boost: Enabled) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

acpi_cpufreq schedutil

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

acpi_cpufreq ondemand

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

acpi_cpufreq performance

Changed Processor to 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads).

Processor Change: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001229

AMD P-State Linux 6.3 TestingOpenBenchmarking.orgPhoronix Test Suite2 x AMD EPYC 7773X 64-Core @ 3.53GHz (128 Cores / 256 Threads)2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads)AMD DAYTONA_X (RYM1009B BIOS)AMD Starship/Matisse512GB800GB INTEL SSDPF21Q800GBASPEEDVE2282 x Mellanox MT27710Ubuntu 22.046.2.0-phx (x86_64)GNOME Shell 42.5X Server 1.21.1.31.3.224GCC 11.3.0 + LLVM 14.0.0ext41920x1080ProcessorsMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen ResolutionAMD P-State Linux 6.3 Testing BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v - amd_pstate_epp powersave balance_performance: Scaling Governor: amd_pstate_epp powersave (EPP: balance_performance) - CPU Microcode: 0xa001229 - amd_pstate_epp performance balance_performance: Scaling Governor: amd_pstate_epp performance (EPP: performance) - CPU Microcode: 0xa001229 - amd_pstate_epp powersave power: Scaling Governor: amd_pstate_epp powersave (EPP: power) - CPU Microcode: 0xa001229 - amd_pstate_epp performance performance: Scaling Governor: amd_pstate_epp performance (EPP: performance) - CPU Microcode: 0xa001229 - amd_pstate schedutil: Scaling Governor: amd-pstate schedutil (Boost: Enabled) - CPU Microcode: 0xa001229 - amd_pstate performance: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa001229 - amd_pstate powersave: Scaling Governor: amd-pstate powersave (Boost: Enabled) - CPU Microcode: 0xa001229 - amd_pstate ondemand: Scaling Governor: amd-pstate ondemand (Boost: Enabled) - CPU Microcode: 0xa001229 - acpi_cpufreq schedutil: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001229 - acpi_cpufreq ondemand: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa001229 - acpi_cpufreq performance: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001229 - Python 3.10.6- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

amd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performanceLogarithmic Result OverviewPhoronix Test SuitePyBenchPHPBenchZstd CompressionStargate Digital Audio WorkstationVP9 libvpx EncodingTimed Gem5 CompilationBRL-CADOpenVINOTimed Node.js CompilationKvazaarTimed Godot Game Engine Compilationuvg266VVenCTimed Linux Kernel CompilationBlenderNAMD7-Zip CompressionSVT-AV1OpenFOAMClickHousenginxNeural Magic DeepSparseTensorFlowOpenVKLGROMACSCockroachDBEmbreex265PostgreSQLXcompact3d Incompact3dOSPRay Studio

AMD P-State Linux 6.3 Testingtensorflow: CPU - 256 - GoogLeNetopenvkl: vklBenchmark Scalaropenvkl: vklBenchmark ISPCtensorflow: CPU - 256 - AlexNetbrl-cad: VGR Performance Metricpgbench: 100 - 500 - Read Write - Average Latencypgbench: 100 - 500 - Read Writeclickhouse: 100M Rows Hits Dataset, Third Runclickhouse: 100M Rows Hits Dataset, Second Runclickhouse: 100M Rows Hits Dataset, First Run / Cold Cachepgbench: 100 - 800 - Read Write - Average Latencypgbench: 100 - 800 - Read Writecockroach: KV, 95% Reads - 512pgbench: 100 - 500 - Read Only - Average Latencypgbench: 100 - 500 - Read Onlyincompact3d: X3D-benchmarking input.i3dbuild-gem5: Time To Compilevpxenc: Speed 5 - Bosphorus 4Kbuild-linux-kernel: allmodconfigvvenc: Bosphorus 4K - Fastpgbench: 100 - 800 - Read Only - Average Latencypgbench: 100 - 800 - Read Onlystargate: 192000 - 1024pgbench: 100 - 1000 - Read Write - Average Latencypgbench: 100 - 1000 - Read Writeopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUpgbench: 100 - 1000 - Read Only - Average Latencypgbench: 100 - 1000 - Read Onlyblender: Barbershop - CPU-Onlycockroach: KV, 10% Reads - 512build-nodejs: Time To Compileospray-studio: 3 - 4K - 32 - Path Tracerospray-studio: 3 - 4K - 1 - Path Tracerospray-studio: 1 - 4K - 1 - Path Tracerospray-studio: 1 - 4K - 32 - Path Traceropenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUvvenc: Bosphorus 4K - Fasterbuild-linux-kernel: defconfigopenfoam: drivaerFastback, Medium Mesh Size - Execution Timeopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timecockroach: MoVR - 512nginx: 500openvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamcompress-zstd: 19, Long Mode - Decompression Speedcompress-zstd: 19, Long Mode - Compression Speeddeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamcompress-7zip: Decompression Ratingcompress-7zip: Compression Ratingdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamcompress-zstd: 19 - Decompression Speedcompress-zstd: 19 - Compression Speeddeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUbuild-godot: Time To Compilesvt-av1: Preset 4 - Bosphorus 4Kblender: Pabellon Barcelona - CPU-Onlygromacs: MPI CPU - water_GMX50_bareopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUblender: Classroom - CPU-Onlyphpbench: PHP Benchmark Suitesvt-av1: Preset 12 - Bosphorus 4Kdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamx265: Bosphorus 4Kpybench: Total For Average Test Timesuvg266: Bosphorus 4K - Mediumembree: Pathtracer ISPC - Asian Dragonkvazaar: Bosphorus 4K - Ultra Fastkvazaar: Bosphorus 4K - Super Fastuvg266: Bosphorus 4K - Ultra Fastkvazaar: Bosphorus 4K - Mediumuvg266: Bosphorus 4K - Super Fastblender: Fishy Cat - CPU-Onlynamd: ATPase Simulation - 327,506 Atomssvt-av1: Preset 13 - Bosphorus 4Kembree: Pathtracer ISPC - Crownamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance38.4136451487.75285398317.37228873372.98373.47355.1232.9612427575876.40.3901288550264.910481157.10211.63176.4953.3590.64112482662.05925945.509219783.5135205.470.8281207540141.7944725.5111.94941798130411013543817.493654.516.32625.521167.409116.05227641.8146738.1617.103738.04239.05267.15205.6828310.2961195.08.9168.9182926.20284030.0315.52587.7380108.1971716703500471869.215072.84511278.316.0868.075673.0239207.6114307.03851195.3553.0941.8983.45345.9911.07924.175291.4537.94687682175.455104.5730610.7001158.1292403.29176.9866830.096718.56100324.2892.206450.6747.9741.1329.4239.9619.170.22286170.265122.501440.1937451697.12290518114.63835610406.99409.86395.5329.8232683086214.80.3831306099264.590464149.76713.37172.8844.0220.64412417262.34807941.177242993.4535601.830.8271209033140.1850217.2105.52941650129911033557317.413670.787.39722.623170.71478114.86885761.0147764.2517.063748.17239.29266.96205.4179310.43301203.69.2868.7056929.78944015.9115.54587.8421108.1954726521522348868.871972.94971278.617.6867.927572.9379207.4377307.64201195.6053.0737.3214.15845.7211.17924.165294.9737.68697478186.048104.7553609.6137157.5501404.953476.9790830.013120.5599827.0194.784156.1454.6947.2531.9946.2618.800.22270194.103123.145831.6434647765.63286395117.48628682353.17349.30339.6833.1292417374380.00.3871292798263.300232173.2017.95184.4702.4710.64212459141.80123846.474215223.3236975.340.8151226429143.0443287.2120.48341532130311023524317.533645.604.76930.833169.24992116.28282570.5145614.7617.143730.66238.16268.24205.6999309.37881186.08.7268.5591931.60054033.6315.50587.7795108.1498661420459617868.924672.79521269.815.2867.019973.0501207.3328307.71291199.8752.9147.9352.44346.7311.13124.245277.0238.35671207155.770104.6604609.8987158.0751403.586077.0202829.603515.33100817.3393.727941.8345.5633.7620.6633.7919.740.22450145.323121.297040.3938551296.73298071915.52932286394.98407.73392.9529.0002759686477.30.3891286042264.824544148.50312.83172.8574.0230.64512404062.34644738.341260853.3836507.110.8151226743140.3649015.5105.82541686130211013521017.373679.317.35222.530167.81864116.19384763.4152654.8617.073744.85239.70266.56205.3031310.74481203.39.2668.5813931.58214005.0315.55587.6097108.1144733882514443868.261673.05611276.217.5866.981873.1372207.1853307.89201203.5252.7937.0114.18145.7511.07424.175291.0037.57700287173.314104.6233610.3155157.7002404.546476.9051830.324120.63101027.0693.501255.8554.7746.0832.3046.3118.950.22021188.423122.872926.6332746836.50283650427.74419298251.84254.40252.7966.3871239772179.60.796636088267.536092156.9453.06182.7683.1361.1467049290.81141881.192126133.5533751.581.411714980147.4641485.5113.13143705137611663697632.422062.046.23025.392182.43689127.85527195.9138510.0046.491416.77240.82265.31212.6277299.56801191.59.2071.1617897.63754262.2914.63605.6728104.8933699228394982895.127270.74991261.817.1893.428271.0074214.4729297.13871260.4950.3541.9403.32248.498.48225.435029.0540.0471112590.277108.6614587.4762164.2008388.639278.8686809.904816.3698712.2588.802226.5426.2121.6514.3925.4320.260.2342072.221116.753040.8937453497.50281535615.25732858406.41404.95394.3228.7152788082071.40.3811311837265.312622146.64413.32173.6364.0210.63012686882.36307040.155249043.3936428.760.8121230841140.3549340.4104.93441588130010983518617.373678.917.30622.519168.799116.10875766.8151325.0117.053749.69239.02267.30205.4057310.30041171.29.3168.6499930.49324030.7915.52586.8584108.4041746376530689867.899372.90791188.117.6866.959573.2692207.6741307.26691195.2353.0337.0534.18445.7711.05324.175292.0837.73701215182.358104.7278609.9637157.7992404.295076.9068830.851920.74101026.8993.605055.2753.7745.4632.0045.4118.890.22464191.046123.02488.747210216.5440561475.984668676.6675.8666.81146.572546516811.81.571318480540.5448811100.3631.861094.3740.5682.5223173600.301450201.101497324.555175.963.203312245933.4111461.4752.9863329506854867000291743315.26202.831.157156.783773.03283773.96684126.827774.70107.17596.041229.8651.521124.304656.6582140.11.06295.4918215.516724236.972.543485.212918.20481042871009704864.702812.9683146.11.974868.105713.00281143.055555.22457565.218.38258.8730.558297.672.167153.78830.31254.467957036.647577.7688109.7693884.291370.8684431.9597147.68804.3787753.9724.79177.727.436.884.836.77124.481.4098232.26519.668537.0336351475.69286374216.43632486310.66306.46297.7741.9881905675334.70.4901037703262.403117153.9038.47177.0633.6760.8159977421.35854955.954178753.4035501.211.069955977141.9145780.3109.81341897132211183544035.391915.376.64624.520167.90491119.63471574.8122126.5636.351960.30228.75279.33206.1379309.59581178.09.1368.5979931.20324103.6415.24589.6910107.4707739016485387876.496172.51951280.517.2876.332172.4101208.0910306.39941210.7652.4840.8123.86546.199.55024.485224.8337.85705341171.877105.1513607.3304158.9464401.731376.5661834.463819.29100424.5892.800452.6052.1741.9030.3241.5719.180.22289161.778121.857639.2437653179.36302117117.90928016352.85362.27351.2133.7232374379962.20.3891291471263.625285149.22214.36172.6063.7670.63612580662.34611244.364225673.4136248.380.8081237871140.5547827.0106.46642130130611033550517.443663.487.34722.610166.47566116.43538438.2146083.1617.093741.06239.94266.14205.4931310.09401203.29.2968.5451932.00274054.3015.41587.7789108.1330748549475861868.815773.10261270.917.4866.622373.0290207.2711307.71651195.7653.0637.5764.01345.9511.17324.175292.4237.61698785167.611104.7469609.7624157.8251404.273077.0980828.896620.6799921.2193.761552.9352.3240.8222.9740.7118.900.22025144.342122.705540.0035752494.62281426917.19429347357.94357.63351.3934.0592349381782.30.4451124224264.797139152.99010.72174.9463.9740.74510745002.32677044.891222793.4435666.690.9241082794141.9849459.9107.14342264132211203562817.653621.587.37323.440168.99869120.10383698.0149876.5217.333689.97241.17264.82206.4473308.67651203.29.2168.7068929.79104041.3115.44588.6134107.8991740039507039872.891272.77291264.717.5872.065072.7821207.8753306.68221203.4252.7638.3654.09045.9210.85324.365250.1537.92708218180.332105.0236608.3023158.0475403.280677.0107829.174519.90100627.2092.953755.5854.7844.5032.3645.1919.000.22290180.343120.799840.4236752495.71292157215.18333019401.81410.46393.1529.5372709386045.20.3891285905263.627543147.00214.17173.6344.0500.64812348692.36707439.602252523.7232979.740.8321202637140.4549731.9105.54141859130611043540617.483655.417.32022.652164.04046115.75608765.2147285.7817.093741.35238.32268.04205.2817310.61451209.19.1268.7650928.53814032.1015.49587.3828108.1608742955528289869.187273.15921272.817.5867.829673.2510207.5798307.16581195.1453.1237.3844.18245.8511.12524.175291.8137.71699816180.860104.8041609.0422157.8814404.130477.0588828.816120.96100226.9391.372455.9255.0346.4532.0946.0719.010.22441189.131123.0519OpenBenchmarking.org

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries too. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 256 - Model: GoogLeNetamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance918273645SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.19, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.12, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.10, N = 338.4140.1931.6440.3926.6340.898.7437.0339.2440.0040.42
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 256 - Model: GoogLeNetamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance918273645Min: 38.31 / Avg: 38.41 / Max: 38.49Min: 40.12 / Avg: 40.19 / Max: 40.3Min: 31.49 / Avg: 31.64 / Max: 31.73Min: 40.01 / Avg: 40.39 / Max: 40.61Min: 26.53 / Avg: 26.63 / Max: 26.82Min: 40.83 / Avg: 40.89 / Max: 40.98Min: 8.51 / Avg: 8.74 / Max: 8.88Min: 36.91 / Avg: 37.03 / Max: 37.21Min: 39.13 / Avg: 39.24 / Max: 39.31Min: 39.91 / Avg: 40 / Max: 40.12Min: 40.3 / Avg: 40.42 / Max: 40.61

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 1.3.1Benchmark: vklBenchmark Scalaramd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance80160240320400SE +/- 6.08, N = 6SE +/- 3.82, N = 5SE +/- 2.19, N = 3SE +/- 1.20, N = 3SE +/- 2.31, N = 3SE +/- 3.95, N = 9SE +/- 0.33, N = 3SE +/- 3.76, N = 3SE +/- 4.33, N = 3SE +/- 1.76, N = 3SE +/- 4.13, N = 936437434638532737472363376357367MIN: 71 / MAX: 1707MIN: 75 / MAX: 1552MIN: 62 / MAX: 1800MIN: 75 / MAX: 1589MIN: 72 / MAX: 1129MIN: 74 / MAX: 1559MIN: 11 / MAX: 516MIN: 73 / MAX: 1686MIN: 75 / MAX: 1829MIN: 75 / MAX: 1532MIN: 73 / MAX: 1729
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 1.3.1Benchmark: vklBenchmark Scalaramd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance70140210280350Min: 339 / Avg: 364 / Max: 378Min: 365 / Avg: 373.6 / Max: 383Min: 342 / Avg: 346.33 / Max: 349Min: 383 / Avg: 385.33 / Max: 387Min: 323 / Avg: 327 / Max: 331Min: 353 / Avg: 373.78 / Max: 389Min: 71 / Avg: 71.67 / Max: 72Min: 357 / Avg: 363.33 / Max: 370Min: 367 / Avg: 375.67 / Max: 380Min: 354 / Avg: 357.33 / Max: 360Min: 349 / Avg: 367.22 / Max: 385

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 1.3.1Benchmark: vklBenchmark ISPCamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance120240360480600SE +/- 4.72, N = 7SE +/- 1.76, N = 3SE +/- 2.08, N = 3SE +/- 4.37, N = 3SE +/- 5.51, N = 3SE +/- 6.51, N = 4SE +/- 1.20, N = 3SE +/- 3.61, N = 3SE +/- 6.96, N = 3SE +/- 4.59, N = 8SE +/- 1.76, N = 3514516477512468534102514531524524MIN: 148 / MAX: 1583MIN: 150 / MAX: 1507MIN: 107 / MAX: 1723MIN: 151 / MAX: 1504MIN: 146 / MAX: 1159MIN: 153 / MAX: 1522MIN: 24 / MAX: 400MIN: 149 / MAX: 1600MIN: 153 / MAX: 1787MIN: 148 / MAX: 1602MIN: 149 / MAX: 1516
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 1.3.1Benchmark: vklBenchmark ISPCamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance90180270360450Min: 501 / Avg: 513.57 / Max: 535Min: 513 / Avg: 515.67 / Max: 519Min: 474 / Avg: 477 / Max: 481Min: 507 / Avg: 512.33 / Max: 521Min: 458 / Avg: 468 / Max: 477Min: 526 / Avg: 533.5 / Max: 553Min: 100 / Avg: 102.33 / Max: 104Min: 507 / Avg: 514 / Max: 519Min: 520 / Avg: 531.33 / Max: 544Min: 502 / Avg: 524.25 / Max: 537Min: 521 / Avg: 523.67 / Max: 527

