Xeon & EPYC Tests

Various Server CPU benchmarks

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2010047-VE-2009185VE58
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
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
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
Disable Color Branding
Prefer Vertical Bar Graphs

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable
Show Perf Per Clock Calculation Graphs Where Applicable
Show Perf Per RAM Channel 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
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
2 x Xeon Gold 5220R
March 26 2020
  9 Hours, 36 Minutes
Xeon Gold 5220R
March 27 2020
  10 Hours, 11 Minutes
Xeon Platinum 8280
March 28 2020
  8 Hours, 39 Minutes
2 x Xeon Platinum 8280
March 28 2020
  8 Hours, 49 Minutes
Xeon Gold 5218
March 29 2020
  11 Hours, 15 Minutes
Xeon Silver 4216
March 30 2020
  11 Hours, 48 Minutes
Xeon Gold 6226R
March 30 2020
  9 Hours, 51 Minutes
2 x Xeon Gold 6226R
March 31 2020
  9 Hours, 29 Minutes
2 x Xeon Silver 4216
March 31 2020
  10 Hours, 35 Minutes
Xeon W-3275M
April 19 2020
  9 Hours, 52 Minutes
2 x Xeon Platinum 8275CL
June 02 2020
  11 Hours, 15 Minutes
2 x Xeon Platinum 8275CL NUMA off
June 03 2020
  9 Hours, 44 Minutes
EPYC 2 7R32
August 22 2020
  7 Hours, 24 Minutes
2 x Xeon Platinum 8259CL
September 16 2020
  9 Hours, 25 Minutes
2 x Xeon Platinum 8259CL NUMA off
September 17 2020
  9 Hours, 36 Minutes
Xeon Platinum 8259CL
October 03 2020
  10 Hours, 8 Minutes
Invert Behavior (Only Show Selected Data)
  9 Hours, 51 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):


Xeon & EPYC TestsProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkAudioOSKernelDesktopDisplay ServerDisplay DriverCompilerFile-SystemScreen ResolutionOpenGL2 x Xeon Gold 5220RXeon Gold 5220RXeon Platinum 82802 x Xeon Platinum 8280Xeon Gold 5218Xeon Silver 4216Xeon Gold 6226R2 x Xeon Gold 6226R2 x Xeon Silver 4216Xeon W-3275M2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA offEPYC 2 7R322 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA offXeon Platinum 8259CL2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads)GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS)Intel Sky Lake-E DMI3 Registers12 x 32 GB DDR4-2933MT/s HMA84GR7CJR4N-WM280GB INTEL SSDPED1D280GAASPEEDVE2282 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbEUbuntu 20.045.4.0-18-generic (x86_64)GNOME Shell 3.36.0X Server 1.20.7modesetting 1.20.7GCC 9.3.0ext41920x1080Intel Xeon Gold 5220R @ 3.90GHz (18 Cores / 36 Threads)6 x 32 GB DDR4-2933MT/s HMA84GR7CJR4N-WM1024x768Intel Xeon Platinum 8280 @ 4.00GHz (28 Cores / 56 Threads)2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads)12 x 32 GB DDR4-2933MT/s HMA84GR7CJR4N-WMIntel Xeon Gold 5218 @ 3.90GHz (16 Cores / 32 Threads)6 x 32 GB DDR4-2933MT/s HMA84GR7CJR4N-WM2 x VE2281920x1080Intel Xeon Silver 4216 @ 3.20GHz (16 Cores / 32 Threads)3 x VE228Intel Xeon Gold 6226R @ 3.90GHz (16 Cores / 32 Threads)4 x VE2282 x Intel Xeon Gold 6226R @ 3.90GHz (32 Cores / 64 Threads)12 x 32 GB DDR4-2933MT/s HMA84GR7CJR4N-WM5 x VE2282 x Intel Xeon Silver 4216 @ 3.20GHz (32 Cores / 64 Threads)6 x VE228Intel Xeon W-3275M @ 4.60GHz (28 Cores / 56 Threads)Supermicro X11SPA-T v1.01 (3.1 BIOS)188GB2 x 1024GB Samsung SSD 970 PRO 1TBeVGA NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz)Realtek ALC888-VDBenQ SW271Intel I210 + Aquantia AQC107 NBase-T/IEEEUbuntu 19.105.3.0-46-generic (x86_64)GNOME Shell 3.34.3X Server 1.20.5NVIDIA 430.504.6.0GCC 9.2.1 20191008 + CUDA 10.13840x21602 x Intel Xeon Platinum 8275CL @ 3.90GHz (48 Cores / 96 Threads)ASRockRack EP2C621D12 WS (P2.10 BIOS)32 GB + 32 GB + 16384 MB + 32 GB + 16384 MB + 32 GB + 32 GB + 32 GB DDR4-3200MT/s256GB TOSHIBA THNSNJ25 + 600GB INTEL SSDSC2BB60 + 6001GB HGST HUS726060ALllvmpipe 220GBCreative Labs EMU20k2DELL UP2516D4 x Intel X722 for 1GbE5.3.0-55-generic (x86_64)GNOME Shell 3.34.1X Server3.3 Mesa 19.2.1 (LLVM 9.0 256 bits)GCC 9.2.1 201910082560x14403.3 Mesa 19.2.8 (LLVM 9.0 256 bits)AMD EPYC 7R32 48-Core @ 2.80GHz (48 Cores / 96 Threads)Supermicro H11SSL-i v2.00 (2.1 BIOS)AMD Starship/Matisse8 x 16384 MB DDR4-3200MT/s HMA82GR7CJR8N-XN32GB Mass Storage + 256GB TOSHIBA THNSNJ25 + 600GB INTEL SSDSC2BB60 + 6001GB HGST HUS726060ALllvmpipe 126GBCrystal View2 x Intel I2105.3.0-64-generic (x86_64)3.3 Mesa 19.2.8 (LLVM 9.0 128 bits)800x6002 x Intel Xeon Platinum 8259L @ 3.50GHz (48 Cores / 96 Threads)ASRockRack EP2C621D16-4LP (P2.20 BIOS)Intel Sky Lake-E DMI3 Registers12 x 16384 MB DDR4-3200MT/s Hynix HMA82GR7CJR8N-XN256GB TOSHIBA THNSNJ25llvmpipe 188GBNVIDIA Device 10f8DELL UP2516D4 x Intel X722 for 1GbE3.3 Mesa 19.2.8 (LLVM 9.0 256 bits)2560x1440Intel Xeon Platinum 8259L @ 3.50GHz (24 Cores / 48 Threads)6 x 16384 MB DDR4-3200MT/s Hynix HMA82GR7CJR8N-XNllvmpipe 93GBOpenBenchmarking.orgCompiler Details- 2 x Xeon Gold 5220R: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- Xeon Gold 5220R: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- Xeon Platinum 8280: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- 2 x Xeon Platinum 8280: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- Xeon Gold 5218: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- Xeon Silver 4216: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- Xeon Gold 6226R: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- 2 x Xeon Gold 6226R: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- 2 x Xeon Silver 4216: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- Xeon W-3275M: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- 2 x Xeon Platinum 8275CL: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- 2 x Xeon Platinum 8275CL NUMA off: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- EPYC 2 7R32: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- 2 x Xeon Platinum 8259CL: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- 2 x Xeon Platinum 8259CL NUMA off: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- Xeon Platinum 8259CL: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Details- 2 x Xeon Gold 5220R: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c- Xeon Gold 5220R: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c- Xeon Platinum 8280: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c- 2 x Xeon Platinum 8280: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c- Xeon Gold 5218: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c- Xeon Silver 4216: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c- Xeon Gold 6226R: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c- 2 x Xeon Gold 6226R: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c- 2 x Xeon Silver 4216: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c- Xeon W-3275M: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c- 2 x Xeon Platinum 8275CL: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002b- 2 x Xeon Platinum 8275CL NUMA off: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c- EPYC 2 7R32: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301034- 2 x Xeon Platinum 8259CL: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x4002f01- 2 x Xeon Platinum 8259CL NUMA off: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x4002f01- Xeon Platinum 8259CL: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x4002f01Java Details- 2 x Xeon Gold 5220R: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-2ubuntu2)- Xeon Gold 5220R: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-2ubuntu2)- Xeon Platinum 8280: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-2ubuntu2)- 2 x Xeon Platinum 8280: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-2ubuntu2)- Xeon Gold 5218: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-2ubuntu2)- Xeon Silver 4216: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-2ubuntu2)- Xeon Gold 6226R: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-2ubuntu2)- 2 x Xeon Gold 6226R: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-2ubuntu2)- 2 x Xeon Silver 4216: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-2ubuntu2)- Xeon W-3275M: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-1ubuntu119.10.1)- 2 x Xeon Platinum 8275CL: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-2ubuntu219.10)- 2 x Xeon Platinum 8275CL NUMA off: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-2ubuntu219.10)- EPYC 2 7R32: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-2ubuntu219.10)- 2 x Xeon Platinum 8259CL: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-2ubuntu219.10)- 2 x Xeon Platinum 8259CL NUMA off: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-2ubuntu219.10)- Xeon Platinum 8259CL: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-2ubuntu219.10)Python Details- 2 x Xeon Gold 5220R: + Python 3.8.2- Xeon Gold 5220R: + Python 3.8.2- Xeon Platinum 8280: + Python 3.8.2- 2 x Xeon Platinum 8280: + Python 3.8.2- Xeon Gold 5218: + Python 3.8.2- Xeon Silver 4216: + Python 3.8.2- Xeon Gold 6226R: + Python 3.8.2- 2 x Xeon Gold 6226R: + Python 3.8.2- 2 x Xeon Silver 4216: + Python 3.8.2- Xeon W-3275M: Python 2.7.17 + Python 3.7.5- 2 x Xeon Platinum 8275CL: Python 2.7.17 + Python 3.7.5- 2 x Xeon Platinum 8275CL NUMA off: Python 2.7.17 + Python 3.7.5- EPYC 2 7R32: Python 2.7.17 + Python 3.7.5- 2 x Xeon Platinum 8259CL: Python 2.7.17 + Python 3.7.5- 2 x Xeon Platinum 8259CL NUMA off: Python 2.7.17 + Python 3.7.5- Xeon Platinum 8259CL: Python 2.7.17 + Python 3.7.5Security Details- 2 x Xeon Gold 5220R: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled- Xeon Gold 5220R: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled- Xeon Platinum 8280: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled- 2 x Xeon Platinum 8280: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled- Xeon Gold 5218: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled- Xeon Silver 4216: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled- Xeon Gold 6226R: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled- 2 x Xeon Gold 6226R: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled- 2 x Xeon Silver 4216: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled- Xeon W-3275M: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled- 2 x Xeon Platinum 8275CL: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled- 2 x Xeon Platinum 8275CL NUMA off: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled- EPYC 2 7R32: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- 2 x Xeon Platinum 8259CL: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled- 2 x Xeon Platinum 8259CL NUMA off: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled- Xeon Platinum 8259CL: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabledOpenCL Details- Xeon W-3275M: GPU Compute Cores: 4352