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries too. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 256 - Model: AlexNetamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance20406080100SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.63, N = 6SE +/- 0.28, N = 3SE +/- 0.31, N = 3SE +/- 0.36, N = 3SE +/- 0.01, N = 3SE +/- 0.66, N = 3SE +/- 1.99, N = 9SE +/- 0.82, N = 9SE +/- 0.99, N = 387.7597.1265.6396.7336.5097.5016.5475.6979.3694.6295.71
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 256 - Model: AlexNetamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance20406080100Min: 87.69 / Avg: 87.75 / Max: 87.83Min: 97.05 / Avg: 97.12 / Max: 97.25Min: 63.37 / Avg: 65.63 / Max: 66.82Min: 96.2 / Avg: 96.73 / Max: 97.17Min: 36.12 / Avg: 36.5 / Max: 37.12Min: 96.87 / Avg: 97.5 / Max: 98.11Min: 16.53 / Avg: 16.54 / Max: 16.57Min: 74.37 / Avg: 75.69 / Max: 76.49Min: 70.29 / Avg: 79.36 / Max: 83.83Min: 90.53 / Avg: 94.62 / Max: 96.66Min: 93.74 / Avg: 95.71 / Max: 96.84

BRL-CAD

BRL-CAD is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.34VGR Performance Metricamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance600K1200K1800K2400K3000K28539832905181286395129807192836504281535640561428637423021171281426929215721. (CXX) g++ options: -std=c++14 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lregex_brl -lz_brl -lnetpbm -ldl -lm -ltk8.6

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latencyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance20406080100SE +/- 0.28, N = 12SE +/- 0.71, N = 12SE +/- 0.28, N = 12SE +/- 0.24, N = 12SE +/- 2.25, N = 12SE +/- 0.22, N = 12SE +/- 2.49, N = 12SE +/- 1.31, N = 12SE +/- 0.30, N = 12SE +/- 0.46, N = 12SE +/- 0.23, N = 1217.3714.6417.4915.5327.7415.2675.9816.4417.9117.1915.181. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latencyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance1530456075Min: 14.9 / Avg: 17.37 / Max: 18.52Min: 7.84 / Avg: 14.64 / Max: 16.17Min: 14.95 / Avg: 17.49 / Max: 18.6Min: 13.66 / Avg: 15.53 / Max: 16.51Min: 17.53 / Avg: 27.74 / Max: 41.47Min: 13.01 / Avg: 15.26 / Max: 16Min: 51.06 / Avg: 75.98 / Max: 83.24Min: 11.5 / Avg: 16.44 / Max: 23.53Min: 15.11 / Avg: 17.91 / Max: 19.36Min: 13.64 / Avg: 17.19 / Max: 18.86Min: 13.3 / Avg: 15.18 / Max: 15.931. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 500 - Mode: Read Writeamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance8K16K24K32K40KSE +/- 508.85, N = 12SE +/- 2742.94, N = 12SE +/- 497.87, N = 12SE +/- 524.88, N = 12SE +/- 1491.09, N = 12SE +/- 539.21, N = 12SE +/- 295.83, N = 12SE +/- 2388.98, N = 12SE +/- 523.79, N = 12SE +/- 904.79, N = 12SE +/- 531.49, N = 122887335610286823228619298328586686324862801629347330191. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 500 - Mode: Read Writeamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance6K12K18K24K30KMin: 26997.89 / Avg: 28873.06 / Max: 33551.32Min: 30916.81 / Avg: 35609.68 / Max: 63760.94Min: 26887.22 / Avg: 28681.56 / Max: 33456.03Min: 30285.84 / Avg: 32285.73 / Max: 36596.63Min: 12057.49 / Avg: 19297.86 / Max: 28530.99Min: 31256.78 / Avg: 32857.63 / Max: 38444.51Min: 6006.66 / Avg: 6686.23 / Max: 9792.4Min: 21247.94 / Avg: 32485.74 / Max: 43471.02Min: 25830.95 / Avg: 28015.99 / Max: 33089.43Min: 26506.49 / Avg: 29347.03 / Max: 36658.31Min: 31384.96 / Avg: 33018.82 / Max: 37600.591. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

ClickHouse

ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ / https://github.com/ClickHouse/ClickBench/tree/main/clickhouse with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all separate queries performed as an aggregate. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third Runamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance90180270360450SE +/- 3.70, N = 3SE +/- 1.36, N = 3SE +/- 2.43, N = 3SE +/- 3.27, N = 3SE +/- 2.60, N = 3SE +/- 2.49, N = 3SE +/- 0.60, N = 3SE +/- 0.84, N = 3SE +/- 1.95, N = 3SE +/- 2.12, N = 3SE +/- 1.10, N = 3372.98406.99353.17394.98251.84406.4176.66310.66352.85357.94401.81MIN: 54.1 / MAX: 4285.71MIN: 53.29 / MAX: 3333.33MIN: 44.91 / MAX: 3000MIN: 57.97 / MAX: 3529.41MIN: 48.15 / MAX: 3157.89MIN: 52.77 / MAX: 3529.41MIN: 8.52 / MAX: 588.24MIN: 51.28 / MAX: 2222.22MIN: 50.59 / MAX: 3529.41MIN: 56.71 / MAX: 2857.14MIN: 56.71 / MAX: 3333.33
OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third Runamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance70140210280350Min: 368.13 / Avg: 372.98 / Max: 380.26Min: 405.05 / Avg: 406.99 / Max: 409.62Min: 350.45 / Avg: 353.17 / Max: 358.01Min: 388.46 / Avg: 394.98 / Max: 398.61Min: 248.97 / Avg: 251.84 / Max: 257.02Min: 401.66 / Avg: 406.41 / Max: 410.07Min: 75.81 / Avg: 76.66 / Max: 77.81Min: 308.98 / Avg: 310.66 / Max: 311.6Min: 350.37 / Avg: 352.85 / Max: 356.69Min: 354.46 / Avg: 357.94 / Max: 361.79Min: 399.64 / Avg: 401.81 / Max: 403.26

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second Runamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance90180270360450SE +/- 3.92, N = 3SE +/- 4.88, N = 3SE +/- 1.73, N = 3SE +/- 1.07, N = 3SE +/- 3.86, N = 3SE +/- 4.90, N = 3SE +/- 0.06, N = 3SE +/- 2.11, N = 3SE +/- 0.20, N = 3SE +/- 2.51, N = 3SE +/- 3.72, N = 3373.47409.86349.30407.73254.40404.9575.86306.46362.27357.63410.46MIN: 52.86 / MAX: 3750MIN: 57.64 / MAX: 4285.71MIN: 45.25 / MAX: 4000MIN: 56.66 / MAX: 4285.71MIN: 47.85 / MAX: 4285.71MIN: 54.05 / MAX: 4285.71MIN: 50.98 / MAX: 2222.22MIN: 50.98 / MAX: 4615.38MIN: 57.8 / MAX: 3529.41MIN: 58.42 / MAX: 4615.38
OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second Runamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance70140210280350Min: 365.7 / Avg: 373.47 / Max: 378.28Min: 403.95 / Avg: 409.86 / Max: 419.54Min: 346.56 / Avg: 349.3 / Max: 352.51Min: 405.89 / Avg: 407.73 / Max: 409.59Min: 247.24 / Avg: 254.4 / Max: 260.5Min: 395.83 / Avg: 404.95 / Max: 412.61Min: 75.79 / Avg: 75.86 / Max: 75.97Min: 302.61 / Avg: 306.46 / Max: 309.88Min: 361.87 / Avg: 362.27 / Max: 362.5Min: 354.13 / Avg: 357.63 / Max: 362.51Min: 404.89 / Avg: 410.46 / Max: 417.52

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, First Run / Cold Cacheamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance90180270360450SE +/- 1.39, N = 3SE +/- 4.76, N = 3SE +/- 0.77, N = 3SE +/- 2.11, N = 3SE +/- 2.12, N = 3SE +/- 0.63, N = 3SE +/- 0.36, N = 3SE +/- 0.46, N = 3SE +/- 1.22, N = 3SE +/- 3.45, N = 3SE +/- 3.06, N = 3355.12395.53339.68392.95252.79394.3266.81297.77351.21351.39393.15MIN: 43.45 / MAX: 4000MIN: 48.98 / MAX: 4000MIN: 39.27 / MAX: 3157.89MIN: 51.28 / MAX: 3750MIN: 43.29 / MAX: 4000MIN: 48.47 / MAX: 3750MIN: 44.15 / MAX: 2068.97MIN: 49.63 / MAX: 4000MIN: 47.54 / MAX: 2857.14MIN: 50.63 / MAX: 3750
OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, First Run / Cold Cacheamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance70140210280350Min: 352.86 / Avg: 355.12 / Max: 357.66Min: 386.1 / Avg: 395.53 / Max: 401.38Min: 338.25 / Avg: 339.68 / Max: 340.88Min: 388.82 / Avg: 392.95 / Max: 395.75Min: 250.54 / Avg: 252.79 / Max: 257.02Min: 393.62 / Avg: 394.32 / Max: 395.57Min: 66.11 / Avg: 66.81 / Max: 67.3Min: 297 / Avg: 297.77 / Max: 298.59Min: 348.77 / Avg: 351.21 / Max: 352.44Min: 344.86 / Avg: 351.39 / Max: 356.56Min: 390.07 / Avg: 393.15 / Max: 399.28

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latencyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance306090120150SE +/- 0.29, N = 3SE +/- 0.30, N = 3SE +/- 0.32, N = 12SE +/- 0.32, N = 4SE +/- 3.77, N = 9SE +/- 0.24, N = 12SE +/- 1.56, N = 12SE +/- 0.33, N = 3SE +/- 0.30, N = 12SE +/- 0.34, N = 3SE +/- 0.37, N = 332.9629.8233.1329.0066.3928.72146.5741.9933.7234.0629.541. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latencyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance306090120150Min: 32.42 / Avg: 32.96 / Max: 33.43Min: 29.38 / Avg: 29.82 / Max: 30.4Min: 31.08 / Avg: 33.13 / Max: 34.76Min: 28.15 / Avg: 29 / Max: 29.71Min: 50.68 / Avg: 66.39 / Max: 79.35Min: 27.73 / Avg: 28.72 / Max: 30.44Min: 133.68 / Avg: 146.57 / Max: 153.34Min: 41.65 / Avg: 41.99 / Max: 42.65Min: 31.6 / Avg: 33.72 / Max: 35.36Min: 33.64 / Avg: 34.06 / Max: 34.74Min: 28.81 / Avg: 29.54 / Max: 30.031. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 800 - Mode: Read Writeamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance6K12K18K24K30KSE +/- 216.59, N = 3SE +/- 272.14, N = 3SE +/- 233.05, N = 12SE +/- 307.60, N = 4SE +/- 766.72, N = 9SE +/- 225.23, N = 12SE +/- 60.47, N = 12SE +/- 148.91, N = 3SE +/- 213.86, N = 12SE +/- 234.54, N = 3SE +/- 343.31, N = 32427526830241732759612397278805465190562374323493270931. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 800 - Mode: Read Writeamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance5K10K15K20K25KMin: 23930.99 / Avg: 24274.61 / Max: 24674.86Min: 26312.27 / Avg: 26830.44 / Max: 27233.79Min: 23016.2 / Avg: 24172.64 / Max: 25741.03Min: 26928.97 / Avg: 27596.08 / Max: 28415.04Min: 10082.58 / Avg: 12397.5 / Max: 15785.1Min: 26278.87 / Avg: 27880.32 / Max: 28855.29Min: 5217.06 / Avg: 5465.16 / Max: 5984.41Min: 18757.88 / Avg: 19055.7 / Max: 19205.96Min: 22624.13 / Avg: 23743.21 / Max: 25317.23Min: 23028.6 / Avg: 23493.41 / Max: 23780.58Min: 26639.03 / Avg: 27092.96 / Max: 27766.071. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

CockroachDB

CockroachDB is a cloud-native, distributed SQL database for data intensive applications. This test profile uses a server-less CockroachDB configuration to test various Coackroach workloads on the local host with a single node. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 95% Reads - Concurrency: 512amd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance20K40K60K80K100KSE +/- 1522.12, N = 15SE +/- 262.84, N = 3SE +/- 99.42, N = 3SE +/- 465.83, N = 3SE +/- 1298.96, N = 15SE +/- 1631.30, N = 15SE +/- 36.89, N = 3SE +/- 1169.53, N = 15SE +/- 1766.85, N = 15SE +/- 1583.45, N = 15SE +/- 373.82, N = 375876.486214.874380.086477.372179.682071.416811.875334.779962.281782.386045.2
OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 95% Reads - Concurrency: 512amd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance15K30K45K60K75KMin: 65816.2 / Avg: 75876.37 / Max: 80529.8Min: 85696.1 / Avg: 86214.83 / Max: 86548Min: 74235.4 / Avg: 74380 / Max: 74570.5Min: 85548.5 / Avg: 86477.33 / Max: 87004.5Min: 61553.5 / Avg: 72179.64 / Max: 75239.6Min: 73063.5 / Avg: 82071.36 / Max: 87887.6Min: 16756.4 / Avg: 16811.8 / Max: 16881.7Min: 63319 / Avg: 75334.7 / Max: 77807.4Min: 71266.1 / Avg: 79962.16 / Max: 87123.7Min: 71074.9 / Avg: 81782.33 / Max: 86539Min: 85407.7 / Avg: 86045.2 / Max: 86702.2

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latencyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance0.35350.7071.06051.4141.7675SE +/- 0.010, N = 11SE +/- 0.003, N = 3SE +/- 0.005, N = 3SE +/- 0.003, N = 3SE +/- 0.025, N = 12SE +/- 0.001, N = 3SE +/- 0.016, N = 6SE +/- 0.020, N = 12SE +/- 0.009, N = 12SE +/- 0.006, N = 3SE +/- 0.005, N = 40.3900.3830.3870.3890.7960.3811.5710.4900.3890.4450.3891. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latencyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance246810Min: 0.37 / Avg: 0.39 / Max: 0.49Min: 0.38 / Avg: 0.38 / Max: 0.39Min: 0.38 / Avg: 0.39 / Max: 0.4Min: 0.38 / Avg: 0.39 / Max: 0.39Min: 0.61 / Avg: 0.8 / Max: 0.85Min: 0.38 / Avg: 0.38 / Max: 0.38Min: 1.52 / Avg: 1.57 / Max: 1.63Min: 0.44 / Avg: 0.49 / Max: 0.62Min: 0.37 / Avg: 0.39 / Max: 0.49Min: 0.43 / Avg: 0.44 / Max: 0.46Min: 0.38 / Avg: 0.39 / Max: 0.41. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 500 - Mode: Read Onlyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance300K600K900K1200K1500KSE +/- 28243.17, N = 11SE +/- 10261.05, N = 3SE +/- 16514.38, N = 3SE +/- 10272.10, N = 3SE +/- 23969.59, N = 12SE +/- 2192.30, N = 3SE +/- 3162.32, N = 6SE +/- 38153.01, N = 12SE +/- 24805.29, N = 12SE +/- 16168.04, N = 3SE +/- 16034.65, N = 41288550130609912927981286042636088131183731848010377031291471112422412859051. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 500 - Mode: Read Onlyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance200K400K600K800K1000KMin: 1011512.28 / Avg: 1288550.12 / Max: 1337863.47Min: 1292535.34 / Avg: 1306099.35 / Max: 1326218.54Min: 1261089.99 / Avg: 1292797.88 / Max: 1316660.03Min: 1268530.43 / Avg: 1286041.69 / Max: 1304101.37Min: 590744.86 / Avg: 636088.42 / Max: 817173.51Min: 1307619.5 / Avg: 1311836.67 / Max: 1314984.56Min: 307689.08 / Avg: 318480.31 / Max: 328709.21Min: 803734.7 / Avg: 1037703.23 / Max: 1137828.29Min: 1029816.65 / Avg: 1291470.78 / Max: 1371525.93Min: 1098431.35 / Avg: 1124224.17 / Max: 1154010.35Min: 1248928.6 / Avg: 1285905.25 / Max: 1326885.651. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3damd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance120240360480600SE +/- 0.99, N = 3SE +/- 1.22, N = 3SE +/- 0.28, N = 3SE +/- 0.44, N = 3SE +/- 0.30, N = 3SE +/- 0.86, N = 3SE +/- 0.43, N = 3SE +/- 0.67, N = 3SE +/- 0.32, N = 3SE +/- 0.74, N = 3SE +/- 0.25, N = 3264.91264.59263.30264.82267.54265.31540.54262.40263.63264.80263.631. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3damd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance100200300400500Min: 263.43 / Avg: 264.91 / Max: 266.78Min: 263.01 / Avg: 264.59 / Max: 267Min: 262.98 / Avg: 263.3 / Max: 263.86Min: 264.29 / Avg: 264.82 / Max: 265.69Min: 266.96 / Avg: 267.54 / Max: 267.97Min: 263.66 / Avg: 265.31 / Max: 266.53Min: 539.75 / Avg: 540.54 / Max: 541.25Min: 261.24 / Avg: 262.4 / Max: 263.57Min: 263.19 / Avg: 263.63 / Max: 264.25Min: 263.44 / Avg: 264.8 / Max: 265.97Min: 263.22 / Avg: 263.63 / Max: 264.081. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