2 x Xeon Gold 5220RXeon Gold 5220RXeon Platinum 82802 x Xeon Platinum 8280Xeon Gold 5218Xeon Silver 4216Xeon Gold 6226R2 x Xeon Gold 6226R2 x Xeon Silver 4216Xeon W-3275M2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA offEPYC 2 7R322 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA offXeon Platinum 8259CLLogarithmic Result OverviewPhoronix Test SuiteMKL-DNN DNNLArrayFireOSPrayHigh Performance Conjugate GradientLuxCoreRenderJohn The RipperEmbreeIntel MPI BenchmarksStockfishasmFishChaos Group V-RAYBlenderPostgreSQL pgbenchLAMMPS Molecular Dynamics SimulatorTimed Linux Kernel Compilationdav1dIntel Open Image DenoiseTimed LLVM CompilationSVT-AV1Timed MrBayes AnalysisTungsten RendererAppleseedBasis UniversalDeepSpeechBuild2SVT-VP9Timed GCC CompilationTimed GDB GNU Debugger CompilationMlpack BenchmarkPHPBenchNettleScikit-LearnPyBenchNumpy BenchmarklzbenchZstd CompressionRenaissanceHimeno BenchmarkRadiance BenchmarkDaCapo Benchmark

Xeon & EPYC Testsmkl-dnn: Convolution Batch conv_googlenet_v3 - u8s8f32arrayfire: Conjugate Gradient CPUarrayfire: BLAS CPUmkl-dnn: Convolution Batch conv_alexnet - f32mkl-dnn: Convolution Batch conv_all - u8s8f32mkl-dnn: Convolution Batch conv_googlenet_v3 - f32mkl-dnn: Convolution Batch conv_alexnet - u8s8f32mkl-dnn: Convolution Batch conv_all - f32mkl-dnn: Deconvolution Batch deconv_3d - f32mkl-dnn: IP Batch All - u8s8f32mkl-dnn: Convolution Batch conv_alexnet - bf16bf16bf16mkl-dnn: Convolution Batch conv_all - bf16bf16bf16mkl-dnn: Convolution Batch conv_googlenet_v3 - bf16bf16bf16ospray: NASA Streamlines - Path Tracerospray: XFrog Forest - SciVisospray: XFrog Forest - Path Tracermkl-dnn: Convolution Batch conv_3d - bf16bf16bf16ospray: NASA Streamlines - SciVismkl-dnn: Deconvolution Batch deconv_3d - bf16bf16bf16ospray: San Miguel - SciVisembree: Pathtracer ISPC - Crownospray: San Miguel - Path Tracerhpcg: embree: Pathtracer ISPC - Asian Dragonembree: Pathtracer ISPC - Asian Dragon Objmkl-dnn: Deconvolution Batch deconv_1d - f32luxcorerender: Rainbow Colors and Prismblender: Classroom - CPU-Onlynamd: ATPase Simulation - 327,506 Atomsluxcorerender: DLSCmkl-dnn: Deconvolution Batch deconv_1d - bf16bf16bf16john-the-ripper: MD5blender: Pabellon Barcelona - CPU-Onlyjohn-the-ripper: Blowfishmkl-dnn: Convolution Batch conv_3d - u8s8f32intel-mpi: IMB-P2P PingPongmkl-dnn: Deconvolution Batch deconv_1d - u8s8f32npb: EP.Dospray: Magnetic Reconnection - SciVisnpb: EP.Cmkl-dnn: Deconvolution Batch deconv_all - bf16bf16bf16mkl-dnn: Deconvolution Batch deconv_3d - u8s8f32blender: BMW27 - CPU-Onlyembree: Pathtracer - Crownstockfish: Total Timeasmfish: 1024 Hash Memory, 26 Depthv-ray: CPUembree: Pathtracer - Asian Dragonembree: Pathtracer - Asian Dragon Objblender: Fishy Cat - CPU-Onlymkl-dnn: IP Batch 1D - bf16bf16bf16mkl-dnn: IP Batch 1D - f32npb: SP.Bblender: Barbershop - CPU-Onlylammps: Rhodopsin Proteinappleseed: Disney Materialmkl-dnn: Deconvolution Batch deconv_all - f32tungsten: Hairbasis: UASTC Level 3npb: LU.Cbuild-linux-kernel: Time To Compilenpb: BT.Cdav1d: Summer Nature 1080ppgbench: Buffer Test - Normal Load - Read Onlymkl-dnn: IP Batch All - f32dav1d: Chimera 1080p 10-bitoidn: Memorialbuild-llvm: Time To Compilenpb: MG.Cdav1d: Summer Nature 4Kappleseed: Emilysvt-av1: Enc Mode 8 - 1080psvt-av1: Enc Mode 4 - 1080pmrbayes: Primate Phylogeny Analysispyperformance: python_startupmlpack: scikit_qdapgbench: Buffer Test - Normal Load - Read Writemlpack: scikit_icadeepspeech: CPUbuild2: Time To Compilemlpack: scikit_linearridgeregressionsvt-vp9: Visual Quality Optimized - Bosphorus 1080pbuild-gcc: Time To Compilebuild-gdb: Time To Compileappleseed: Material Testernettle: poly1305-aesnettle: chachanettle: aes256lzbench: Crush 0 - Decompressionphpbench: PHP Benchmark Suitepyperformance: floatpyperformance: django_templatescikit-learn: lzbench: Brotli 2 - Decompressionbasis: ETC1Slzbench: Zstd 1 - Compressionpybench: Total For Average Test Timessmhasher: wyhashsmhasher: wyhashnumpy: lzbench: Zstd 8 - Decompressioncompress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19mlpack: scikit_svmlzbench: Brotli 2 - Compressionlzbench: Zstd 1 - Decompressionnettle: sha512himeno: Poisson Pressure Solverradiance: Serialradiance: SMP Parallellzbench: Crush 0 - Compressionrenaissance: Apache Spark PageRankpyperformance: regex_compiledacapobench: Jythontungsten: Water Causticlzbench: Zstd 8 - Compressionrenaissance: Scala Dottyrenaissance: Savina Reactors.IOrenaissance: Apache Spark Bayescloverleaf: Lagrangian-Eulerian Hydrodynamics2 x Xeon Gold 5220RXeon Gold 5220RXeon Platinum 82802 x Xeon Platinum 8280Xeon Gold 5218Xeon Silver 4216Xeon Gold 6226R2 x Xeon Gold 6226R2 x Xeon Silver 4216Xeon W-3275M2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA offEPYC 2 7R322 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA offXeon Platinum 8259CL15.75429.8982359.13122.7612479.2854.819035.9778999.5442.697004.08605712.2013917.52187.16810.427.193.9815.217755.569.4259143.4833.44693.9525.630343.098337.14982.126804.46165.960.603334.447.229754821000208.30513244896.4119650424.3333330.5608903780.5947.623768.663152.413112.3660.6729.515374235829855018514027035.875732.330198.245.727912.2300950932.88260.5617.37888.8566341278.2511.072627.981108883.4036.699100761.29321.84598798.57132410.634870.8127.97286.78258984.18177.89180.64579749.2095.302134.92811.242.6934227.72490377.41125.1186372.1512.39237.571060.578146.439189.4596532797.221024.9756159.2141963128311347.310.45861354.554437110018.806300.73110110.44917.921721147489.153404.690861746.918230.5619324540.720167487723.3367747414.61926257.0083662.7671.0628.45326.4091201.54244.7454826.71108.16166.73521948.774.889664.610541433.477839.95369.2875.383.702.0629.917328.5716.825323.2617.66042.1413.352923.604220.34183.364322.48328.811.157452.3213.14282506000404.78255479696.9210276849.5217390.8437091966.6127.031863.155695.586072.57113.3016.051438167326432179392188619.610517.7957175.958.685904.4998523346.56456.479.535158.772381920.7418.984046.70856744.8759.01250787.79274.98383120.6905098.9079558.0518.41430.42631197.22160.59284.2797433.0884.285134.48311.334.2445518.59351568.19126.0780191.6412.25224.011167.683151.909162.8603532779.781020.0936133.9142862969011447.110.11265156.018444111418.815313.76119410.35517.821761180485.863398.397455749.923242.5159821704.485168483425.0080767556.32922776.2953150.0961.2811.29004.1153432.1694.19372846.1242.075826.8391765.7451.962793.23121637.3743497.47166.9849.496.253.4614.0780507.6960538.4628.77303.5214.909738.310033.04901.462324.11198.250.707093.796.553744090000246.31428645919.9416653864.7681160.3710363283.3842.873194.182935.993716.9869.8026.280062891312687620753471032.247429.2061110.674.831702.3945132682.14287.8015.314103.8330991113.5412.686330.68974255.6740.89871842.34323.20560887.7666966.7950965.4031.10308.74137089.05199.08197.64950551.9176.030128.84811.230.4553139.05777767.36118.0937774.1181.67265.401063.705144.643123.9791032867.481051.1116313.1644064916410946.29.12767351.446457107622.678330.3312248.20317.191811212501.983510.205159728.36123510120621.229164454722.0167776664.25421975.1222674.1750.967.460507.4813430.2849.84371517.4423.177219.8143496.8161.136083.11002320.0601766.3586.539118.1812.056.677.9291290.914.3581769.5253.23046.5328.854268.424158.69451.240297.15100.470.362267.194.068477880000129.01840843005.4831821690.5507250.3944556284.6571.436104.941779.151893.7238.7945.61211197157951338398966433157.487051.785366.393.659641.6398670893.41187.3324.78868.618272881.7837.8270619.885140090.3227.309136046.53409.88909916.4900869.5246685.1434.49221.51569175.12221.31154.98075256.9827.033129.98611.238.3524466.91122763.35122.2246862.7761.82233.171005.530142.695193.442412868.691051.9366320.0042864969310945.99.39262352.694449107322.677321.8211249.13717.191761168500.983514.604106728.246226.0769623588.397164471121.5896756890.60626764.9413228.6330.6934.60317.0421002.09298.3005840.26131.08881.07052363.005.804204.838751874.4710255.2484.5944.373.011.6839.998523.2621.429018.8714.41631.7513.013819.432116.76853.994881.88433.421.511681.7416.54841912667531.982140311821.39066471.04347830.9767301635.7822.221621.486721.027189.03149.3912.388232424332365618171698115.310413.8526229.288.82714.7569622329.34589.078.158182.5579721699.6922.486655.20948143.4967.15648617.05265.46322051.6311879.3095955.8815.80501.21830328.65136.86328.13913327.1933.339147.73411.137.4140894.89675668.78128.40692101.7162.46172.821218.874156.299179.7515052798.561024.4936164.7943063245511447.210.28665558.473446110119.806315.14119511.12217.981761184489.513405.035897747.844241.8979623703.029167509625.9635748286.12327198.0803477.3311.3745.05027.819765.491395.4416241.16171.428105.8263129.937.636465.592751875.2310258.0484.8953.412.341.3140.019218.1821.475514.7111.38271.4011.888315.591113.49185.310871.88432.111.517211.7716.55161893333531.392042412300.38923779.55072461.273751571.4917.941545.506721.547457.86149.0212.431631174576350854961710515.279613.8827229.7110.90145.1665821149.68593.137.810194.4018432201.0423.612958.24646723.0171.77046389.79232.35313376.77991710.193050.1012.85531.15228301.13132.46345.38996126.4603.309193.46615.440.7540373.30489481.36135.99744109.6992.97173.181398.020177.772188.7767562291.69837.6125024.3935351569713757.512.03054267.461365134222.13122004.08272.1299811.43020.89146973399.992823.595364909.318299.7398225271.433204576828.8979648634.69122798.3823588.6921.4917.97356.4512137.03155.3684478.9369.143142.22021227.073.130064.538211042.345709.17269.9915.523.682.0222.424329.4112.327122.6916.80992.0213.958122.459819.32282.231262.51321.531.135862.359.903622583000400.96271269374.6010620968.6086950.5286322094.5325.482044.243966.735864.26111.8215.994339776292446149252207419.347217.4223173.955.714394.4136623859.79453.2210.325155.228014983.91318.612944.94358594.5057.77256576.12307.75376860.3186158.8423362.3222.01433.19131633.6170.07276.76865434.6364.340123.70211.031.9646503.28304061.82119.7871788.9771.93221.951092.587139.120156.6056142795.491024.9926161.4242963243111547.39.92465354.790445110325.13419429.87318.87119310.33017.921761182488.813401.157135746.687242.0029521743.019168460924.0874746999.49727198.8562856.8501.2711.32827.1553912.3081.14002377.9136.371626.5363694.3241.707494.11779527.0172871.11137.73410.567.093.8811.607655.566.2964742.2731.73183.7126.591040.432534.80301.497244.32163.320.582374.51835.384024977667207.41534854821.2420467429.5217390.3690603969.6045.454005.262169.932987.0859.4528.960275203729838945143474934.691931.311796.413.212812.1897549232.24257.0118.15084.844108711.38910.665327.226106268.3336.59577470.67358.62587882.23269910.523973.9533.06279.68258681.42203.10177.66114851.7105.431124.25810.944.5337715.21627174.63123.3870270.6082.08256.91996.904133.444185.3571542797.431025.3846157.4941863260111347.110.44960854.947437110425.12919424.11304.16110010.20617.771721141489.423410.383938745.686233.0429124522.220167480623.1916727231.01427972.9983405.4140.9323.702816.921497.75197.9143215.1787.543455.33611578.243.855124.82603938.9105156.69246.4466.624.572.5520.516334.4810.937927.8421.74682.6323.157428.973225.06783.065903.65218.060.769823.438.869133764000272.72410216329.9417176230.5362320.7703003144.7032.532984.023600.953849.1378.7223.267460