Timed Gem5 Compilation

This test times how long it takes to compile Gem5. Gem5 is a simulator for computer system architecture research. Gem5 is widely used for computer architecture research within the industry, academia, and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 21.2Time To Compileamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance2004006008001000SE +/- 1.30, N = 3SE +/- 1.78, N = 3SE +/- 1.51, N = 8SE +/- 0.95, N = 3SE +/- 1.72, N = 3SE +/- 0.56, N = 3SE +/- 13.66, N = 3SE +/- 1.36, N = 3SE +/- 1.73, N = 3SE +/- 1.68, N = 4SE +/- 0.41, N = 3157.10149.77173.20148.50156.95146.641100.36153.90149.22152.99147.00
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 21.2Time To Compileamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance2004006008001000Min: 154.81 / Avg: 157.1 / Max: 159.31Min: 146.21 / Avg: 149.77 / Max: 151.75Min: 168.09 / Avg: 173.2 / Max: 182.12Min: 146.92 / Avg: 148.5 / Max: 150.19Min: 153.97 / Avg: 156.94 / Max: 159.93Min: 145.56 / Avg: 146.64 / Max: 147.41Min: 1084.2 / Avg: 1100.36 / Max: 1127.52Min: 152.14 / Avg: 153.9 / Max: 156.58Min: 146.17 / Avg: 149.22 / Max: 152.17Min: 149.01 / Avg: 152.99 / Max: 157.18Min: 146.54 / Avg: 147 / Max: 147.83

VP9 libvpx Encoding

This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.13Speed: Speed 5 - Input: Bosphorus 4Kamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance48121620SE +/- 0.12, N = 3SE +/- 0.27, N = 15SE +/- 0.14, N = 15SE +/- 0.41, N = 12SE +/- 0.04, N = 12SE +/- 0.26, N = 15SE +/- 0.01, N = 3SE +/- 0.10, N = 12SE +/- 0.01, N = 3SE +/- 0.12, N = 15SE +/- 0.20, N = 311.6313.377.9512.833.0613.321.868.4714.3610.7214.171. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.13Speed: Speed 5 - Input: Bosphorus 4Kamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance48121620Min: 11.51 / Avg: 11.63 / Max: 11.87Min: 11.68 / Avg: 13.37 / Max: 14.58Min: 7.31 / Avg: 7.95 / Max: 8.78Min: 10.69 / Avg: 12.83 / Max: 14.67Min: 2.81 / Avg: 3.06 / Max: 3.33Min: 11.7 / Avg: 13.32 / Max: 14.77Min: 1.84 / Avg: 1.86 / Max: 1.87Min: 7.85 / Avg: 8.47 / Max: 9.27Min: 14.34 / Avg: 14.36 / Max: 14.37Min: 10.11 / Avg: 10.72 / Max: 11.85Min: 13.9 / Avg: 14.17 / Max: 14.561. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

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 or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: allmodconfigamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance2004006008001000SE +/- 0.78, N = 3SE +/- 0.74, N = 3SE +/- 0.62, N = 3SE +/- 0.76, N = 3SE +/- 1.59, N = 3SE +/- 0.72, N = 3SE +/- 2.74, N = 3SE +/- 1.27, N = 3SE +/- 0.77, N = 3SE +/- 0.85, N = 3SE +/- 0.71, N = 3176.50172.88184.47172.86182.77173.641094.37177.06172.61174.95173.63
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: allmodconfigamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance2004006008001000Min: 175.69 / Avg: 176.49 / Max: 178.06Min: 172.07 / Avg: 172.88 / Max: 174.36Min: 183.23 / Avg: 184.47 / Max: 185.14Min: 171.92 / Avg: 172.86 / Max: 174.35Min: 180.63 / Avg: 182.77 / Max: 185.88Min: 172.78 / Avg: 173.64 / Max: 175.07Min: 1090.21 / Avg: 1094.37 / Max: 1099.53Min: 175.79 / Avg: 177.06 / Max: 179.6Min: 171.78 / Avg: 172.61 / Max: 174.15Min: 174.03 / Avg: 174.95 / Max: 176.65Min: 172.41 / Avg: 173.63 / Max: 174.87

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under The Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 4K - Video Preset: Fastamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance0.91131.82262.73393.64524.5565SE +/- 0.023, N = 3SE +/- 0.011, N = 3SE +/- 0.011, N = 3SE +/- 0.018, N = 3SE +/- 0.009, N = 3SE +/- 0.021, N = 3SE +/- 0.002, N = 3SE +/- 0.009, N = 3SE +/- 0.007, N = 3SE +/- 0.014, N = 3SE +/- 0.005, N = 33.3594.0222.4714.0233.1364.0210.5683.6763.7673.9744.0501. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 4K - Video Preset: Fastamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance246810Min: 3.32 / Avg: 3.36 / Max: 3.39Min: 4.01 / Avg: 4.02 / Max: 4.04Min: 2.46 / Avg: 2.47 / Max: 2.49Min: 4 / Avg: 4.02 / Max: 4.06Min: 3.12 / Avg: 3.14 / Max: 3.15Min: 3.98 / Avg: 4.02 / Max: 4.05Min: 0.56 / Avg: 0.57 / Max: 0.57Min: 3.66 / Avg: 3.68 / Max: 3.69Min: 3.76 / Avg: 3.77 / Max: 3.78Min: 3.95 / Avg: 3.97 / Max: 4Min: 4.04 / Avg: 4.05 / Max: 4.061. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latencyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance0.56751.1351.70252.272.8375SE +/- 0.004, N = 3SE +/- 0.008, N = 3SE +/- 0.001, N = 3SE +/- 0.004, N = 3SE +/- 0.033, N = 12SE +/- 0.005, N = 3SE +/- 0.022, N = 8SE +/- 0.033, N = 12SE +/- 0.001, N = 3SE +/- 0.008, N = 4SE +/- 0.004, N = 30.6410.6440.6420.6451.1460.6302.5220.8150.6360.7450.6481. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latencyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance246810Min: 0.63 / Avg: 0.64 / Max: 0.65Min: 0.63 / Avg: 0.64 / Max: 0.66Min: 0.64 / Avg: 0.64 / Max: 0.64Min: 0.64 / Avg: 0.65 / Max: 0.65Min: 0.97 / Avg: 1.15 / Max: 1.27Min: 0.62 / Avg: 0.63 / Max: 0.64Min: 2.45 / Avg: 2.52 / Max: 2.63Min: 0.73 / Avg: 0.82 / Max: 0.99Min: 0.64 / Avg: 0.64 / Max: 0.64Min: 0.72 / Avg: 0.75 / Max: 0.76Min: 0.64 / Avg: 0.65 / Max: 0.661. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 800 - Mode: Read Onlyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance300K600K900K1200K1500KSE +/- 8403.56, N = 3SE +/- 15062.87, N = 3SE +/- 2388.78, N = 3SE +/- 7684.39, N = 3SE +/- 21438.85, N = 12SE +/- 9347.57, N = 3SE +/- 2702.31, N = 8SE +/- 36540.35, N = 12SE +/- 716.94, N = 3SE +/- 11695.71, N = 4SE +/- 8479.39, N = 3124826612417261245914124040670492912686883173609977421258066107450012348691. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 800 - Mode: Read Onlyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance200K400K600K800K1000KMin: 1232371.43 / Avg: 1248265.81 / Max: 1260944.42Min: 1217811.34 / Avg: 1241725.62 / Max: 1269549.4Min: 1242181.93 / Avg: 1245914.18 / Max: 1250363.24Min: 1225304.65 / Avg: 1240405.83 / Max: 1250429.34Min: 629035.3 / Avg: 704928.6 / Max: 822831.53Min: 1259329.31 / Avg: 1268687.69 / Max: 1287382.82Min: 303886.7 / Avg: 317360.44 / Max: 326197.62Min: 811196.52 / Avg: 997741.59 / Max: 1099792.13Min: 1256810.53 / Avg: 1258065.51 / Max: 1259293.66Min: 1051900.36 / Avg: 1074499.62 / Max: 1107211.29Min: 1218651.05 / Avg: 1234869.03 / Max: 1247271.361. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Stargate Digital Audio Workstation

Stargate is an open-source, cross-platform digital audio workstation (DAW) software package with "a unique and carefully curated experience" with scalability from old systems up through modern multi-core systems. Stargate is GPLv3 licensed and makes use of Qt5 (PyQt5) for its user-interface. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 192000 - Buffer Size: 1024amd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance0.53261.06521.59782.13042.663SE +/- 0.017556, N = 15SE +/- 0.005634, N = 3SE +/- 0.042633, N = 12SE +/- 0.031447, N = 3SE +/- 0.011706, N = 12SE +/- 0.008972, N = 3SE +/- 0.000425, N = 3SE +/- 0.009049, N = 3SE +/- 0.001977, N = 3SE +/- 0.003977, N = 3SE +/- 0.015239, N = 32.0592592.3480791.8012382.3464470.8114182.3630700.3014501.3585492.3461122.3267702.3670741. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 192000 - Buffer Size: 1024amd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance246810Min: 1.95 / Avg: 2.06 / Max: 2.17Min: 2.34 / Avg: 2.35 / Max: 2.36Min: 1.44 / Avg: 1.8 / Max: 1.98Min: 2.29 / Avg: 2.35 / Max: 2.4Min: 0.75 / Avg: 0.81 / Max: 0.89Min: 2.35 / Avg: 2.36 / Max: 2.38Min: 0.3 / Avg: 0.3 / Max: 0.3Min: 1.35 / Avg: 1.36 / Max: 1.38Min: 2.34 / Avg: 2.35 / Max: 2.35Min: 2.32 / Avg: 2.33 / Max: 2.33Min: 2.34 / Avg: 2.37 / Max: 2.391. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latencyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance4080120160200SE +/- 0.45, N = 3SE +/- 0.30, N = 12SE +/- 0.48, N = 3SE +/- 0.31, N = 3SE +/- 4.17, N = 9SE +/- 0.10, N = 3SE +/- 1.19, N = 3SE +/- 0.57, N = 3SE +/- 0.45, N = 12SE +/- 0.32, N = 3SE +/- 0.11, N = 345.5141.1846.4738.3481.1940.16201.1055.9544.3644.8939.601. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latencyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance4080120160200Min: 44.79 / Avg: 45.51 / Max: 46.33Min: 39.28 / Avg: 41.18 / Max: 43.03Min: 45.58 / Avg: 46.47 / Max: 47.24Min: 37.86 / Avg: 38.34 / Max: 38.91Min: 57.51 / Avg: 81.19 / Max: 100.87Min: 40.02 / Avg: 40.16 / Max: 40.36Min: 198.79 / Avg: 201.1 / Max: 202.76Min: 55.38 / Avg: 55.95 / Max: 57.09Min: 41.13 / Avg: 44.36 / Max: 47.55Min: 44.32 / Avg: 44.89 / Max: 45.41Min: 39.38 / Avg: 39.6 / Max: 39.751. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 1000 - Mode: Read Writeamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance6K12K18K24K30KSE +/- 214.70, N = 3SE +/- 174.68, N = 12SE +/- 224.57, N = 3SE +/- 207.97, N = 3SE +/- 734.11, N = 9SE +/- 63.64, N = 3SE +/- 29.56, N = 3SE +/- 179.41, N = 3SE +/- 232.73, N = 12SE +/- 157.83, N = 3SE +/- 72.30, N = 32197824299215222608512613249044973178752256722279252521. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 1000 - Mode: Read Writeamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance5K10K15K20K25KMin: 21586.13 / Avg: 21978.12 / Max: 22325.94Min: 23241.27 / Avg: 24299.43 / Max: 25461.11Min: 21168.85 / Avg: 21522.16 / Max: 21938.98Min: 25700.79 / Avg: 26085.17 / Max: 26414.99Min: 9913.63 / Avg: 12613.18 / Max: 17389.94Min: 24778.84 / Avg: 24903.74 / Max: 24987.42Min: 4931.91 / Avg: 4972.98 / Max: 5030.35Min: 17516.58 / Avg: 17875.39 / Max: 18056.9Min: 21031.42 / Avg: 22566.77 / Max: 24312.99Min: 22021.23 / Avg: 22278.54 / Max: 22565.54Min: 25155.12 / Avg: 25251.78 / Max: 25393.251. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance612182430SE +/- 0.10, N = 15SE +/- 0.07, N = 12SE +/- 0.09, N = 15SE +/- 0.10, N = 15SE +/- 0.11, N = 12SE +/- 0.12, N = 12SE +/- 0.07, N = 3SE +/- 0.10, N = 12SE +/- 0.11, N = 15SE +/- 0.10, N = 15SE +/- 0.04, N = 53.513.453.323.383.553.3924.553.403.413.443.72MIN: 5.27 / MAX: 260.671. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance612182430Min: 2.7 / Avg: 3.51 / Max: 3.89Min: 3.06 / Avg: 3.45 / Max: 3.79Min: 2.82 / Avg: 3.32 / Max: 3.86Min: 2.67 / Avg: 3.38 / Max: 3.83Min: 3.14 / Avg: 3.55 / Max: 4.35Min: 2.75 / Avg: 3.39 / Max: 3.95Min: 24.41 / Avg: 24.55 / Max: 24.63Min: 2.96 / Avg: 3.4 / Max: 4.03Min: 2.68 / Avg: 3.41 / Max: 3.92Min: 2.76 / Avg: 3.44 / Max: 3.88Min: 3.55 / Avg: 3.72 / Max: 3.81. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance8K16K24K32K40KSE +/- 1060.84, N = 15SE +/- 724.32, N = 12SE +/- 894.45, N = 15SE +/- 1139.15, N = 15SE +/- 909.70, N = 12SE +/- 1205.35, N = 12SE +/- 15.51, N = 3SE +/- 946.71, N = 12SE +/- 1216.09, N = 15SE +/- 1008.62, N = 15SE +/- 342.83, N = 535205.4735601.8336975.3436507.1133751.5836428.765175.9635501.2136248.3835666.6932979.741. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance6K12K18K24K30KMin: 31580.26 / Avg: 35205.47 / Max: 44801.41Min: 32282.02 / Avg: 35601.83 / Max: 39561.94Min: 31951.77 / Avg: 36975.34 / Max: 42448.52Min: 32108.08 / Avg: 36507.11 / Max: 44843.56Min: 27711.37 / Avg: 33751.58 / Max: 37370.94Min: 31019.09 / Avg: 36428.76 / Max: 43513.13Min: 5154.41 / Avg: 5175.96 / Max: 5206.06Min: 29986.71 / Avg: 35501.21 / Max: 40179.71Min: 31374.8 / Avg: 36248.38 / Max: 44738.51Min: 31624.57 / Avg: 35666.69 / Max: 43364.73Min: 32429.86 / Avg: 32979.74 / Max: 34319.341. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latencyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance0.72071.44142.16212.88283.6035SE +/- 0.004, N = 3SE +/- 0.005, N = 3SE +/- 0.002, N = 3SE +/- 0.004, N = 3SE +/- 0.040, N = 12SE +/- 0.009, N = 3SE +/- 0.018, N = 3SE +/- 0.048, N = 12SE +/- 0.004, N = 3SE +/- 0.003, N = 3SE +/- 0.006, N = 30.8280.8270.8150.8151.4110.8123.2031.0690.8080.9240.8321. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latencyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance246810Min: 0.82 / Avg: 0.83 / Max: 0.84Min: 0.82 / Avg: 0.83 / Max: 0.84Min: 0.81 / Avg: 0.82 / Max: 0.82Min: 0.81 / Avg: 0.82 / Max: 0.82Min: 1.22 / Avg: 1.41 / Max: 1.6Min: 0.8 / Avg: 0.81 / Max: 0.82Min: 3.17 / Avg: 3.2 / Max: 3.23Min: 0.91 / Avg: 1.07 / Max: 1.32Min: 0.8 / Avg: 0.81 / Max: 0.82Min: 0.92 / Avg: 0.92 / Max: 0.93Min: 0.82 / Avg: 0.83 / Max: 0.841. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 1000 - Mode: Read Onlyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance300K600K900K1200K1500KSE +/- 5837.45, N = 3SE +/- 7063.00, N = 3SE +/- 3162.21, N = 3SE +/- 6415.45, N = 3SE +/- 20475.53, N = 12SE +/- 13365.19, N = 3SE +/- 1792.34, N = 3SE +/- 40789.54, N = 12SE +/- 5317.94, N = 3SE +/- 3711.22, N = 3SE +/- 9650.25, N = 3120754012090331226429122674371498012308413122459559771237871108279412026371. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 1000 - Mode: Read Onlyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance200K400K600K800K1000KMin: 1196205.14 / Avg: 1207539.69 / Max: 1215630.49Min: 1197052.53 / Avg: 1209033.08 / Max: 1221504.68Min: 1220738.41 / Avg: 1226428.77 / Max: 1231664.27Min: 1213912.71 / Avg: 1226742.75 / Max: 1233286.73Min: 626602.84 / Avg: 714980.47 / Max: 822367.15Min: 1214626.39 / Avg: 1230841.47 / Max: 1257352.5Min: 309229.86 / Avg: 312245.23 / Max: 315431.62Min: 756600.7 / Avg: 955976.65 / Max: 1097338.72Min: 1227589.96 / Avg: 1237870.76 / Max: 1245371.28Min: 1076531.86 / Avg: 1082794.07 / Max: 1089375.99Min: 1184175.77 / Avg: 1202636.9 / Max: 1216743.111. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Barbershop - Compute: CPU-Onlyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance2004006008001000SE +/- 0.14, N = 3SE +/- 0.14, N = 3SE +/- 0.33, N = 3SE +/- 0.20, N = 3SE +/- 0.32, N = 3SE +/- 0.10, N = 3SE +/- 0.78, N = 3SE +/- 0.24, N = 3SE +/- 0.28, N = 3SE +/- 0.15, N = 3SE +/- 0.03, N = 3141.79140.18143.04140.36147.46140.35933.41141.91140.55141.98140.45
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Barbershop - Compute: CPU-Onlyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance160320480640800Min: 141.54 / Avg: 141.79 / Max: 142.04Min: 139.91 / Avg: 140.18 / Max: 140.4Min: 142.54 / Avg: 143.04 / Max: 143.65Min: 140.01 / Avg: 140.36 / Max: 140.7Min: 147.06 / Avg: 147.46 / Max: 148.08Min: 140.16 / Avg: 140.35 / Max: 140.47Min: 932.25 / Avg: 933.41 / Max: 934.9Min: 141.63 / Avg: 141.91 / Max: 142.38Min: 139.99 / Avg: 140.55 / Max: 140.93Min: 141.7 / Avg: 141.98 / Max: 142.19Min: 140.4 / Avg: 140.45 / Max: 140.51