569696668958102759228.203225.4971125.355.565002.6669942220.94333.4014.161107.4980891364.2613.603134.63285606.5345.31565509.98272.55501697.23823111.421559.5120.43347.82752832.47159.60222.96851440.5484.216194.50415.450.1034916.03085294.45133.0116086.3252.99206.421268.815169.704197.7404422294.74841.6495061.6034451996413757.512.54950965.644359134322.12922011.20262.7893010.97821.09142943401.132817.673053907.757281.2518028045.920204580227.3948638583.01428596.1054199.4111.0013.45044.4233128.39108.5682967.9249.874431.9893878.3902.275263.59218702.0653880.44188.6118.695.723.1716.590645.458.4627334.4826.40103.2514.162335.149530.34581.745153.79213.360.814343.537.615953654000265.41403266183.1120246604.6231880.4584223210.52403025.113293.943852.3774.9624.550361170651662256413301430.105727.1952118.095.563042.8671531426.53304.7914.562106.6433921292.6212.710430.63469606.8436.36769347.58537.84567696.5059127.5443981.6027.35281.67835376.11256.60196.92978653.8196.389143.34817.732.6511704.23180454.91123.8525266.4151.99282.18994.583134.824124.1473013207.981172.1537070.6050973433994.549.99.66172147.65350895118.50826298.77367.5612988.38015.781961299550.933866.090988665.7219.83610921015.543157432121.5517846970.90425186.6662743.6231.1417.754913.226259.0179.11092023.4733.630559.90401206.221.173855.36708348.2431919.5093.359617.0211.366.258.7123482.624.3795263.5449.04615.828.4140538.765836.66521.331097.09108.976.733.969067388333139.11777713250.8935954425.3623190.35536250.881730.802059.0341.6841.78991098743071195499015832640.078735.667669.934.103691.95992189.5522.30168.606542981.0588.2906721.06027.100422.89629984.51425319.103090.2815.06218.050218.14152.90204955.3745.243125.86762.023890.77088253.50113.1439664.5032.36191.66966.599128.950189.2961662785.991025.6036172.5543464017311.06559252.608439113326.08618770.15338.44105310.94516.871701099487.553440.518277753.635232.6959424505.962468522.7599736733.16026906.8865185.62110.48419.6546325.0757.51111708.0525.053330.6427650.9811.172783.84746348.3261918.2893.284216.9511.366.248.6470783.334.3600266.6749.95595.876.3297151.874144.71511.251167.31108.946.753.965107350667139.00783273252.4835888907.9855070.35471458.821705.352057.9341.7241.39441084125141030339555852545.767440.850270.044.060411.63599190.0120.98468.202167910.1428.1933720.99429.258406.66725740.72379512.682090.7819.55244.910216.86152.09368156.1225.942124.29757.253197.74295453.66138.2562964.4212.46228.381032.978145.510194.8468612803.551027.5926184.2043263902611.49058253.135443112326.12918775.94315.6699910.28918.421721090490.263430.766164753.433227.1599524666.363475922.7088757042.35427361.5974510.830730.30635.13990.79896.688111728.842.54131301.36710.1402.20471149.33916.6011.035.8576.9258.8245.18694.7317.060852.354145.43302.225408.12101.340.486147.283972000132.04664753076.7620348261.0289851131.133570.46403485.991899.2441.7647.64641167650281132789776289752.953247.580665.671.6756051225.18177.7920.82162.4310471485.477.6745519.19399821.8924.005106415.53676.16891303.1219438.88390140.1428.71200.03949330.15321.17147.68585654.4725.71492.36116.339.546105.72895749.4772.8159959.9561.79291.17849.192108.675175.1937082046.35750.3574665.3338050052466.410.41956454.3104181226323.5812669.23015.161651148478.093769.723664730.7219.6528121641.954213524622.3247836577.34319303.5613057.0590.368.747948.4305319.5856.64651793.7525.772222.3830559.4681.266493.04866399.2982197.81106.89315.62510.425.719.2066576.924.8719462.546.17575.5827.106059.056350.97691.257956.40124.590.445515.884.490396554667158.13708883551.3831988149.2463770.3762225310.1662.55052.631904.282238.0547.6338.12221035138531199123575180346.792042.761379.004.489181.5768753978.90211.3322.53573.581913739.1639.2621723.088120961.9127.581104107.99431.76795715.3113559.9766989.5533.89232.05363393.35215.64161.84631453.0405.955139.75011.342.884009.40533158.48117.7261366.6672.30229.911012.035129.689185.2297342497.86917.7505513.0839457348312364.212.45955157.826399125224.15120225.18310.4010119.94918.761571027437.623147.907521841.647258.3438825275.159200517224.5437697256.92028107.0363495.6120.787.636517.6045650.7155.35651734.2025.067219.3723461.9351.263952.78193399.3082198.18106.71415.5410.325.719.1875176.924.8568961.5846.41845.5416.517159.050250.86481.225895.52124.670.454225.864.465236608333157.99709553548.6032444647.4347830.3614145284.3462.55059.021904.452252.6748.0038.10331041066761050706065305146.908442.494679.224.464401.5372938493.57211.3721.88773.216224743.6959.0907323.14794642.9929.27684766.14400.24790827.5724646.6584288.6633.10244.94043490.15212.99163.70723252.3145.996141.89822.641.293168.73208157.69135.0510069.1952.42229.531073.762146.435197.2937742516.87917.5055523.3139657434812364.112.95454358.280407125324.15420231.58293.5396610.29419.621591032438.233130.858713841.323255.5888625636.694200516124.7792717566.34228251.8283813.7460.6312.70594.6772950.16107.8043402.0748.064030.8800874.2012.200533.43236796.7534364.00207.9118.095.382.9617.321743.489.3710732.9724.72673.0013.642532.908828.29281.639283.30246.810.869253.047.982923384000305.20355997095.6216759832.260870.4156142677.6437.042641.323368.214426.0686.8921.382954437117593507942906126.063823.7192134.225.699002.6997724288.34350.4713.040120.1693461029.2414.804635.98365522.4641.13751975.35353.78512031.4192317.8907167.3327.99317.61033490.03205.63219.319746.8735.112138.84611.431.985941.31814161.20117.3569276.1472.00256.241067.641132.228127.9962962492.48920.5135517.0240456979312264.112.08858757.399410125024.18720221.25321.1310899.67218.671601061436.733152.501437842.099273.1259122226.845200501225.3555717200.75226711.1733017.3251.11OpenBenchmarking.org

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_googlenet_v3 - Data Type: u8s8f322 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M160320480640800SE +/- 0.00643, N = 3SE +/- 0.01218, N = 3SE +/- 0.02555, N = 3SE +/- 0.01740, N = 3SE +/- 0.29660, N = 3SE +/- 0.02611, N = 3SE +/- 0.03597, N = 3SE +/- 0.01146, N = 3SE +/- 7.24186, N = 3SE +/- 0.01482, N = 3SE +/- 0.02138, N = 3SE +/- 0.01762, N = 3SE +/- 0.00834, N = 3SE +/- 0.01386, N = 3SE +/- 0.02504, N = 3SE +/- 0.01662, N = 315.7542011.328208.747947.6365117.7549010.484107.4605023.70280730.3060034.6031028.4532017.9735012.7059011.2900045.0502013.45040MIN: 698.321. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

ArrayFire

ArrayFire is an GPU and CPU numeric processing library, this test uses the built-in CPU and OpenCL ArrayFire benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient CPU2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M816243240SE +/- 0.099, N = 15SE +/- 0.072, N = 15SE +/- 0.091, N = 15SE +/- 0.243, N = 15SE +/- 0.220, N = 3SE +/- 0.272, N = 15SE +/- 0.086, N = 6SE +/- 0.372, N = 15SE +/- 0.217, N = 3SE +/- 0.069, N = 9SE +/- 0.094, N = 3SE +/- 0.026, N = 3SE +/- 0.022, N = 3SE +/- 0.067, N = 3SE +/- 0.047, N = 3SE +/- 0.075, N = 159.8987.1558.4307.60413.2209.6547.48116.92035.1307.0426.4096.4514.6774.1157.8194.4231. (CXX) g++ options: -rdynamic

OpenBenchmarking.orgGFLOPS, More Is BetterArrayFire 3.7Test: BLAS CPU2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M14002800420056007000SE +/- 3.91, N = 3SE +/- 31.78, N = 3SE +/- 122.72, N = 12SE +/- 14.66, N = 3SE +/- 61.47, N = 3SE +/- 4.90, N = 3SE +/- 20.06, N = 3SE +/- 0.79, N = 3SE +/- 6.50, N = 3SE +/- 0.62, N = 3SE +/- 0.37, N = 3SE +/- 4.16, N = 3SE +/- 1.09, N = 3SE +/- 25.11, N = 3SE +/- 1.52, N = 3SE +/- 30.40, N = 32359.133912.305319.585650.716259.016325.073430.281497.75990.801002.091201.542137.032950.163432.16765.493128.391. (CXX) g++ options: -rdynamic