CockroachDB

CockroachDB is a cloud-native, distributed SQL database for data intensive applications. This test profile uses a server-less CockroachDB configuration to test various Coackroach workloads on the local host with a single node. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 10% Reads - Concurrency: 512amd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance11K22K33K44K55KSE +/- 451.19, N = 3SE +/- 504.99, N = 3SE +/- 530.33, N = 4SE +/- 207.31, N = 3SE +/- 410.53, N = 15SE +/- 526.94, N = 3SE +/- 162.55, N = 3SE +/- 457.69, N = 6SE +/- 524.19, N = 15SE +/- 590.54, N = 4SE +/- 577.32, N = 344725.550217.243287.249015.541485.549340.411461.445780.347827.049459.949731.9
OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 10% Reads - Concurrency: 512amd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance9K18K27K36K45KMin: 44240.9 / Avg: 44725.47 / Max: 45627Min: 49212.5 / Avg: 50217.23 / Max: 50808.7Min: 41772.2 / Avg: 43287.18 / Max: 44249.3Min: 48626.4 / Avg: 49015.5 / Max: 49334.1Min: 39104.5 / Avg: 41485.45 / Max: 43973.3Min: 48365.8 / Avg: 49340.37 / Max: 50175Min: 11217.5 / Avg: 11461.4 / Max: 11769.5Min: 44496.8 / Avg: 45780.27 / Max: 47230.3Min: 43662.8 / Avg: 47827.05 / Max: 50564.7Min: 47773.5 / Avg: 49459.88 / Max: 50437.9Min: 48577.8 / Avg: 49731.93 / Max: 50338.7

Timed Node.js Compilation

This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 18.8Time To Compileamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance160320480640800SE +/- 0.68, N = 3SE +/- 0.15, N = 3SE +/- 0.22, N = 3SE +/- 0.19, N = 3SE +/- 0.24, N = 3SE +/- 0.08, N = 3SE +/- 0.88, N = 3SE +/- 0.13, N = 3SE +/- 0.23, N = 3SE +/- 0.16, N = 3SE +/- 0.15, N = 3111.95105.53120.48105.83113.13104.93752.99109.81106.47107.14105.54
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 18.8Time To Compileamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance130260390520650Min: 110.75 / Avg: 111.95 / Max: 113.11Min: 105.27 / Avg: 105.53 / Max: 105.79Min: 120.25 / Avg: 120.48 / Max: 120.93Min: 105.48 / Avg: 105.83 / Max: 106.13Min: 112.68 / Avg: 113.13 / Max: 113.51Min: 104.8 / Avg: 104.93 / Max: 105.08Min: 751.96 / Avg: 752.99 / Max: 754.74Min: 109.6 / Avg: 109.81 / Max: 110.05Min: 106.02 / Avg: 106.47 / Max: 106.75Min: 106.96 / Avg: 107.14 / Max: 107.46Min: 105.28 / Avg: 105.54 / Max: 105.8

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Traceramd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance70K140K210K280K350KSE +/- 62.74, N = 3SE +/- 58.85, N = 3SE +/- 90.34, N = 3SE +/- 36.04, N = 3SE +/- 7.42, N = 3SE +/- 83.21, N = 3SE +/- 671.47, N = 3SE +/- 85.87, N = 3SE +/- 70.48, N = 3SE +/- 28.29, N = 3SE +/- 98.82, N = 3417984165041532416864370541588332950418974213042264418591. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Traceramd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance60K120K180K240K300KMin: 41693 / Avg: 41798 / Max: 41910Min: 41533 / Avg: 41650.33 / Max: 41717Min: 41440 / Avg: 41532.33 / Max: 41713Min: 41615 / Avg: 41686.33 / Max: 41731Min: 43696 / Avg: 43705.33 / Max: 43720Min: 41422 / Avg: 41588.33 / Max: 41676Min: 331647 / Avg: 332950 / Max: 333883Min: 41765 / Avg: 41896.67 / Max: 42058Min: 42044 / Avg: 42130.33 / Max: 42270Min: 42209 / Avg: 42264 / Max: 42303Min: 41739 / Avg: 41859 / Max: 420551. (CXX) g++ options: -O3 -lm -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Traceramd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance15K30K45K60K75KSE +/- 0.58, N = 3SE +/- 2.03, N = 3SE +/- 0.88, N = 3SE +/- 2.08, N = 3SE +/- 1.15, N = 3SE +/- 1.45, N = 3SE +/- 831.01, N = 12SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 2.19, N = 3SE +/- 1.45, N = 31304129913031302137613006854813221306132213061. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Traceramd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance12K24K36K48K60KMin: 1303 / Avg: 1304 / Max: 1305Min: 1296 / Avg: 1299.33 / Max: 1303Min: 1302 / Avg: 1303.33 / Max: 1305Min: 1298 / Avg: 1302 / Max: 1305Min: 1374 / Avg: 1376 / Max: 1378Min: 1297 / Avg: 1299.67 / Max: 1302Min: 64005 / Avg: 68547.92 / Max: 72464Min: 1321 / Avg: 1322.33 / Max: 1323Min: 1305 / Avg: 1306.33 / Max: 1307Min: 1318 / Avg: 1322.33 / Max: 1325Min: 1304 / Avg: 1306.33 / Max: 13091. (CXX) g++ options: -O3 -lm -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Traceramd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance14K28K42K56K70KSE +/- 1.20, N = 3SE +/- 1.33, N = 3SE +/- 0.67, N = 3SE +/- 0.88, N = 3SE +/- 0.88, N = 3SE +/- 1.15, N = 3SE +/- 875.42, N = 12SE +/- 2.03, N = 3SE +/- 2.85, N = 3SE +/- 1.20, N = 3SE +/- 1.00, N = 31101110311021101116610986700011181103112011041. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Traceramd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance12K24K36K48K60KMin: 1099 / Avg: 1101.33 / Max: 1103Min: 1100 / Avg: 1102.67 / Max: 1104Min: 1101 / Avg: 1101.67 / Max: 1103Min: 1100 / Avg: 1101.33 / Max: 1103Min: 1164 / Avg: 1165.67 / Max: 1167Min: 1096 / Avg: 1098 / Max: 1100Min: 62673 / Avg: 67000.17 / Max: 70922Min: 1115 / Avg: 1118.33 / Max: 1122Min: 1097 / Avg: 1102.67 / Max: 1106Min: 1118 / Avg: 1119.67 / Max: 1122Min: 1103 / Avg: 1104 / Max: 11061. (CXX) g++ options: -O3 -lm -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Traceramd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance60K120K180K240K300KSE +/- 29.34, N = 3SE +/- 76.22, N = 3SE +/- 69.50, N = 3SE +/- 31.26, N = 3SE +/- 66.07, N = 3SE +/- 23.07, N = 3SE +/- 829.19, N = 3SE +/- 52.33, N = 3SE +/- 88.76, N = 3SE +/- 25.51, N = 3SE +/- 117.33, N = 3354383557335243352103697635186291743354403550535628354061. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Traceramd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance50K100K150K200K250KMin: 35380 / Avg: 35438.33 / Max: 35473Min: 35431 / Avg: 35573 / Max: 35692Min: 35109 / Avg: 35243 / Max: 35342Min: 35172 / Avg: 35210 / Max: 35272Min: 36894 / Avg: 36976.33 / Max: 37107Min: 35141 / Avg: 35185.67 / Max: 35218Min: 290491 / Avg: 291743.33 / Max: 293311Min: 35376 / Avg: 35440.33 / Max: 35544Min: 35343 / Avg: 35504.67 / Max: 35649Min: 35577 / Avg: 35628 / Max: 35655Min: 35233 / Avg: 35406.33 / Max: 356301. (CXX) g++ options: -O3 -lm -ldl

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance70140210280350SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 1.86, N = 15SE +/- 0.02, N = 3SE +/- 2.16, N = 15SE +/- 2.27, N = 12SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 317.4917.4117.5317.3732.4217.37315.2635.3917.4417.6517.48MIN: 86.78 / MAX: 701.541. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance60120180240300Min: 17.46 / Avg: 17.49 / Max: 17.5Min: 17.37 / Avg: 17.41 / Max: 17.46Min: 17.45 / Avg: 17.53 / Max: 17.58Min: 17.34 / Avg: 17.37 / Max: 17.4Min: 24.65 / Avg: 32.42 / Max: 42.96Min: 17.33 / Avg: 17.37 / Max: 17.4Min: 294.81 / Avg: 315.26 / Max: 326.9Min: 22.03 / Avg: 35.39 / Max: 43.49Min: 17.41 / Avg: 17.44 / Max: 17.51Min: 17.58 / Avg: 17.65 / Max: 17.78Min: 17.45 / Avg: 17.48 / Max: 17.531. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance8001600240032004000SE +/- 3.07, N = 3SE +/- 6.01, N = 3SE +/- 8.08, N = 3SE +/- 3.54, N = 3SE +/- 113.70, N = 15SE +/- 4.65, N = 3SE +/- 1.43, N = 15SE +/- 155.56, N = 12SE +/- 6.58, N = 3SE +/- 13.56, N = 3SE +/- 4.78, N = 33654.513670.783645.603679.312062.043678.91202.831915.373663.483621.583655.411. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance6001200180024003000Min: 3651.27 / Avg: 3654.51 / Max: 3660.64Min: 3659.09 / Avg: 3670.78 / Max: 3679.06Min: 3634.61 / Avg: 3645.6 / Max: 3661.36Min: 3672.63 / Avg: 3679.31 / Max: 3684.68Min: 1487.91 / Avg: 2062.04 / Max: 2592.55Min: 3673.37 / Avg: 3678.91 / Max: 3688.14Min: 195.54 / Avg: 202.83 / Max: 216.79Min: 1470.06 / Avg: 1915.37 / Max: 2901.75Min: 3650.33 / Avg: 3663.48 / Max: 3670.27Min: 3594.46 / Avg: 3621.58 / Max: 3635.52Min: 3646.2 / Avg: 3655.41 / Max: 3662.231. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under The Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 4K - Video Preset: Fasteramd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance246810SE +/- 0.045, N = 3SE +/- 0.075, N = 3SE +/- 0.018, N = 3SE +/- 0.083, N = 4SE +/- 0.049, N = 3SE +/- 0.084, N = 4SE +/- 0.008, N = 3SE +/- 0.030, N = 3SE +/- 0.068, N = 3SE +/- 0.043, N = 3SE +/- 0.075, N = 36.3267.3974.7697.3526.2307.3061.1576.6467.3477.3737.3201. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 4K - Video Preset: Fasteramd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance3691215Min: 6.24 / Avg: 6.33 / Max: 6.39Min: 7.3 / Avg: 7.4 / Max: 7.54Min: 4.75 / Avg: 4.77 / Max: 4.8Min: 7.14 / Avg: 7.35 / Max: 7.54Min: 6.14 / Avg: 6.23 / Max: 6.31Min: 7.08 / Avg: 7.31 / Max: 7.47Min: 1.14 / Avg: 1.16 / Max: 1.17Min: 6.6 / Avg: 6.65 / Max: 6.7Min: 7.21 / Avg: 7.35 / Max: 7.43Min: 7.31 / Avg: 7.37 / Max: 7.45Min: 7.18 / Avg: 7.32 / Max: 7.441. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto

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 or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfigamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance306090120150SE +/- 0.16, N = 13SE +/- 0.15, N = 13SE +/- 0.24, N = 13SE +/- 0.14, N = 15SE +/- 0.23, N = 14SE +/- 0.18, N = 10SE +/- 1.30, N = 9SE +/- 0.21, N = 15SE +/- 0.14, N = 13SE +/- 0.17, N = 14SE +/- 0.14, N = 1325.5222.6230.8322.5325.3922.52156.7824.5222.6123.4422.65
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfigamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance306090120150Min: 25.19 / Avg: 25.52 / Max: 27.46Min: 22.32 / Avg: 22.62 / Max: 24.38Min: 30.14 / Avg: 30.83 / Max: 33.56Min: 22.18 / Avg: 22.53 / Max: 24.41Min: 24.82 / Avg: 25.39 / Max: 28.24Min: 22.22 / Avg: 22.52 / Max: 24.09Min: 154.96 / Avg: 156.78 / Max: 167.16Min: 24.15 / Avg: 24.52 / Max: 27.5Min: 22.41 / Avg: 22.61 / Max: 24.32Min: 23.13 / Avg: 23.44 / Max: 25.67Min: 22.43 / Avg: 22.65 / Max: 24.31

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Execution Timeamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance170340510680850167.41170.71169.25167.82182.44168.80773.03167.90166.48169.00164.041. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Mesh Timeamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance170340510680850116.05114.87116.28116.19127.86116.11773.97119.63116.44120.10115.761. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

CockroachDB

CockroachDB is a cloud-native, distributed SQL database for data intensive applications. This test profile uses a server-less CockroachDB configuration to test various Coackroach workloads on the local host with a single node. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: MoVR - Concurrency: 512amd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance170340510680850SE +/- 2.27, N = 3SE +/- 1.59, N = 3SE +/- 1.71, N = 3SE +/- 2.65, N = 3SE +/- 2.51, N = 15SE +/- 1.79, N = 3SE +/- 0.42, N = 3SE +/- 4.45, N = 3SE +/- 0.92, N = 3SE +/- 3.24, N = 3SE +/- 3.30, N = 3641.8761.0570.5763.4195.9766.8126.8574.8438.2698.0765.2
OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: MoVR - Concurrency: 512amd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance130260390520650Min: 638.4 / Avg: 641.8 / Max: 646.1Min: 758.9 / Avg: 760.97 / Max: 764.1Min: 567.2 / Avg: 570.5 / Max: 572.9Min: 760.3 / Avg: 763.43 / Max: 768.7Min: 183.8 / Avg: 195.89 / Max: 217.5Min: 764.1 / Avg: 766.83 / Max: 770.2Min: 126 / Avg: 126.8 / Max: 127.4Min: 566 / Avg: 574.77 / Max: 580.5Min: 436.6 / Avg: 438.23 / Max: 439.8Min: 693.2 / Avg: 698.03 / Max: 704.2Min: 759.3 / Avg: 765.2 / Max: 770.7