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_alexnet - Data Type: f322 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M90180270360450SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.23, N = 3SE +/- 0.20, N = 3SE +/- 0.88, N = 3SE +/- 0.79, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 1.13, N = 3SE +/- 0.11, N = 3SE +/- 0.16, N = 3SE +/- 0.05, N = 3SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.95, N = 3SE +/- 0.11, N = 3122.7681.1456.6555.3679.1157.5149.84197.9196.69298.30244.75155.37107.8094.19395.44108.57MIN: 121.68MIN: 79.72MIN: 74.84MIN: 195.97MIN: 93.63MIN: 297.84MIN: 242.31MIN: 154.79MIN: 106.14MIN: 93.73MIN: 390.56MIN: 102.461. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_all - Data Type: u8s8f322 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M3K6K9K12K15KSE +/- 2.07, N = 3SE +/- 10.67, N = 3SE +/- 1.51, N = 3SE +/- 0.82, N = 3SE +/- 3.97, N = 3SE +/- 0.40, N = 3SE +/- 3.12, N = 3SE +/- 23.72, N = 3SE +/- 19.01, N = 3SE +/- 1.57, N = 3SE +/- 4.48, N = 3SE +/- 7.74, N = 3SE +/- 4.13, N = 3SE +/- 1.24, N = 3SE +/- 4.87, N = 3SE +/- 15.10, N = 32479.282377.911793.751734.202023.471708.051517.443215.1711728.805840.264826.714478.933402.072846.126241.162967.92MIN: 3181.24MIN: 11565.1MIN: 5831.48MIN: 4806.63MIN: 4461.44MIN: 3393.59MIN: 2813.78MIN: 6214.68MIN: 2893.121. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_googlenet_v3 - Data Type: f322 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M4080120160200SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.10, N = 3SE +/- 0.02, N = 3SE +/- 0.17, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.19, N = 3SE +/- 0.03, N = 3SE +/- 0.24, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 354.8236.3725.7725.0733.6325.0523.1887.5442.54131.09108.1669.1448.0642.08171.4349.87MIN: 54.08MIN: 34.65MIN: 32.49MIN: 86.64MIN: 40.72MIN: 130.56MIN: 106.43MIN: 68.48MIN: 47.62MIN: 41.31MIN: 170.75MIN: 44.781. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_alexnet - Data Type: u8s8f322 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M30060090012001500SE +/- 0.03, N = 3SE +/- 0.25, N = 3SE +/- 0.24, N = 3SE +/- 0.01, N = 3SE +/- 0.73, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.14, N = 3SE +/- 2.69, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 335.9826.5422.3819.3759.9030.6419.8155.341301.3681.0766.7442.2230.8826.84105.8331.99MIN: 1286.291. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_all - Data Type: f322 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M7001400210028003500SE +/- 0.29, N = 3SE +/- 0.79, N = 3SE +/- 0.29, N = 3SE +/- 0.29, N = 3SE +/- 7.07, N = 3SE +/- 5.95, N = 3SE +/- 0.78, N = 3SE +/- 1.69, N = 3SE +/- 2.05, N = 3SE +/- 0.47, N = 3SE +/- 1.16, N = 3SE +/- 0.59, N = 3SE +/- 0.32, N = 3SE +/- 0.39, N = 3SE +/- 1.30, N = 3SE +/- 0.68, N = 3999.54694.32559.47461.941206.22650.98496.821578.24710.142363.001948.771227.07874.20765.753129.93878.39MIN: 995.71MIN: 686.24MIN: 553.8MIN: 1181.19MIN: 639.1MIN: 1571.3MIN: 700.52MIN: 2357.87MIN: 1927.2MIN: 1218.34MIN: 868.41MIN: 755.35MIN: 3085.85MIN: 819.941. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_3d - Data Type: f322 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M246810SE +/- 0.00092, N = 3SE +/- 0.00200, N = 3SE +/- 0.00118, N = 3SE +/- 0.00388, N = 3SE +/- 0.00161, N = 3SE +/- 0.00132, N = 3SE +/- 0.00373, N = 3SE +/- 0.00590, N = 3SE +/- 0.00603, N = 3SE +/- 0.01731, N = 3SE +/- 0.01927, N = 3SE +/- 0.00634, N = 3SE +/- 0.00571, N = 3SE +/- 0.00032, N = 3SE +/- 0.01443, N = 3SE +/- 0.01801, N = 32.697001.707491.266491.263951.173851.172781.136083.855122.204715.804204.889663.130062.200531.962797.636462.27526MIN: 2.66MIN: 3.82MIN: 2.14MIN: 5.77MIN: 4.84MIN: 3.1MIN: 2.17MIN: 1.95MIN: 7.57MIN: 2.121. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: IP Batch All - Data Type: u8s8f322 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M306090120150SE +/- 0.03777, N = 3SE +/- 0.03959, N = 3SE +/- 0.01481, N = 3SE +/- 0.00908, N = 3SE +/- 0.06319, N = 3SE +/- 0.01731, N = 3SE +/- 0.04146, N = 4SE +/- 0.04012, N = 3SE +/- 0.23997, N = 3SE +/- 0.00870, N = 3SE +/- 0.02448, N = 3SE +/- 0.01160, N = 3SE +/- 0.00119, N = 3SE +/- 0.00398, N = 3SE +/- 0.03131, N = 3SE +/- 0.03226, N = 34.086054.117793.048662.781935.367083.847463.110024.82603149.339004.838754.610544.538213.432363.231215.592753.59218MIN: 144.741. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_alexnet - Data Type: bf16bf16bf162 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M400800120016002000SE +/- 0.06, N = 3SE +/- 4.23, N = 3SE +/- 0.23, N = 3SE +/- 0.11, N = 3SE +/- 0.07, N = 3SE +/- 0.33, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 1.48, N = 3SE +/- 0.09, N = 3SE +/- 0.41, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 1.04, N = 3712.20527.02399.30399.31348.24348.33320.06938.911874.471433.471042.34796.75637.371875.23702.07MIN: 710.93MIN: 521.14MIN: 398.05MIN: 398.47MIN: 346.92MIN: 347.28MIN: 319.23MIN: 937.57MIN: 1873.87MIN: 1421.77MIN: 1041.43MIN: 795.52MIN: 636.97MIN: 1873.9MIN: 687.861. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_all - Data Type: bf16bf16bf162 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M2K4K6K8K10KSE +/- 3.93, N = 3SE +/- 2.73, N = 3SE +/- 0.11, N = 3SE +/- 0.30, N = 3SE +/- 0.16, N = 3SE +/- 0.26, N = 3SE +/- 1.13, N = 3SE +/- 6.81, N = 3SE +/- 0.34, N = 3SE +/- 4.68, N = 3SE +/- 0.12, N = 3SE +/- 0.11, N = 3SE +/- 0.26, N = 3SE +/- 0.35, N = 3SE +/- 0.11, N = 33917.522871.112197.812198.181919.501918.281766.355156.6910255.207839.955709.174364.003497.4710258.003880.44MIN: 3906.67MIN: 2860.81MIN: 2191.04MIN: 2191.82MIN: 1911.94MIN: 1911.42MIN: 5142.07MIN: 10250.1MIN: 7795.37MIN: 5699.77MIN: 4358.26MIN: 3490.41MIN: 10250.4MIN: 37671. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_googlenet_v3 - Data Type: bf16bf16bf162 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M100200300400500SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.42, N = 3SE +/- 0.10, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.20, N = 3187.17137.73106.89106.7193.3693.2886.54246.45484.59369.29269.99207.91166.98484.90188.61MIN: 186.33MIN: 136.67MIN: 105.9MIN: 105.9MIN: 92.35MIN: 92.44MIN: 85.56MIN: 245.49MIN: 484.13MIN: 365.68MIN: 268.99MIN: 207.27MIN: 166.21MIN: 484.15MIN: 178.561. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific 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.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: Path Tracer2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M48121620SE +/- 0.000, N = 12SE +/- 0.037, N = 3SE +/- 0.000, N = 3SE +/- 0.080, N = 3SE +/- 0.073, N = 4SE +/- 0.000, N = 12SE +/- 0.000, N = 12SE +/- 0.000, N = 12SE +/- 0.068, N = 4SE +/- 0.006, N = 3SE +/- 0.000, N = 12SE +/- 0.008, N = 4SE +/- 0.022, N = 3SE +/- 0.030, N = 3SE +/- 0.000, N = 15SE +/- 0.006, N = 1210.42010.56015.62515.54017.02016.95018.1806.62016.6004.3705.3805.5208.0909.4903.4108.690MIN: 8.47 / MAX: 10.53MIN: 8.77 / MAX: 10.75MIN: 11.11 / MAX: 15.87MIN: 14.93 / MAX: 15.87MIN: 11.76 / MAX: 17.54MIN: 16.13 / MAX: 17.54MIN: 12.2 / MAX: 18.52MIN: 5.52 / MAX: 6.76MIN: 15.87 / MAX: 16.95MIN: 4.29 / MAX: 4.44MIN: 5.29 / MAX: 5.46MIN: 5.43 / MAX: 5.62MIN: 7.94 / MAX: 8.2MIN: 9.26 / MAX: 9.62MIN: 3.33 / MAX: 3.45MIN: 8.33 / MAX: 9.01

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: SciVis2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M3691215SE +/- 0.00, N = 6SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.02, N = 7SE +/- 0.00, N = 13SE +/- 0.00, N = 13SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.04, N = 3SE +/- 0.00, N = 12SE +/- 0.00, N = 6SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 3SE +/- 0.00, N = 12SE +/- 0.00, N = 87.197.0910.4210.3211.3611.3612.054.5711.033.013.703.685.386.252.345.72MIN: 6.45 / MAX: 7.25MIN: 6.37 / MAX: 7.14MIN: 8.2 / MAX: 10.53MIN: 10.1 / MAX: 10.42MIN: 9.8 / MAX: 11.49MIN: 10.99 / MAX: 11.49MIN: 9.71 / MAX: 12.2MIN: 4.08 / MAX: 4.61MIN: 10.75 / MAX: 11.24MIN: 2.98 / MAX: 3.05MIN: 3.66 / MAX: 3.73MIN: 3.64 / MAX: 3.7MIN: 5.29 / MAX: 5.41MIN: 6.13 / MAX: 6.29MIN: 2.3 / MAX: 2.36MIN: 5.56 / MAX: 5.78

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: Path Tracer2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M246810SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.01, N = 6SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 12SE +/- 0.00, N = 5SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 6SE +/- 0.00, N = 3SE +/- 0.00, N = 6SE +/- 0.00, N = 4SE +/- 0.00, N = 3SE +/- 0.00, N = 73.983.885.715.716.256.246.672.555.851.682.062.022.963.461.313.17MIN: 3.64 / MAX: 4.02MIN: 3.57 / MAX: 3.92MIN: 5.08 / MAX: 5.78MIN: 5.59 / MAX: 5.75MIN: 5.68 / MAX: 6.29MIN: 6.1 / MAX: 6.29MIN: 5.85 / MAX: 6.76MIN: 2.28 / MAX: 2.57MIN: 5.65 / MAX: 5.99MIN: 1.67MIN: 2.04 / MAX: 2.07MIN: 2 / MAX: 2.04MIN: 2.92 / MAX: 2.99MIN: 3.41 / MAX: 3.47MIN: 1.3 / MAX: 1.32MIN: 3.09 / MAX: 3.19

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_3d - Data Type: bf16bf16bf162 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M918273645SE +/- 0.00301, N = 3SE +/- 0.00770, N = 3SE +/- 0.00172, N = 3SE +/- 0.00811, N = 3SE +/- 0.00882, N = 3SE +/- 0.00469, N = 3SE +/- 0.00328, N = 3SE +/- 0.00466, N = 3SE +/- 0.00339, N = 3SE +/- 0.01559, N = 3SE +/- 0.00584, N = 3SE +/- 0.00403, N = 3SE +/- 0.00390, N = 3SE +/- 0.00904, N = 3SE +/- 0.24390, N = 415.2177011.607609.206659.187518.712348.647077.9291220.5163039.9985029.9173022.4243017.3217014.0780040.0192016.59060MIN: 15.05MIN: 11.46MIN: 9.04MIN: 9.03MIN: 8.5MIN: 8.43MIN: 20.35MIN: 39.89MIN: 29.42MIN: 22.32MIN: 17.21MIN: 13.95MIN: 39.9MIN: 14.981. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific 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.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: SciVis2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M20406080100SE +/- 0.00, N = 15SE +/- 0.00, N = 15SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.71, N = 9SE +/- 0.00, N = 12SE +/- 0.00, N = 13SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 355.5655.5676.9276.9282.6283.3390.9134.4876.9223.2628.5729.4143.4850.0018.1845.45MIN: 24.39MIN: 19.23MIN: 27.78 / MAX: 83.33MIN: 71.43 / MAX: 83.33MIN: 26.32 / MAX: 90.91MIN: 71.43 / MAX: 90.91MIN: 29.41MIN: 18.87 / MAX: 35.71MIN: 71.43 / MAX: 83.33MIN: 22.73 / MAX: 23.81MIN: 26.32 / MAX: 29.41MIN: 26.32MIN: 37.04MIN: 43.48MIN: 17.86 / MAX: 18.52MIN: 43.48 / MAX: 47.62

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_3d - Data Type: bf16bf16bf162 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M510152025SE +/- 0.01392, N = 3SE +/- 0.00159, N = 3SE +/- 0.00712, N = 3SE +/- 0.00526, N = 3SE +/- 0.01549, N = 3SE +/- 0.00222, N = 3SE +/- 0.00369, N = 3SE +/- 0.00821, N = 3SE +/- 0.05476, N = 3SE +/- 0.00134, N = 3SE +/- 0.00297, N = 3SE +/- 0.00210, N = 3SE +/- 0.00251, N = 3SE +/- 0.02388, N = 3SE +/- 0.03985, N = 39.425916.296474.871944.856894.379524.360024.3581710.9379021.4290016.8253012.327109.371077.6960521.475508.46273MIN: 9.32MIN: 6.25MIN: 4.83MIN: 4.82MIN: 10.86MIN: 21.29MIN: 16.72MIN: 12.27MIN: 9.33MIN: 7.67MIN: 21.24MIN: 8.211. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific 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.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVis2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M1530456075SE +/- 0.00, N = 12SE +/- 0.60, N = 3SE +/- 0.00, N = 3SE +/- 0.92, N = 4SE +/- 0.54, N = 12SE +/- 0.00, N = 12SE +/- 0.62, N = 15SE +/- 0.07, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.04, N = 12SE +/- 0.36, N = 3SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 1243.4842.2762.5061.5863.5466.6769.5227.8458.8218.8723.2622.6932.9738.4614.7134.48MIN: 28.57 / MAX: 45.45MIN: 28.57 / MAX: 43.48MIN: 35.71MIN: 55.56 / MAX: 62.5MIN: 35.71 / MAX: 66.67MIN: 55.56MIN: 37.04 / MAX: 71.43MIN: 17.86 / MAX: 28.57MIN: 52.63 / MAX: 62.5MIN: 18.52 / MAX: 19.23MIN: 21.74 / MAX: 23.81MIN: 21.74 / MAX: 22.73MIN: 32.26 / MAX: 33.33MIN: 37.04MIN: 14.29 / MAX: 14.93MIN: 30.3 / MAX: 35.71

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: Crown2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M1224364860SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.38, N = 3SE +/- 0.05, N = 3SE +/- 0.49, N = 12SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 333.4531.7346.1846.4249.0549.9653.2321.7545.1914.4217.6616.8124.7328.7711.3826.40MIN: 32.87 / MAX: 34.13MIN: 31.27 / MAX: 32.36MIN: 42.99 / MAX: 47.93MIN: 45.24 / MAX: 47.89MIN: 37.93 / MAX: 51.79MIN: 48.68 / MAX: 51.86MIN: 51.36 / MAX: 55.83MIN: 21.43 / MAX: 22.13MIN: 44.15 / MAX: 46.52MIN: 14.3 / MAX: 14.63MIN: 17.5 / MAX: 17.85MIN: 16.67 / MAX: 17MIN: 24.4 / MAX: 25.05MIN: 28.26 / MAX: 29.24MIN: 11.32 / MAX: 11.49MIN: 25.71 / MAX: 26.95