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 500amd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance30K60K90K120K150KSE +/- 1575.56, N = 5SE +/- 1361.88, N = 3SE +/- 1620.42, N = 5SE +/- 2024.19, N = 3SE +/- 115.95, N = 3SE +/- 684.93, N = 3SE +/- 131.35, N = 3SE +/- 208.90, N = 3SE +/- 1781.93, N = 4SE +/- 977.04, N = 3SE +/- 693.20, N = 3146738.16147764.25145614.76152654.86138510.00151325.0127774.70122126.56146083.16149876.52147285.781. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 500amd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance30K60K90K120K150KMin: 143546.24 / Avg: 146738.16 / Max: 152707.13Min: 145140.31 / Avg: 147764.25 / Max: 149708.97Min: 143048.93 / Avg: 145614.76 / Max: 152019.23Min: 149581.94 / Avg: 152654.86 / Max: 156473.84Min: 138287.27 / Avg: 138510 / Max: 138677.28Min: 150609.95 / Avg: 151325.01 / Max: 152694.43Min: 27525.23 / Avg: 27774.7 / Max: 27970.74Min: 121730.88 / Avg: 122126.56 / Max: 122440.56Min: 143269.99 / Avg: 146083.16 / Max: 151306Min: 148103.53 / Avg: 149876.52 / Max: 151474.48Min: 146251.12 / Avg: 147285.78 / Max: 148602.291. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance20406080100SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 2.29, N = 12SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 3.03, N = 15SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 317.1017.0617.1417.0746.4917.05107.1736.3517.0917.3317.09MIN: 9.33 / MAX: 84.63MIN: 9.02 / MAX: 83.41MIN: 9.37 / MAX: 88.86MIN: 8.56 / MAX: 80.26MIN: 8.5 / MAX: 147.24MIN: 9.39 / MAX: 80.76MIN: 59.84 / MAX: 344.36MIN: 7.98 / MAX: 137.61MIN: 9.24 / MAX: 81.88MIN: 9.07 / MAX: 83.28MIN: 9.82 / MAX: 80.611. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance20406080100Min: 17.09 / Avg: 17.1 / Max: 17.11Min: 17.06 / Avg: 17.06 / Max: 17.06Min: 17.13 / Avg: 17.14 / Max: 17.14Min: 17.07 / Avg: 17.07 / Max: 17.08Min: 32.29 / Avg: 46.49 / Max: 55.33Min: 17.05 / Avg: 17.05 / Max: 17.06Min: 107.13 / Avg: 107.17 / Max: 107.23Min: 20.44 / Avg: 36.35 / Max: 52.56Min: 17.08 / Avg: 17.09 / Max: 17.1Min: 17.32 / Avg: 17.33 / Max: 17.34Min: 17.09 / Avg: 17.09 / Max: 17.091. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance8001600240032004000SE +/- 1.15, N = 3SE +/- 0.22, N = 3SE +/- 0.85, N = 3SE +/- 0.90, N = 3SE +/- 78.31, N = 12SE +/- 1.03, N = 3SE +/- 0.14, N = 3SE +/- 176.75, N = 15SE +/- 1.38, N = 3SE +/- 1.17, N = 3SE +/- 0.08, N = 33738.043748.173730.663744.851416.773749.69596.041960.303741.063689.973741.351. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance7001400210028003500Min: 3736.41 / Avg: 3738.04 / Max: 3740.27Min: 3747.73 / Avg: 3748.17 / Max: 3748.4Min: 3729.46 / Avg: 3730.66 / Max: 3732.31Min: 3743.11 / Avg: 3744.85 / Max: 3746.13Min: 1155.17 / Avg: 1416.77 / Max: 1979.72Min: 3747.65 / Avg: 3749.69 / Max: 3750.98Min: 595.77 / Avg: 596.04 / Max: 596.21Min: 1216.01 / Avg: 1960.3 / Max: 3128Min: 3739.49 / Avg: 3741.06 / Max: 3743.81Min: 3687.64 / Avg: 3689.97 / Max: 3691.18Min: 3741.23 / Avg: 3741.35 / Max: 3741.51. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance30060090012001500SE +/- 0.82, N = 3SE +/- 1.09, N = 3SE +/- 0.51, N = 3SE +/- 2.12, N = 3SE +/- 0.48, N = 3SE +/- 0.54, N = 3SE +/- 7.94, N = 15SE +/- 0.15, N = 3SE +/- 1.21, N = 3SE +/- 1.01, N = 3SE +/- 0.97, N = 3239.05239.29238.16239.70240.82239.021229.86228.75239.94241.17238.32MIN: 599.82 / MAX: 5117.071. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance2004006008001000Min: 237.76 / Avg: 239.05 / Max: 240.57Min: 237.4 / Avg: 239.29 / Max: 241.16Min: 237.48 / Avg: 238.16 / Max: 239.15Min: 236.55 / Avg: 239.7 / Max: 243.74Min: 240.15 / Avg: 240.82 / Max: 241.76Min: 238.4 / Avg: 239.02 / Max: 240.09Min: 1176.44 / Avg: 1229.86 / Max: 1279.81Min: 228.48 / Avg: 228.75 / Max: 228.98Min: 238.53 / Avg: 239.94 / Max: 242.35Min: 239.16 / Avg: 241.17 / Max: 242.32Min: 236.76 / Avg: 238.32 / Max: 240.111. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance60120180240300SE +/- 1.00, N = 3SE +/- 1.18, N = 3SE +/- 0.60, N = 3SE +/- 2.34, N = 3SE +/- 0.47, N = 3SE +/- 0.60, N = 3SE +/- 0.34, N = 15SE +/- 0.14, N = 3SE +/- 1.35, N = 3SE +/- 1.08, N = 3SE +/- 1.06, N = 3267.15266.96268.24266.56265.31267.3051.52279.33266.14264.82268.041. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance50100150200250Min: 265.28 / Avg: 267.15 / Max: 268.71Min: 264.92 / Avg: 266.96 / Max: 269Min: 267.08 / Avg: 268.24 / Max: 269.07Min: 262.12 / Avg: 266.56 / Max: 270.07Min: 264.41 / Avg: 265.31 / Max: 266.02Min: 266.12 / Avg: 267.3 / Max: 268.08Min: 49.48 / Avg: 51.52 / Max: 53.98Min: 279.13 / Avg: 279.33 / Max: 279.59Min: 263.47 / Avg: 266.14 / Max: 267.76Min: 263.56 / Avg: 264.82 / Max: 266.98Min: 266.1 / Avg: 268.04 / Max: 269.741. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance2004006008001000SE +/- 0.17, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.11, N = 3SE +/- 0.01, N = 3SE +/- 1.11, N = 3SE +/- 0.25, N = 3SE +/- 0.09, N = 3SE +/- 0.31, N = 3SE +/- 0.17, N = 3205.68205.42205.70205.30212.63205.411124.30206.14205.49206.45205.28
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance2004006008001000Min: 205.37 / Avg: 205.68 / Max: 205.96Min: 205.34 / Avg: 205.42 / Max: 205.48Min: 205.61 / Avg: 205.7 / Max: 205.8Min: 205.14 / Avg: 205.3 / Max: 205.48Min: 212.42 / Avg: 212.63 / Max: 212.8Min: 205.39 / Avg: 205.41 / Max: 205.42Min: 1122.14 / Avg: 1124.3 / Max: 1125.79Min: 205.86 / Avg: 206.14 / Max: 206.64Min: 205.38 / Avg: 205.49 / Max: 205.68Min: 205.83 / Avg: 206.45 / Max: 206.77Min: 205.07 / Avg: 205.28 / Max: 205.62

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance70140210280350SE +/- 0.30, N = 3SE +/- 0.12, N = 3SE +/- 0.37, N = 3SE +/- 0.15, N = 3SE +/- 0.24, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.48, N = 3SE +/- 0.24, N = 3SE +/- 0.62, N = 3SE +/- 0.30, N = 3310.30310.43309.38310.74299.57310.3056.66309.60310.09308.68310.61
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance60120180240300Min: 309.69 / Avg: 310.3 / Max: 310.63Min: 310.2 / Avg: 310.43 / Max: 310.56Min: 308.9 / Avg: 309.38 / Max: 310.11Min: 310.57 / Avg: 310.74 / Max: 311.04Min: 299.27 / Avg: 299.57 / Max: 300.05Min: 310.14 / Avg: 310.3 / Max: 310.4Min: 56.55 / Avg: 56.66 / Max: 56.76Min: 308.65 / Avg: 309.6 / Max: 310.19Min: 309.78 / Avg: 310.09 / Max: 310.56Min: 308.04 / Avg: 308.68 / Max: 309.92Min: 310.02 / Avg: 310.61 / Max: 310.91

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Decompression Speedamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance30060090012001500SE +/- 1.23, N = 3SE +/- 7.42, N = 3SE +/- 20.88, N = 3SE +/- 5.97, N = 3SE +/- 1.07, N = 3SE +/- 18.37, N = 3SE +/- 0.15, N = 3SE +/- 11.54, N = 3SE +/- 9.03, N = 3SE +/- 11.09, N = 3SE +/- 7.61, N = 31195.01203.61186.01203.31191.51171.2140.11178.01203.21203.21209.11. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Decompression Speedamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance2004006008001000Min: 1193.4 / Avg: 1194.97 / Max: 1197.4Min: 1194.6 / Avg: 1203.57 / Max: 1218.3Min: 1147.3 / Avg: 1186.03 / Max: 1218.9Min: 1196.2 / Avg: 1203.33 / Max: 1215.2Min: 1189.4 / Avg: 1191.53 / Max: 1192.7Min: 1134.5 / Avg: 1171.2 / Max: 1190.9Min: 139.9 / Avg: 140.13 / Max: 140.4Min: 1156.5 / Avg: 1178.03 / Max: 1196Min: 1194 / Avg: 1203.23 / Max: 1221.3Min: 1189.8 / Avg: 1203.2 / Max: 1225.2Min: 1194 / Avg: 1209.1 / Max: 1218.31. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Compression Speedamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance3691215SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.12, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.11, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.10, N = 38.919.288.729.269.209.311.069.139.299.219.121. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Compression Speedamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance3691215Min: 8.79 / Avg: 8.91 / Max: 9Min: 9.27 / Avg: 9.28 / Max: 9.29Min: 8.49 / Avg: 8.72 / Max: 8.89Min: 9.22 / Avg: 9.26 / Max: 9.29Min: 9.18 / Avg: 9.2 / Max: 9.22Min: 9.28 / Avg: 9.31 / Max: 9.34Min: 1.05 / Avg: 1.06 / Max: 1.07Min: 8.91 / Avg: 9.13 / Max: 9.24Min: 9.28 / Avg: 9.29 / Max: 9.29Min: 9.17 / Avg: 9.21 / Max: 9.25Min: 8.94 / Avg: 9.12 / Max: 9.271. (CC) gcc options: -O3 -pthread -lz -llzma

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance60120180240300SE +/- 0.28, N = 3SE +/- 0.18, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.11, N = 368.9268.7168.5668.5871.1668.65295.4968.6068.5568.7168.77
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance50100150200250Min: 68.61 / Avg: 68.92 / Max: 69.49Min: 68.51 / Avg: 68.71 / Max: 69.07Min: 68.5 / Avg: 68.56 / Max: 68.65Min: 68.39 / Avg: 68.58 / Max: 68.72Min: 71.07 / Avg: 71.16 / Max: 71.25Min: 68.51 / Avg: 68.65 / Max: 68.8Min: 295.36 / Avg: 295.49 / Max: 295.58Min: 68.57 / Avg: 68.6 / Max: 68.62Min: 68.48 / Avg: 68.55 / Max: 68.64Min: 68.55 / Avg: 68.71 / Max: 68.84Min: 68.59 / Avg: 68.76 / Max: 68.96

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance2004006008001000SE +/- 3.90, N = 3SE +/- 2.48, N = 3SE +/- 0.75, N = 3SE +/- 1.42, N = 3SE +/- 0.59, N = 3SE +/- 1.11, N = 3SE +/- 0.06, N = 3SE +/- 0.27, N = 3SE +/- 0.68, N = 3SE +/- 1.23, N = 3SE +/- 1.66, N = 3926.20929.79931.60931.58897.64930.49215.52931.20932.00929.79928.54
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance160320480640800Min: 918.43 / Avg: 926.2 / Max: 930.65Min: 924.84 / Avg: 929.79 / Max: 932.5Min: 930.1 / Avg: 931.6 / Max: 932.38Min: 929.67 / Avg: 931.58 / Max: 934.36Min: 896.51 / Avg: 897.64 / Max: 898.5Min: 928.49 / Avg: 930.49 / Max: 932.32Min: 215.41 / Avg: 215.52 / Max: 215.61Min: 930.67 / Avg: 931.2 / Max: 931.56Min: 930.69 / Avg: 932 / Max: 932.99Min: 928.08 / Avg: 929.79 / Max: 932.18Min: 925.56 / Avg: 928.54 / Max: 931.32

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance5K10K15K20K25KSE +/- 4.72, N = 3SE +/- 8.61, N = 3SE +/- 6.67, N = 3SE +/- 9.11, N = 3SE +/- 8.81, N = 3SE +/- 4.79, N = 3SE +/- 217.31, N = 3SE +/- 15.80, N = 3SE +/- 5.84, N = 3SE +/- 2.84, N = 3SE +/- 4.16, N = 34030.034015.914033.634005.034262.294030.7924236.974103.644054.304041.314032.10MIN: 18903.29 / MAX: 30172.21. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance4K8K12K16K20KMin: 4022.66 / Avg: 4030.03 / Max: 4038.82Min: 3998.98 / Avg: 4015.91 / Max: 4027.1Min: 4021.66 / Avg: 4033.63 / Max: 4044.71Min: 3988.68 / Avg: 4005.03 / Max: 4020.18Min: 4244.76 / Avg: 4262.29 / Max: 4272.67Min: 4022.12 / Avg: 4030.79 / Max: 4038.67Min: 23895.19 / Avg: 24236.97 / Max: 24640.38Min: 4081.47 / Avg: 4103.64 / Max: 4134.22Min: 4045.8 / Avg: 4054.3 / Max: 4065.48Min: 4037.45 / Avg: 4041.31 / Max: 4046.85Min: 4023.78 / Avg: 4032.1 / Max: 4036.481. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance48121620SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 315.5215.5415.5015.5514.6315.522.5415.2415.4115.4415.491. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance48121620Min: 15.49 / Avg: 15.52 / Max: 15.56Min: 15.52 / Avg: 15.54 / Max: 15.59Min: 15.47 / Avg: 15.5 / Max: 15.55Min: 15.52 / Avg: 15.55 / Max: 15.6Min: 14.57 / Avg: 14.63 / Max: 14.72Min: 15.49 / Avg: 15.52 / Max: 15.55Min: 2.52 / Avg: 2.54 / Max: 2.56Min: 15.12 / Avg: 15.24 / Max: 15.34Min: 15.34 / Avg: 15.41 / Max: 15.45Min: 15.39 / Avg: 15.44 / Max: 15.49Min: 15.46 / Avg: 15.49 / Max: 15.521. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance7001400210028003500SE +/- 0.37, N = 3SE +/- 0.13, N = 3SE +/- 0.15, N = 3SE +/- 0.23, N = 3SE +/- 0.38, N = 3SE +/- 0.41, N = 3SE +/- 0.92, N = 3SE +/- 0.30, N = 3SE +/- 0.24, N = 3SE +/- 0.20, N = 3SE +/- 0.22, N = 3587.74587.84587.78587.61605.67586.863485.21589.69587.78588.61587.38
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance6001200180024003000Min: 587 / Avg: 587.74 / Max: 588.12Min: 587.61 / Avg: 587.84 / Max: 588.06Min: 587.5 / Avg: 587.78 / Max: 587.98Min: 587.21 / Avg: 587.61 / Max: 588Min: 604.95 / Avg: 605.67 / Max: 606.24Min: 586.08 / Avg: 586.86 / Max: 587.46Min: 3483.58 / Avg: 3485.21 / Max: 3486.75Min: 589.1 / Avg: 589.69 / Max: 590.03Min: 587.31 / Avg: 587.78 / Max: 588.1Min: 588.22 / Avg: 588.61 / Max: 588.82Min: 586.94 / Avg: 587.38 / Max: 587.64

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance20406080100SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 3SE +/- 0.20, N = 3SE +/- 0.00, N = 3SE +/- 0.18, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3108.20108.20108.15108.11104.89108.4018.20107.47108.13107.90108.16
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance20406080100Min: 108.14 / Avg: 108.2 / Max: 108.23Min: 108.13 / Avg: 108.2 / Max: 108.26Min: 108.14 / Avg: 108.15 / Max: 108.16Min: 107.93 / Avg: 108.11 / Max: 108.25Min: 104.79 / Avg: 104.89 / Max: 105Min: 108.19 / Avg: 108.4 / Max: 108.8Min: 18.2 / Avg: 18.2 / Max: 18.21Min: 107.16 / Avg: 107.47 / Max: 107.78Min: 108.1 / Avg: 108.13 / Max: 108.17Min: 107.85 / Avg: 107.9 / Max: 107.95Min: 108.11 / Avg: 108.16 / Max: 108.19

7-Zip Compression

This is a test of 7-Zip compression/decompression with its integrated benchmark feature. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression Ratingamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance160K320K480K640K800KSE +/- 858.55, N = 3SE +/- 18690.79, N = 3SE +/- 5960.12, N = 3SE +/- 10875.45, N = 4SE +/- 2716.47, N = 7SE +/- 2158.20, N = 3SE +/- 136.02, N = 3SE +/- 1773.36, N = 3SE +/- 156.12, N = 3SE +/- 1725.95, N = 3SE +/- 2437.88, N = 67167037265216614207338826992287463761042877390167485497400397429551. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression Ratingamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance130K260K390K520K650KMin: 715147 / Avg: 716702.67 / Max: 718110Min: 689487 / Avg: 726520.67 / Max: 749444Min: 651474 / Avg: 661419.67 / Max: 672083Min: 701516 / Avg: 733882.25 / Max: 747274Min: 686484 / Avg: 699228.14 / Max: 706369Min: 742205 / Avg: 746376.33 / Max: 749423Min: 104016 / Avg: 104287.33 / Max: 104440Min: 737017 / Avg: 739016.33 / Max: 742553Min: 748292 / Avg: 748548.67 / Max: 748831Min: 737871 / Avg: 740038.67 / Max: 743449Min: 736895 / Avg: 742954.83 / Max: 7528481. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression Ratingamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance110K220K330K440K550KSE +/- 480.40, N = 3SE +/- 5053.05, N = 3SE +/- 3758.30, N = 3SE +/- 5870.22, N = 4SE +/- 3670.50, N = 7SE +/- 6313.35, N = 3SE +/- 1055.88, N = 3SE +/- 2092.51, N = 3SE +/- 3716.48, N = 3SE +/- 6757.49, N = 3SE +/- 5372.93, N = 65004715223484596175144433949825306891009704853874758615070395282891. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression Ratingamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance90K180K270K360K450KMin: 499741 / Avg: 500471 / Max: 501377Min: 512826 / Avg: 522348.33 / Max: 530041Min: 452477 / Avg: 459616.67 / Max: 465222Min: 497431 / Avg: 514443.25 / Max: 522620Min: 383607 / Avg: 394982.14 / Max: 413853Min: 519608 / Avg: 530689 / Max: 541472Min: 99190 / Avg: 100969.67 / Max: 102844Min: 482324 / Avg: 485386.67 / Max: 489388Min: 468854 / Avg: 475861.33 / Max: 481512Min: 497003 / Avg: 507039 / Max: 519896Min: 513023 / Avg: 528289.17 / Max: 5529631. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance10002000300040005000SE +/- 0.37, N = 3SE +/- 0.32, N = 3SE +/- 0.34, N = 3SE +/- 0.36, N = 3SE +/- 0.52, N = 3SE +/- 0.55, N = 3SE +/- 3.96, N = 3SE +/- 0.23, N = 3SE +/- 0.13, N = 3SE +/- 0.08, N = 3SE +/- 0.34, N = 3869.22868.87868.92868.26895.13867.904864.70876.50868.82872.89869.19
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance8001600240032004000Min: 868.8 / Avg: 869.22 / Max: 869.96Min: 868.52 / Avg: 868.87 / Max: 869.51Min: 868.57 / Avg: 868.92 / Max: 869.61Min: 867.55 / Avg: 868.26 / Max: 868.69Min: 894.17 / Avg: 895.13 / Max: 895.94Min: 867.23 / Avg: 867.9 / Max: 868.99Min: 4857.47 / Avg: 4864.7 / Max: 4871.11Min: 876.23 / Avg: 876.5 / Max: 876.95Min: 868.57 / Avg: 868.82 / Max: 868.99Min: 872.75 / Avg: 872.89 / Max: 873.02Min: 868.6 / Avg: 869.19 / Max: 869.76

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance1632486480SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.14, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 372.8572.9572.8073.0670.7572.9112.9772.5273.1072.7773.16
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance1428425670Min: 72.78 / Avg: 72.85 / Max: 72.88Min: 72.9 / Avg: 72.95 / Max: 73.01Min: 72.75 / Avg: 72.8 / Max: 72.85Min: 72.79 / Avg: 73.06 / Max: 73.21Min: 70.57 / Avg: 70.75 / Max: 70.88Min: 72.85 / Avg: 72.91 / Max: 72.97Min: 12.96 / Avg: 12.97 / Max: 12.98Min: 72.46 / Avg: 72.52 / Max: 72.55Min: 72.89 / Avg: 73.1 / Max: 73.27Min: 72.69 / Avg: 72.77 / Max: 72.87Min: 73.04 / Avg: 73.16 / Max: 73.25

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Decompression Speedamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance30060090012001500SE +/- 3.84, N = 5SE +/- 4.93, N = 3SE +/- 2.19, N = 3SE +/- 6.13, N = 3SE +/- 1.88, N = 3SE +/- 28.63, N = 3SE +/- 0.03, N = 3SE +/- 5.25, N = 3SE +/- 2.01, N = 3SE +/- 1.32, N = 3SE +/- 0.97, N = 31278.31278.61269.81276.21261.81188.1146.11280.51270.91264.71272.81. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Decompression Speedamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance2004006008001000Min: 1267.4 / Avg: 1278.32 / Max: 1287.5Min: 1273.6 / Avg: 1278.63 / Max: 1288.5Min: 1266.1 / Avg: 1269.83 / Max: 1273.7Min: 1267.8 / Avg: 1276.17 / Max: 1288.1Min: 1258.2 / Avg: 1261.83 / Max: 1264.5Min: 1154.8 / Avg: 1188.1 / Max: 1245.1Min: 146 / Avg: 146.07 / Max: 146.1Min: 1270.1 / Avg: 1280.53 / Max: 1286.8Min: 1267.7 / Avg: 1270.9 / Max: 1274.6Min: 1262.1 / Avg: 1264.73 / Max: 1266.3Min: 1271.6 / Avg: 1272.77 / Max: 1274.71. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Compression Speedamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance48121620SE +/- 0.16, N = 5SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 316.0017.6015.2017.5017.1017.601.9717.2017.4017.5017.501. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Compression Speedamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance48121620Min: 15.4 / Avg: 16.04 / Max: 16.3Min: 17.5 / Avg: 17.57 / Max: 17.6Min: 15.2 / Avg: 15.23 / Max: 15.3Min: 17.5 / Avg: 17.5 / Max: 17.5Min: 17 / Avg: 17.13 / Max: 17.3Min: 17.5 / Avg: 17.57 / Max: 17.6Min: 1.95 / Avg: 1.97 / Max: 1.98Min: 17.1 / Avg: 17.23 / Max: 17.3Min: 17.2 / Avg: 17.4 / Max: 17.5Min: 17.4 / Avg: 17.5 / Max: 17.6Min: 17.4 / Avg: 17.47 / Max: 17.61. (CC) gcc options: -O3 -pthread -lz -llzma

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance10002000300040005000SE +/- 0.33, N = 3SE +/- 0.23, N = 3SE +/- 0.24, N = 3SE +/- 0.76, N = 3SE +/- 0.79, N = 3SE +/- 0.10, N = 3SE +/- 2.96, N = 3SE +/- 0.56, N = 3SE +/- 0.11, N = 3SE +/- 0.15, N = 3SE +/- 0.69, N = 3868.08867.93867.02866.98893.43866.964868.11876.33866.62872.07867.83
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance8001600240032004000Min: 867.61 / Avg: 868.08 / Max: 868.72Min: 867.5 / Avg: 867.93 / Max: 868.28Min: 866.77 / Avg: 867.02 / Max: 867.5Min: 865.72 / Avg: 866.98 / Max: 868.33Min: 892.12 / Avg: 893.43 / Max: 894.86Min: 866.76 / Avg: 866.96 / Max: 867.09Min: 4862.39 / Avg: 4868.11 / Max: 4872.27Min: 875.25 / Avg: 876.33 / Max: 877.11Min: 866.49 / Avg: 866.62 / Max: 866.83Min: 871.77 / Avg: 872.07 / Max: 872.26Min: 867.12 / Avg: 867.83 / Max: 869.2

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance1632486480SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.00, N = 3SE +/- 0.18, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.10, N = 373.0272.9473.0573.1471.0173.2713.0072.4173.0372.7873.25
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance1428425670Min: 72.92 / Avg: 73.02 / Max: 73.09Min: 72.86 / Avg: 72.94 / Max: 73.03Min: 72.91 / Avg: 73.05 / Max: 73.16Min: 73.07 / Avg: 73.14 / Max: 73.18Min: 70.91 / Avg: 71.01 / Max: 71.08Min: 73.16 / Avg: 73.27 / Max: 73.33Min: 13 / Avg: 13 / Max: 13.01Min: 72.05 / Avg: 72.41 / Max: 72.61Min: 72.93 / Avg: 73.03 / Max: 73.11Min: 72.75 / Avg: 72.78 / Max: 72.82Min: 73.06 / Avg: 73.25 / Max: 73.42

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance2004006008001000SE +/- 0.29, N = 3SE +/- 0.48, N = 3SE +/- 0.11, N = 3SE +/- 0.11, N = 3SE +/- 0.54, N = 3SE +/- 0.30, N = 3SE +/- 0.96, N = 3SE +/- 0.15, N = 3SE +/- 0.52, N = 3SE +/- 0.26, N = 3SE +/- 0.28, N = 3207.61207.44207.33207.19214.47207.671143.06208.09207.27207.88207.58
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance2004006008001000Min: 207.17 / Avg: 207.61 / Max: 208.15Min: 206.85 / Avg: 207.44 / Max: 208.38Min: 207.13 / Avg: 207.33 / Max: 207.52Min: 206.96 / Avg: 207.19 / Max: 207.3Min: 213.5 / Avg: 214.47 / Max: 215.37Min: 207.1 / Avg: 207.67 / Max: 208.13Min: 1141.63 / Avg: 1143.06 / Max: 1144.9Min: 207.88 / Avg: 208.09 / Max: 208.37Min: 206.23 / Avg: 207.27 / Max: 207.84Min: 207.43 / Avg: 207.88 / Max: 208.35Min: 207.2 / Avg: 207.58 / Max: 208.12

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance70140210280350SE +/- 0.63, N = 3SE +/- 0.82, N = 3SE +/- 0.25, N = 3SE +/- 0.09, N = 3SE +/- 0.78, N = 3SE +/- 0.44, N = 3SE +/- 0.07, N = 3SE +/- 0.22, N = 3SE +/- 0.63, N = 3SE +/- 0.60, N = 3SE +/- 0.69, N = 3307.04307.64307.71307.89297.14307.2755.22306.40307.72306.68307.17
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance60120180240300Min: 305.87 / Avg: 307.04 / Max: 308.05Min: 306 / Avg: 307.64 / Max: 308.52Min: 307.42 / Avg: 307.71 / Max: 308.21Min: 307.74 / Avg: 307.89 / Max: 308.06Min: 295.77 / Avg: 297.14 / Max: 298.46Min: 306.67 / Avg: 307.27 / Max: 308.13Min: 55.09 / Avg: 55.22 / Max: 55.32Min: 305.99 / Avg: 306.4 / Max: 306.76Min: 307.08 / Avg: 307.72 / Max: 308.98Min: 305.52 / Avg: 306.68 / Max: 307.54Min: 305.79 / Avg: 307.17 / Max: 307.93

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance16003200480064008000SE +/- 0.15, N = 3SE +/- 0.45, N = 3SE +/- 0.05, N = 3SE +/- 8.32, N = 3SE +/- 0.52, N = 3SE +/- 0.68, N = 3SE +/- 16.67, N = 3SE +/- 0.24, N = 3SE +/- 1.11, N = 3SE +/- 0.25, N = 3SE +/- 0.38, N = 31195.351195.601199.871203.521260.491195.237565.211210.761195.761203.421195.14MIN: 7058.85 / MAX: 8272.071. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance13002600390052006500Min: 1195.15 / Avg: 1195.35 / Max: 1195.65Min: 1194.79 / Avg: 1195.6 / Max: 1196.35Min: 1199.77 / Avg: 1199.87 / Max: 1199.95Min: 1195.12 / Avg: 1203.52 / Max: 1220.15Min: 1259.5 / Avg: 1260.49 / Max: 1261.26Min: 1194.05 / Avg: 1195.23 / Max: 1196.42Min: 7540.6 / Avg: 7565.21 / Max: 7597Min: 1210.39 / Avg: 1210.76 / Max: 1211.22Min: 1194.39 / Avg: 1195.76 / Max: 1197.96Min: 1202.93 / Avg: 1203.42 / Max: 1203.71Min: 1194.56 / Avg: 1195.14 / Max: 1195.871. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance1224364860SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.35, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 353.0953.0752.9152.7950.3553.038.3852.4853.0652.7653.121. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance1122334455Min: 53.01 / Avg: 53.09 / Max: 53.13Min: 53.03 / Avg: 53.07 / Max: 53.1Min: 52.84 / Avg: 52.91 / Max: 52.95Min: 52.08 / Avg: 52.79 / Max: 53.18Min: 50.3 / Avg: 50.35 / Max: 50.42Min: 52.99 / Avg: 53.03 / Max: 53.07Min: 8.34 / Avg: 8.38 / Max: 8.41Min: 52.43 / Avg: 52.48 / Max: 52.54Min: 52.94 / Avg: 53.06 / Max: 53.13Min: 52.73 / Avg: 52.76 / Max: 52.81Min: 53.1 / Avg: 53.12 / Max: 53.141. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

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.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To Compileamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance60120180240300SE +/- 0.44, N = 3SE +/- 0.05, N = 3SE +/- 0.43, N = 3SE +/- 0.27, N = 3SE +/- 0.30, N = 15SE +/- 0.46, N = 3SE +/- 1.50, N = 3SE +/- 0.12, N = 3SE +/- 0.36, N = 3SE +/- 0.38, N = 3SE +/- 0.23, N = 341.9037.3247.9437.0141.9437.05258.8740.8137.5838.3737.38
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To Compileamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance50100150200250Min: 41.22 / Avg: 41.9 / Max: 42.73Min: 37.23 / Avg: 37.32 / Max: 37.41Min: 47.07 / Avg: 47.94 / Max: 48.4Min: 36.66 / Avg: 37.01 / Max: 37.53Min: 39.97 / Avg: 41.94 / Max: 44.3Min: 36.19 / Avg: 37.05 / Max: 37.73Min: 256.01 / Avg: 258.87 / Max: 261.07Min: 40.64 / Avg: 40.81 / Max: 41.03Min: 36.99 / Avg: 37.58 / Max: 38.23Min: 37.61 / Avg: 38.37 / Max: 38.76Min: 36.93 / Avg: 37.38 / Max: 37.66

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.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 4 - Input: Bosphorus 4Kamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance0.94141.88282.82423.76564.707SE +/- 0.013, N = 3SE +/- 0.008, N = 3SE +/- 0.007, N = 3SE +/- 0.016, N = 3SE +/- 0.022, N = 3SE +/- 0.005, N = 3SE +/- 0.001, N = 3SE +/- 0.020, N = 3SE +/- 0.003, N = 3SE +/- 0.025, N = 3SE +/- 0.002, N = 33.4534.1582.4434.1813.3224.1840.5583.8654.0134.0904.1821. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 4 - Input: Bosphorus 4Kamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance246810Min: 3.44 / Avg: 3.45 / Max: 3.48Min: 4.14 / Avg: 4.16 / Max: 4.17Min: 2.43 / Avg: 2.44 / Max: 2.45Min: 4.16 / Avg: 4.18 / Max: 4.21Min: 3.28 / Avg: 3.32 / Max: 3.35Min: 4.18 / Avg: 4.18 / Max: 4.19Min: 0.56 / Avg: 0.56 / Max: 0.56Min: 3.83 / Avg: 3.87 / Max: 3.89Min: 4.01 / Avg: 4.01 / Max: 4.02Min: 4.04 / Avg: 4.09 / Max: 4.13Min: 4.18 / Avg: 4.18 / Max: 4.191. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Pabellon Barcelona - Compute: CPU-Onlyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance60120180240300SE +/- 0.20, N = 3SE +/- 0.08, N = 3SE +/- 0.42, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.71, N = 3SE +/- 0.29, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.15, N = 345.9945.7246.7345.7548.4945.77297.6746.1945.9545.9245.85
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Pabellon Barcelona - Compute: CPU-Onlyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance50100150200250Min: 45.7 / Avg: 45.99 / Max: 46.36Min: 45.57 / Avg: 45.72 / Max: 45.86Min: 46.11 / Avg: 46.73 / Max: 47.52Min: 45.65 / Avg: 45.75 / Max: 45.92Min: 48.37 / Avg: 48.49 / Max: 48.65Min: 45.73 / Avg: 45.77 / Max: 45.8Min: 296.94 / Avg: 297.67 / Max: 299.09Min: 45.85 / Avg: 46.19 / Max: 46.78Min: 45.83 / Avg: 45.95 / Max: 46.1Min: 45.78 / Avg: 45.92 / Max: 46.02Min: 45.68 / Avg: 45.85 / Max: 46.15

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2023Implementation: MPI CPU - Input: water_GMX50_bareamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance3691215SE +/- 0.032, N = 3SE +/- 0.057, N = 3SE +/- 0.019, N = 3SE +/- 0.065, N = 3SE +/- 0.601, N = 12SE +/- 0.036, N = 3SE +/- 0.004, N = 3SE +/- 0.448, N = 15SE +/- 0.046, N = 3SE +/- 0.125, N = 15SE +/- 0.018, N = 311.07911.17911.13111.0748.48211.0532.1679.55011.17310.85311.1251. (CXX) g++ options: -O3
OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2023Implementation: MPI CPU - Input: water_GMX50_bareamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance3691215Min: 11.02 / Avg: 11.08 / Max: 11.14Min: 11.07 / Avg: 11.18 / Max: 11.27Min: 11.1 / Avg: 11.13 / Max: 11.17Min: 10.94 / Avg: 11.07 / Max: 11.15Min: 3.9 / Avg: 8.48 / Max: 10.59Min: 10.99 / Avg: 11.05 / Max: 11.11Min: 2.16 / Avg: 2.17 / Max: 2.17Min: 4.92 / Avg: 9.55 / Max: 10.59Min: 11.1 / Avg: 11.17 / Max: 11.26Min: 9.5 / Avg: 10.85 / Max: 11.31Min: 11.09 / Avg: 11.13 / Max: 11.151. (CXX) g++ options: -O3

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance306090120150SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 324.1724.1624.2424.1725.4324.17153.7824.4824.1724.3624.17MIN: 78.56 / MAX: 301.881. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance306090120150Min: 24.16 / Avg: 24.17 / Max: 24.18Min: 24.15 / Avg: 24.16 / Max: 24.17Min: 24.23 / Avg: 24.24 / Max: 24.25Min: 24.17 / Avg: 24.17 / Max: 24.18Min: 25.42 / Avg: 25.43 / Max: 25.43Min: 24.16 / Avg: 24.17 / Max: 24.19Min: 153.72 / Avg: 153.78 / Max: 153.85Min: 24.47 / Avg: 24.48 / Max: 24.49Min: 24.16 / Avg: 24.17 / Max: 24.17Min: 24.36 / Avg: 24.36 / Max: 24.36Min: 24.16 / Avg: 24.17 / Max: 24.181. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance11002200330044005500SE +/- 0.95, N = 3SE +/- 1.37, N = 3SE +/- 1.46, N = 3SE +/- 0.41, N = 3SE +/- 0.59, N = 3SE +/- 2.23, N = 3SE +/- 0.10, N = 3SE +/- 1.03, N = 3SE +/- 0.71, N = 3SE +/- 0.47, N = 3SE +/- 0.80, N = 35291.455294.975277.025291.005029.055292.08830.315224.835292.425250.155291.811. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance9001800270036004500Min: 5289.89 / Avg: 5291.45 / Max: 5293.18Min: 5292.58 / Avg: 5294.97 / Max: 5297.33Min: 5274.33 / Avg: 5277.02 / Max: 5279.37Min: 5290.26 / Avg: 5291 / Max: 5291.68Min: 5028.11 / Avg: 5029.05 / Max: 5030.13Min: 5287.61 / Avg: 5292.08 / Max: 5294.33Min: 830.14 / Avg: 830.31 / Max: 830.49Min: 5223.09 / Avg: 5224.83 / Max: 5226.66Min: 5291.21 / Avg: 5292.42 / Max: 5293.67Min: 5249.21 / Avg: 5250.15 / Max: 5250.66Min: 5290.38 / Avg: 5291.81 / Max: 5293.161. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Classroom - Compute: CPU-Onlyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance60120180240300SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.12, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.10, N = 337.9437.6838.3537.5740.0437.73254.4637.8537.6137.9237.71
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Classroom - Compute: CPU-Onlyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance50100150200250Min: 37.82 / Avg: 37.94 / Max: 38.02Min: 37.55 / Avg: 37.68 / Max: 37.82Min: 38.24 / Avg: 38.35 / Max: 38.54Min: 37.48 / Avg: 37.57 / Max: 37.63Min: 40 / Avg: 40.04 / Max: 40.11Min: 37.52 / Avg: 37.73 / Max: 37.94Min: 254.28 / Avg: 254.46 / Max: 254.58Min: 37.79 / Avg: 37.85 / Max: 37.91Min: 37.52 / Avg: 37.61 / Max: 37.74Min: 37.74 / Avg: 37.92 / Max: 38.02Min: 37.55 / Avg: 37.71 / Max: 37.88

PHPBench

PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark Suiteamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance150K300K450K600K750KSE +/- 2423.31, N = 3SE +/- 5808.55, N = 12SE +/- 981.48, N = 3SE +/- 4455.74, N = 3SE +/- 5021.57, N = 3SE +/- 3225.60, N = 3SE +/- 423.55, N = 3SE +/- 5843.40, N = 3SE +/- 2191.80, N = 3SE +/- 5594.67, N = 3SE +/- 4034.04, N = 368768269747867120770028771112570121579570705341698785708218699816
OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark Suiteamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance120K240K360K480K600KMin: 682996 / Avg: 687682.33 / Max: 691096Min: 635365 / Avg: 697477.75 / Max: 710951Min: 669667 / Avg: 671206.67 / Max: 673031Min: 692468 / Avg: 700286.67 / Max: 707899Min: 702953 / Avg: 711125.33 / Max: 720267Min: 694783 / Avg: 701214.67 / Max: 704865Min: 78937 / Avg: 79570 / Max: 80374Min: 699306 / Avg: 705341.33 / Max: 717026Min: 694416 / Avg: 698785.33 / Max: 701276Min: 697569 / Avg: 708218.33 / Max: 716517Min: 692015 / Avg: 699815.67 / Max: 705500

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.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 12 - Input: Bosphorus 4Kamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance4080120160200SE +/- 2.85, N = 15SE +/- 3.08, N = 15SE +/- 1.61, N = 15SE +/- 2.85, N = 15SE +/- 1.29, N = 15SE +/- 3.27, N = 15SE +/- 0.49, N = 12SE +/- 2.56, N = 15SE +/- 2.84, N = 15SE +/- 3.33, N = 15SE +/- 3.08, N = 15175.46186.05155.77173.3190.28182.3636.65171.88167.61180.33180.861. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 12 - Input: Bosphorus 4Kamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance306090120150Min: 145.51 / Avg: 175.45 / Max: 187.02Min: 158.99 / Avg: 186.05 / Max: 208.03Min: 144.22 / Avg: 155.77 / Max: 165.17Min: 148.51 / Avg: 173.31 / Max: 195.93Min: 82.05 / Avg: 90.28 / Max: 101.98Min: 157.41 / Avg: 182.36 / Max: 209.44Min: 31.33 / Avg: 36.65 / Max: 37.47Min: 149.38 / Avg: 171.88 / Max: 186.6Min: 138.08 / Avg: 167.61 / Max: 186.23Min: 147.46 / Avg: 180.33 / Max: 198.5Min: 154.22 / Avg: 180.86 / Max: 206.41. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance120240360480600SE +/- 0.11, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.25, N = 3SE +/- 0.14, N = 3SE +/- 0.31, N = 3SE +/- 0.05, N = 3SE +/- 0.20, N = 3SE +/- 0.06, N = 3SE +/- 0.11, N = 3104.57104.76104.66104.62108.66104.73577.77105.15104.75105.02104.80
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance100200300400500Min: 104.4 / Avg: 104.57 / Max: 104.79Min: 104.68 / Avg: 104.76 / Max: 104.82Min: 104.57 / Avg: 104.66 / Max: 104.71Min: 104.55 / Avg: 104.62 / Max: 104.73Min: 108.35 / Avg: 108.66 / Max: 109.16Min: 104.56 / Avg: 104.73 / Max: 105.01Min: 577.28 / Avg: 577.77 / Max: 578.36Min: 105.07 / Avg: 105.15 / Max: 105.25Min: 104.52 / Avg: 104.75 / Max: 105.15Min: 104.91 / Avg: 105.02 / Max: 105.09Min: 104.63 / Avg: 104.8 / Max: 105

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance130260390520650SE +/- 0.85, N = 3SE +/- 0.26, N = 3SE +/- 0.24, N = 3SE +/- 0.35, N = 3SE +/- 1.22, N = 3SE +/- 0.82, N = 3SE +/- 0.09, N = 3SE +/- 0.13, N = 3SE +/- 1.19, N = 3SE +/- 0.14, N = 3SE +/- 0.68, N = 3610.70609.61609.90610.32587.48609.96109.77607.33609.76608.30609.04
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance110220330440550Min: 609.02 / Avg: 610.7 / Max: 611.77Min: 609.18 / Avg: 609.61 / Max: 610.09Min: 609.59 / Avg: 609.9 / Max: 610.38Min: 609.86 / Avg: 610.32 / Max: 611Min: 585.04 / Avg: 587.48 / Max: 588.72Min: 608.4 / Avg: 609.96 / Max: 611.2Min: 109.6 / Avg: 109.77 / Max: 109.9Min: 607.13 / Avg: 607.33 / Max: 607.59Min: 607.39 / Avg: 609.76 / Max: 611Min: 608.12 / Avg: 608.3 / Max: 608.59Min: 608.23 / Avg: 609.04 / Max: 610.4

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance2004006008001000SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.17, N = 3SE +/- 0.17, N = 3SE +/- 0.12, N = 3SE +/- 1.48, N = 3SE +/- 0.14, N = 3SE +/- 0.18, N = 3SE +/- 0.15, N = 3SE +/- 0.09, N = 3158.13157.55158.08157.70164.20157.80884.29158.95157.83158.05157.88
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance160320480640800Min: 158.06 / Avg: 158.13 / Max: 158.24Min: 157.44 / Avg: 157.55 / Max: 157.7Min: 158.05 / Avg: 158.08 / Max: 158.11Min: 157.47 / Avg: 157.7 / Max: 158.03Min: 163.86 / Avg: 164.2 / Max: 164.39Min: 157.59 / Avg: 157.8 / Max: 158.01Min: 882.18 / Avg: 884.29 / Max: 887.13Min: 158.78 / Avg: 158.95 / Max: 159.23Min: 157.48 / Avg: 157.83 / Max: 158.08Min: 157.88 / Avg: 158.05 / Max: 158.35Min: 157.79 / Avg: 157.88 / Max: 158.05

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance90180270360450SE +/- 0.20, N = 3SE +/- 0.15, N = 3SE +/- 0.10, N = 3SE +/- 0.32, N = 3SE +/- 0.49, N = 3SE +/- 0.37, N = 3SE +/- 0.15, N = 3SE +/- 0.34, N = 3SE +/- 0.60, N = 3SE +/- 0.36, N = 3SE +/- 0.15, N = 3403.29404.95403.59404.55388.64404.3070.87401.73404.27403.28404.13
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance70140210280350Min: 402.93 / Avg: 403.29 / Max: 403.64Min: 404.73 / Avg: 404.95 / Max: 405.23Min: 403.4 / Avg: 403.59 / Max: 403.72Min: 403.92 / Avg: 404.55 / Max: 404.97Min: 388.03 / Avg: 388.64 / Max: 389.61Min: 403.63 / Avg: 404.3 / Max: 404.91Min: 70.58 / Avg: 70.87 / Max: 71.04Min: 401.07 / Avg: 401.73 / Max: 402.19Min: 403.34 / Avg: 404.27 / Max: 405.4Min: 402.56 / Avg: 403.28 / Max: 403.67Min: 403.83 / Avg: 404.13 / Max: 404.31

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance90180270360450SE +/- 0.14, N = 3SE +/- 0.16, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 0.17, N = 3SE +/- 0.14, N = 3SE +/- 0.04, N = 3SE +/- 0.12, N = 3SE +/- 0.04, N = 376.9976.9877.0276.9178.8776.91431.9676.5777.1077.0177.06
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance80160240320400Min: 76.74 / Avg: 76.99 / Max: 77.23Min: 76.66 / Avg: 76.98 / Max: 77.19Min: 76.87 / Avg: 77.02 / Max: 77.25Min: 76.71 / Avg: 76.91 / Max: 77.07Min: 78.78 / Avg: 78.87 / Max: 79.04Min: 76.68 / Avg: 76.91 / Max: 77.18Min: 431.68 / Avg: 431.96 / Max: 432.26Min: 76.32 / Avg: 76.57 / Max: 76.8Min: 77.02 / Avg: 77.1 / Max: 77.15Min: 76.77 / Avg: 77.01 / Max: 77.19Min: 76.98 / Avg: 77.06 / Max: 77.1

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance2004006008001000SE +/- 1.36, N = 3SE +/- 1.68, N = 3SE +/- 1.08, N = 3SE +/- 1.26, N = 3SE +/- 0.84, N = 3SE +/- 1.41, N = 3SE +/- 0.17, N = 3SE +/- 1.55, N = 3SE +/- 0.64, N = 3SE +/- 1.55, N = 3SE +/- 0.63, N = 3830.10830.01829.60830.32809.90830.85147.69834.46828.90829.17828.82
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance150300450600750Min: 827.84 / Avg: 830.1 / Max: 832.53Min: 828.03 / Avg: 830.01 / Max: 833.36Min: 827.5 / Avg: 829.6 / Max: 831.04Min: 828.13 / Avg: 830.32 / Max: 832.5Min: 808.24 / Avg: 809.9 / Max: 810.9Min: 828.31 / Avg: 830.85 / Max: 833.18Min: 147.36 / Avg: 147.69 / Max: 147.91Min: 831.79 / Avg: 834.46 / Max: 837.15Min: 827.96 / Avg: 828.9 / Max: 830.12Min: 826.71 / Avg: 829.17 / Max: 832.04Min: 827.72 / Avg: 828.82 / Max: 829.89

x265

This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4Kamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance510152025SE +/- 0.08, N = 3SE +/- 0.16, N = 3SE +/- 0.18, N = 3SE +/- 0.18, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.19, N = 3SE +/- 0.16, N = 3SE +/- 0.17, N = 3SE +/- 0.23, N = 318.5620.5515.3320.6316.3620.744.3719.2920.6719.9020.961. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4Kamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance510152025Min: 18.43 / Avg: 18.56 / Max: 18.71Min: 20.31 / Avg: 20.55 / Max: 20.84Min: 14.97 / Avg: 15.33 / Max: 15.58Min: 20.28 / Avg: 20.63 / Max: 20.88Min: 16.33 / Avg: 16.36 / Max: 16.42Min: 20.59 / Avg: 20.74 / Max: 20.83Min: 4.36 / Avg: 4.37 / Max: 4.4Min: 19.09 / Avg: 19.29 / Max: 19.66Min: 20.36 / Avg: 20.67 / Max: 20.9Min: 19.59 / Avg: 19.9 / Max: 20.17Min: 20.59 / Avg: 20.96 / Max: 21.391. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

PyBench

This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test Timesamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance2K4K6K8K10KSE +/- 0.88, N = 3SE +/- 6.01, N = 3SE +/- 7.22, N = 3SE +/- 4.04, N = 3SE +/- 2.85, N = 3SE +/- 3.28, N = 3SE +/- 41.93, N = 3SE +/- 5.81, N = 3SE +/- 7.81, N = 3SE +/- 9.13, N = 3SE +/- 5.81, N = 310039981008101098710108775100499910061002
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test Timesamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance15003000450060007500Min: 1002 / Avg: 1003.33 / Max: 1005Min: 986 / Avg: 997.67 / Max: 1006Min: 999 / Avg: 1007.67 / Max: 1022Min: 1002 / Avg: 1010 / Max: 1015Min: 984 / Avg: 987.33 / Max: 993Min: 1005 / Avg: 1009.67 / Max: 1016Min: 8693 / Avg: 8774.67 / Max: 8832Min: 993 / Avg: 1003.67 / Max: 1013Min: 986 / Avg: 999 / Max: 1013Min: 989 / Avg: 1006.33 / Max: 1020Min: 993 / Avg: 1002.33 / Max: 1013

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Mediumamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance612182430SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.12, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.19, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 324.2827.0117.3327.0612.2526.893.9724.5821.2127.2026.93
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Mediumamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance612182430Min: 24.23 / Avg: 24.28 / Max: 24.31Min: 26.93 / Avg: 27.01 / Max: 27.06Min: 17.16 / Avg: 17.33 / Max: 17.56Min: 26.89 / Avg: 27.06 / Max: 27.2Min: 12.11 / Avg: 12.25 / Max: 12.4Min: 26.8 / Avg: 26.89 / Max: 26.96Min: 3.96 / Avg: 3.97 / Max: 3.99Min: 24.57 / Avg: 24.58 / Max: 24.59Min: 21.02 / Avg: 21.21 / Max: 21.58Min: 27.17 / Avg: 27.2 / Max: 27.22Min: 26.88 / Avg: 26.93 / Max: 27.04

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0Binary: Pathtracer ISPC - Model: Asian Dragonamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance20406080100SE +/- 0.79, N = 15SE +/- 0.87, N = 15SE +/- 0.91, N = 15SE +/- 0.93, N = 15SE +/- 0.79, N = 15SE +/- 0.98, N = 15SE +/- 0.02, N = 3SE +/- 1.15, N = 15SE +/- 0.79, N = 6SE +/- 0.85, N = 6SE +/- 0.72, N = 1592.2194.7893.7393.5088.8093.6124.7992.8093.7692.9591.37MIN: 87.15 / MAX: 100.61MIN: 86.18 / MAX: 101.48MIN: 86.21 / MAX: 102.02MIN: 87.15 / MAX: 102.17MIN: 82.24 / MAX: 97.26MIN: 86.72 / MAX: 102.65MIN: 24.19 / MAX: 25.44MIN: 85.44 / MAX: 101.26MIN: 88.79 / MAX: 100.41MIN: 88.86 / MAX: 98.52MIN: 86.16 / MAX: 99.08
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0Binary: Pathtracer ISPC - Model: Asian Dragonamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance20406080100Min: 88.76 / Avg: 92.21 / Max: 97.8Min: 87.61 / Avg: 94.78 / Max: 98.87Min: 88.19 / Avg: 93.73 / Max: 99.5Min: 88.85 / Avg: 93.5 / Max: 99.31Min: 84.88 / Avg: 88.8 / Max: 93.42Min: 88.36 / Avg: 93.6 / Max: 99.72Min: 24.75 / Avg: 24.79 / Max: 24.83Min: 86.78 / Avg: 92.8 / Max: 98.26Min: 91.04 / Avg: 93.76 / Max: 96.71Min: 90.43 / Avg: 92.95 / Max: 95.84Min: 87.76 / Avg: 91.37 / Max: 95.5

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Ultra Fastamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance1326395265SE +/- 0.70, N = 15SE +/- 0.40, N = 5SE +/- 1.47, N = 15SE +/- 0.46, N = 5SE +/- 0.10, N = 3SE +/- 0.11, N = 5SE +/- 0.07, N = 3SE +/- 0.50, N = 4SE +/- 0.44, N = 5SE +/- 0.48, N = 5SE +/- 0.48, N = 550.6756.1441.8355.8526.5455.277.7252.6052.9355.5855.921. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Ultra Fastamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance1122334455Min: 46.62 / Avg: 50.67 / Max: 55.32Min: 55.17 / Avg: 56.14 / Max: 57.46Min: 34.29 / Avg: 41.83 / Max: 50.83Min: 54.03 / Avg: 55.85 / Max: 56.45Min: 26.42 / Avg: 26.54 / Max: 26.74Min: 55.02 / Avg: 55.27 / Max: 55.65Min: 7.58 / Avg: 7.72 / Max: 7.82Min: 51.72 / Avg: 52.6 / Max: 53.59Min: 51.77 / Avg: 52.93 / Max: 54.02Min: 54.44 / Avg: 55.58 / Max: 56.78Min: 55.06 / Avg: 55.92 / Max: 57.651. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Super Fastamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance1224364860SE +/- 0.60, N = 15SE +/- 0.60, N = 5SE +/- 1.49, N = 15SE +/- 0.44, N = 5SE +/- 0.13, N = 3SE +/- 0.51, N = 5SE +/- 0.08, N = 3SE +/- 0.26, N = 4SE +/- 0.20, N = 4SE +/- 0.50, N = 5SE +/- 0.52, N = 547.9754.6945.5654.7726.2153.777.4352.1752.3254.7855.031. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Super Fastamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance1122334455Min: 45.05 / Avg: 47.97 / Max: 53.55Min: 52.88 / Avg: 54.69 / Max: 56.47Min: 34.87 / Avg: 45.56 / Max: 52.85Min: 53.41 / Avg: 54.77 / Max: 55.67Min: 26 / Avg: 26.21 / Max: 26.46Min: 52.46 / Avg: 53.77 / Max: 55.59Min: 7.29 / Avg: 7.43 / Max: 7.58Min: 51.53 / Avg: 52.17 / Max: 52.74Min: 51.92 / Avg: 52.32 / Max: 52.66Min: 53.52 / Avg: 54.78 / Max: 55.72Min: 53.56 / Avg: 55.03 / Max: 56.481. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra Fastamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance1122334455SE +/- 0.43, N = 4SE +/- 0.33, N = 4SE +/- 0.67, N = 15SE +/- 0.28, N = 4SE +/- 0.08, N = 3SE +/- 0.49, N = 5SE +/- 0.04, N = 3SE +/- 0.19, N = 4SE +/- 0.18, N = 4SE +/- 0.30, N = 4SE +/- 0.21, N = 441.1347.2533.7646.0821.6545.466.8841.9040.8244.5046.45
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra Fastamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance1020304050Min: 40.64 / Avg: 41.13 / Max: 42.41Min: 46.55 / Avg: 47.25 / Max: 47.92Min: 30.62 / Avg: 33.76 / Max: 38.73Min: 45.42 / Avg: 46.08 / Max: 46.66Min: 21.5 / Avg: 21.65 / Max: 21.74Min: 44 / Avg: 45.46 / Max: 46.91Min: 6.82 / Avg: 6.88 / Max: 6.96Min: 41.65 / Avg: 41.9 / Max: 42.45Min: 40.32 / Avg: 40.82 / Max: 41.14Min: 43.81 / Avg: 44.5 / Max: 45.19Min: 45.97 / Avg: 46.45 / Max: 47.01

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Mediumamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance816243240SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.13, N = 3SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 0.14, N = 3SE +/- 0.13, N = 329.4231.9920.6632.3014.3932.004.8330.3222.9732.3632.091. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Mediumamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance714212835Min: 29.33 / Avg: 29.42 / Max: 29.48Min: 31.89 / Avg: 31.99 / Max: 32.14Min: 20.63 / Avg: 20.66 / Max: 20.68Min: 32.19 / Avg: 32.3 / Max: 32.44Min: 14.23 / Avg: 14.39 / Max: 14.48Min: 31.83 / Avg: 32 / Max: 32.25Min: 4.81 / Avg: 4.83 / Max: 4.85Min: 30.17 / Avg: 30.32 / Max: 30.41Min: 22.68 / Avg: 22.97 / Max: 23.16Min: 32.08 / Avg: 32.36 / Max: 32.53Min: 31.84 / Avg: 32.09 / Max: 32.241. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super Fastamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance1122334455SE +/- 0.28, N = 4SE +/- 0.22, N = 4SE +/- 0.58, N = 15SE +/- 0.28, N = 4SE +/- 0.09, N = 3SE +/- 0.18, N = 4SE +/- 0.01, N = 3SE +/- 0.33, N = 4SE +/- 0.25, N = 4SE +/- 0.30, N = 4SE +/- 0.16, N = 439.9646.2633.7946.3125.4345.416.7741.5740.7145.1946.07
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super Fastamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance918273645Min: 39.45 / Avg: 39.96 / Max: 40.62Min: 45.78 / Avg: 46.26 / Max: 46.8Min: 30.38 / Avg: 33.79 / Max: 37.9Min: 45.63 / Avg: 46.31 / Max: 46.86Min: 25.33 / Avg: 25.43 / Max: 25.62Min: 45.01 / Avg: 45.41 / Max: 45.8Min: 6.75 / Avg: 6.77 / Max: 6.79Min: 40.6 / Avg: 41.57 / Max: 42.1Min: 40.19 / Avg: 40.71 / Max: 41.26Min: 44.52 / Avg: 45.19 / Max: 45.96Min: 45.7 / Avg: 46.07 / Max: 46.44

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Fishy Cat - Compute: CPU-Onlyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance306090120150SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.13, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.18, N = 3SE +/- 0.16, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 319.1718.8019.7418.9520.2618.89124.4819.1818.9019.0019.01
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Fishy Cat - Compute: CPU-Onlyamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance20406080100Min: 19.14 / Avg: 19.17 / Max: 19.2Min: 18.65 / Avg: 18.8 / Max: 18.96Min: 19.48 / Avg: 19.74 / Max: 19.89Min: 18.9 / Avg: 18.95 / Max: 18.99Min: 20.11 / Avg: 20.26 / Max: 20.44Min: 18.68 / Avg: 18.89 / Max: 19.25Min: 124.32 / Avg: 124.48 / Max: 124.8Min: 19.15 / Avg: 19.18 / Max: 19.23Min: 18.86 / Avg: 18.9 / Max: 18.95Min: 18.78 / Avg: 19 / Max: 19.12Min: 18.93 / Avg: 19.01 / Max: 19.09

NAMD

NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 Atomsamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance0.31720.63440.95161.26881.586SE +/- 0.00272, N = 3SE +/- 0.00158, N = 4SE +/- 0.00042, N = 3SE +/- 0.00124, N = 4SE +/- 0.00054, N = 3SE +/- 0.00077, N = 4SE +/- 0.00490, N = 3SE +/- 0.00244, N = 3SE +/- 0.00170, N = 3SE +/- 0.00142, N = 3SE +/- 0.00089, N = 40.222860.222700.224500.220210.234200.224641.409820.222890.220250.222900.22441
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 Atomsamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance246810Min: 0.22 / Avg: 0.22 / Max: 0.23Min: 0.22 / Avg: 0.22 / Max: 0.22Min: 0.22 / Avg: 0.22 / Max: 0.23Min: 0.22 / Avg: 0.22 / Max: 0.22Min: 0.23 / Avg: 0.23 / Max: 0.24Min: 0.22 / Avg: 0.22 / Max: 0.23Min: 1.4 / Avg: 1.41 / Max: 1.42Min: 0.22 / Avg: 0.22 / Max: 0.23Min: 0.22 / Avg: 0.22 / Max: 0.22Min: 0.22 / Avg: 0.22 / Max: 0.23Min: 0.22 / Avg: 0.22 / Max: 0.23

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.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 13 - Input: Bosphorus 4Kamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance4080120160200SE +/- 1.23, N = 12SE +/- 1.60, N = 7SE +/- 1.22, N = 6SE +/- 2.12, N = 15SE +/- 0.85, N = 15SE +/- 1.88, N = 15SE +/- 0.14, N = 3SE +/- 1.52, N = 7SE +/- 1.54, N = 15SE +/- 1.37, N = 10SE +/- 2.47, N = 15170.27194.10145.32188.4272.22191.0532.27161.78144.34180.34189.131. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 13 - Input: Bosphorus 4Kamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance4080120160200Min: 164.46 / Avg: 170.27 / Max: 175.67Min: 190.05 / Avg: 194.1 / Max: 202.87Min: 142.41 / Avg: 145.32 / Max: 149.14Min: 173.98 / Avg: 188.42 / Max: 201.54Min: 66.31 / Avg: 72.22 / Max: 78.46Min: 180.83 / Avg: 191.05 / Max: 207.4Min: 32.01 / Avg: 32.26 / Max: 32.51Min: 157.1 / Avg: 161.78 / Max: 167.3Min: 132.3 / Avg: 144.34 / Max: 152.76Min: 175.2 / Avg: 180.34 / Max: 189.39Min: 174.43 / Avg: 189.13 / Max: 202.771. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0Binary: Pathtracer ISPC - Model: Crownamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance306090120150SE +/- 0.25, N = 7SE +/- 0.11, N = 7SE +/- 0.21, N = 6SE +/- 0.18, N = 7SE +/- 0.22, N = 7SE +/- 0.14, N = 7SE +/- 0.02, N = 3SE +/- 0.24, N = 7SE +/- 0.15, N = 7SE +/- 0.33, N = 7SE +/- 0.13, N = 7122.50123.15121.30122.87116.75123.0219.67121.86122.71120.80123.05MIN: 118.44 / MAX: 132.08MIN: 120.42 / MAX: 134.1MIN: 107.62 / MAX: 132.2MIN: 119.52 / MAX: 133.96MIN: 112.31 / MAX: 126.6MIN: 120.25 / MAX: 132.77MIN: 117.58 / MAX: 131.5MIN: 119.75 / MAX: 131.8MIN: 116.78 / MAX: 132.34MIN: 119.92 / MAX: 135.17
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0Binary: Pathtracer ISPC - Model: Crownamd_pstate_epp powersave balance_performanceamd_pstate_epp performance balance_performanceamd_pstate_epp powersave poweramd_pstate_epp performance performanceamd_pstate schedutilamd_pstate performanceamd_pstate powersaveamd_pstate ondemandacpi_cpufreq schedutilacpi_cpufreq ondemandacpi_cpufreq performance20406080100Min: 121.07 / Avg: 122.5 / Max: 123.01Min: 122.79 / Avg: 123.15 / Max: 123.52Min: 120.52 / Avg: 121.3 / Max: 121.83Min: 122.3 / Avg: 122.87 / Max: 123.55Min: 116.04 / Avg: 116.75 / Max: 117.48Min: 122.61 / Avg: 123.02 / Max: 123.68Min: 19.63 / Avg: 19.67 / Max: 19.7Min: 120.99 / Avg: 121.86 / Max: 122.75Min: 122.23 / Avg: 122.71 / Max: 123.39Min: 119.35 / Avg: 120.8 / Max: 121.67Min: 122.56 / Avg: 123.05 / Max: 123.59

98 Results Shown

TensorFlow
OpenVKL:
  vklBenchmark Scalar
  vklBenchmark ISPC
TensorFlow
BRL-CAD
PostgreSQL:
  100 - 500 - Read Write - Average Latency
  100 - 500 - Read Write
ClickHouse:
  100M Rows Hits Dataset, Third Run
  100M Rows Hits Dataset, Second Run
  100M Rows Hits Dataset, First Run / Cold Cache
PostgreSQL:
  100 - 800 - Read Write - Average Latency
  100 - 800 - Read Write
CockroachDB
PostgreSQL:
  100 - 500 - Read Only - Average Latency
  100 - 500 - Read Only
Xcompact3d Incompact3d
Timed Gem5 Compilation
VP9 libvpx Encoding
Timed Linux Kernel Compilation
VVenC
PostgreSQL:
  100 - 800 - Read Only - Average Latency
  100 - 800 - Read Only
Stargate Digital Audio Workstation
PostgreSQL:
  100 - 1000 - Read Write - Average Latency
  100 - 1000 - Read Write
OpenVINO:
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
    ms
    FPS
PostgreSQL:
  100 - 1000 - Read Only - Average Latency
  100 - 1000 - Read Only
Blender
CockroachDB
Timed Node.js Compilation
OSPRay Studio:
  3 - 4K - 32 - Path Tracer
  3 - 4K - 1 - Path Tracer
  1 - 4K - 1 - Path Tracer
  1 - 4K - 32 - Path Tracer
OpenVINO:
  Person Vehicle Bike Detection FP16 - CPU:
    ms
    FPS
VVenC
Timed Linux Kernel Compilation
OpenFOAM:
  drivaerFastback, Medium Mesh Size - Execution Time
  drivaerFastback, Medium Mesh Size - Mesh Time
CockroachDB
nginx
OpenVINO:
  Vehicle Detection FP16-INT8 - CPU:
    ms
    FPS
  Machine Translation EN To DE FP16 - CPU:
    ms
    FPS
Neural Magic DeepSparse:
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
Zstd Compression:
  19, Long Mode - Decompression Speed
  19, Long Mode - Compression Speed
Neural Magic DeepSparse:
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream:
    ms/batch
    items/sec
OpenVINO:
  Person Detection FP16 - CPU:
    ms
    FPS
Neural Magic DeepSparse:
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream:
    ms/batch
    items/sec
7-Zip Compression:
  Decompression Rating
  Compression Rating
Neural Magic DeepSparse:
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream:
    ms/batch
    items/sec
Zstd Compression:
  19 - Decompression Speed
  19 - Compression Speed
Neural Magic DeepSparse:
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
OpenVINO:
  Face Detection FP16-INT8 - CPU:
    ms
    FPS
Timed Godot Game Engine Compilation
SVT-AV1
Blender
GROMACS
OpenVINO:
  Weld Porosity Detection FP16-INT8 - CPU:
    ms
    FPS
Blender
PHPBench
SVT-AV1
Neural Magic DeepSparse:
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream:
    ms/batch
    items/sec
x265
PyBench
uvg266
Embree
Kvazaar:
  Bosphorus 4K - Ultra Fast
  Bosphorus 4K - Super Fast
uvg266
Kvazaar
uvg266
Blender
NAMD
SVT-AV1
Embree

amd_pstate_epp powersave balance_performance

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: amd_pstate_epp powersave (EPP: balance_performance) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 21 February 2023 21:12 by user phoronix.

amd_pstate_epp performance balance_performance

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: amd_pstate_epp performance (EPP: performance) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 22 February 2023 07:45 by user phoronix.

amd_pstate_epp powersave power

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: amd_pstate_epp powersave (EPP: power) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 22 February 2023 16:11 by user phoronix.

amd_pstate_epp performance performance

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: amd_pstate_epp performance (EPP: performance) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 23 February 2023 05:36 by user phoronix.

amd_pstate schedutil

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: amd-pstate schedutil (Boost: Enabled) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 23 February 2023 13:51 by user phoronix.

amd_pstate performance

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 24 February 2023 06:06 by user phoronix.

amd_pstate powersave

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: amd-pstate powersave (Boost: Enabled) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 24 February 2023 15:36 by user phoronix.

amd_pstate ondemand

Processor: 2 x AMD EPYC 7773X 64-Core @ 3.53GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 512GB, Disk: 800GB INTEL SSDPF21Q800GB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 22.04, Kernel: 6.2.0-phx (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.3, Vulkan: 1.3.224, Compiler: GCC 11.3.0 + LLVM 14.0.0, File-System: ext4, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: amd-pstate ondemand (Boost: Enabled) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 25 February 2023 17:02 by user phoronix.

acpi_cpufreq schedutil

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 26 February 2023 06:05 by user phoronix.

acpi_cpufreq ondemand

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 26 February 2023 16:34 by user phoronix.

acpi_cpufreq performance

Processor: 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 512GB, Disk: 800GB INTEL SSDPF21Q800GB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 22.04, Kernel: 6.2.0-phx (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.3, Vulkan: 1.3.224, Compiler: GCC 11.3.0 + LLVM 14.0.0, File-System: ext4, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 -v
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001229
Python Notes: Python 3.10.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 27 February 2023 05:40 by user phoronix.