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific 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.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: Path Tracer2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M246810SE +/- 0.00, N = 7SE +/- 0.00, N = 8SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 12SE +/- 0.01, N = 4SE +/- 0.01, N = 5SE +/- 0.00, N = 4SE +/- 0.01, N = 3SE +/- 0.00, N = 6SE +/- 0.00, N = 4SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 123.953.715.585.545.825.876.532.634.731.752.142.023.003.521.403.25MIN: 3.41 / MAX: 3.98MIN: 2.99 / MAX: 3.73MIN: 4.61 / MAX: 5.62MIN: 5.49 / MAX: 5.59MIN: 4.69 / MAX: 5.88MIN: 5.75 / MAX: 5.92MIN: 5.18 / MAX: 6.58MIN: 2.35 / MAX: 2.64MIN: 4.69 / MAX: 4.78MIN: 1.74 / MAX: 1.76MIN: 2.13 / MAX: 2.15MAX: 2.03MIN: 2.99 / MAX: 3.01MIN: 3.48 / MAX: 3.53MAX: 1.41MIN: 3.16 / MAX: 3.28

High Performance Conjugate Gradient

HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.12 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M714212835SE +/- 0.15366, N = 3SE +/- 0.12533, N = 3SE +/- 0.12742, N = 3SE +/- 0.00225, N = 3SE +/- 0.60187, N = 9SE +/- 0.06827, N = 7SE +/- 0.24605, N = 3SE +/- 0.00847, N = 3SE +/- 0.00395, N = 3SE +/- 0.01417, N = 3SE +/- 0.08231, N = 3SE +/- 0.02780, N = 3SE +/- 0.03425, N = 3SE +/- 0.04073, N = 3SE +/- 0.03282, N = 3SE +/- 0.15186, N = 325.6303026.5910027.1060016.517108.414056.3297128.8542023.1574017.0608013.0138013.3529013.9581013.6425014.9097011.8883014.162301. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: Asian Dragon2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M1530456075SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.12, N = 3SE +/- 0.53, N = 4SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.08, N = 343.1040.4359.0659.0538.7751.8768.4228.9752.3519.4323.6022.4632.9138.3115.5935.15MIN: 42.68 / MAX: 43.7MIN: 40.04 / MAX: 41.18MIN: 57.51 / MAX: 60.42MIN: 57.78 / MAX: 60.29MIN: 35.85 / MAX: 45.98MIN: 50.96 / MAX: 54.15MIN: 66.22 / MAX: 70.39MIN: 28.72 / MAX: 29.29MIN: 51.67 / MAX: 53.48MIN: 19.37 / MAX: 19.6MIN: 23.45 / MAX: 23.8MIN: 22.38 / MAX: 22.62MIN: 32.68 / MAX: 33.18MIN: 37.87 / MAX: 38.72MIN: 15.54 / MAX: 15.7MIN: 33.95 / MAX: 35.72

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: Asian Dragon Obj2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M1326395265SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.63, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 337.1534.8050.9850.8636.6744.7258.6925.0745.4316.7720.3419.3228.2933.0513.4930.35MIN: 36.74 / MAX: 37.69MIN: 34.51 / MAX: 35.32MIN: 49.91 / MAX: 52.27MIN: 49.88 / MAX: 52.05MIN: 34.56 / MAX: 39.51MIN: 43.9 / MAX: 46.32MIN: 56.97 / MAX: 60.91MIN: 24.86 / MAX: 25.34MIN: 44.82 / MAX: 46.53MIN: 16.69 / MAX: 16.88MIN: 20.23 / MAX: 20.53MIN: 19.25 / MAX: 19.46MIN: 28.06 / MAX: 28.6MIN: 32.72 / MAX: 33.4MIN: 13.43 / MAX: 13.59MIN: 29.95 / MAX: 30.77

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_1d - Data Type: f322 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M1.19492.38983.58474.77965.9745SE +/- 0.00174, N = 3SE +/- 0.00475, N = 3SE +/- 0.00693, N = 3SE +/- 0.00066, N = 3SE +/- 0.00979, N = 3SE +/- 0.00024, N = 3SE +/- 0.00318, N = 3SE +/- 0.00576, N = 3SE +/- 0.01972, N = 3SE +/- 0.00570, N = 3SE +/- 0.00527, N = 3SE +/- 0.00272, N = 3SE +/- 0.00097, N = 3SE +/- 0.00157, N = 3SE +/- 0.01140, N = 3SE +/- 0.01273, N = 32.126801.497241.257951.225891.331091.251161.240293.065902.225403.994883.364322.231261.639281.462325.310871.74515MIN: 2.06MIN: 1.43MIN: 1.2MIN: 1.18MIN: 1.26MIN: 1.19MIN: 1.17MIN: 2.99MIN: 2.11MIN: 3.95MIN: 3.3MIN: 2.17MIN: 1.61MIN: 1.44MIN: 5.16MIN: 1.551. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

LuxCoreRender

LuxCoreRender is an open-source physically based renderer. This test profile is focused on running LuxCoreRender on the CPU as opposed to the OpenCL version. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.3Scene: Rainbow Colors and Prism2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M246810SE +/- 0.30, N = 12SE +/- 0.13, N = 15SE +/- 0.04, N = 3SE +/- 0.37, N = 15SE +/- 0.11, N = 15SE +/- 0.05, N = 3SE +/- 0.40, N = 15SE +/- 0.00, N = 3SE +/- 0.06, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 154.464.326.405.527.097.317.153.658.121.882.482.513.304.111.883.79MIN: 1.23 / MAX: 4.91MIN: 2.71 / MAX: 4.87MIN: 5.65 / MAX: 6.54MIN: 2.11 / MAX: 6.54MIN: 5.64 / MAX: 7.47MIN: 6.62 / MAX: 7.52MIN: 2.92 / MAX: 8.11MIN: 3.56 / MAX: 3.67MIN: 7.87 / MAX: 8.3MIN: 1.85 / MAX: 1.92MIN: 2.4 / MAX: 2.53MIN: 2.44 / MAX: 2.56MIN: 3.24 / MAX: 3.33MIN: 3.96 / MAX: 4.16MIN: 1.84 / MAX: 1.92MIN: 3.45 / MAX: 3.89

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Classroom - Compute: CPU-Only2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M90180270360450SE +/- 0.18, N = 3SE +/- 0.52, N = 3SE +/- 0.06, N = 3SE +/- 0.17, N = 3SE +/- 0.11, N = 3SE +/- 0.29, N = 3SE +/- 0.26, N = 3SE +/- 0.19, N = 3SE +/- 0.40, N = 3SE +/- 0.29, N = 3SE +/- 0.39, N = 3SE +/- 0.16, N = 3SE +/- 0.14, N = 3SE +/- 0.36, N = 3SE +/- 0.20, N = 3SE +/- 0.32, N = 3165.96163.32124.59124.67108.97108.94100.47218.06101.34433.42328.81321.53246.81198.25432.11213.36

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 2.13ATPase Simulation - 327,506 Atoms2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M0.34140.68281.02421.36561.707SE +/- 0.00612, N = 3SE +/- 0.00104, N = 3SE +/- 0.00038, N = 3SE +/- 0.00012, N = 3SE +/- 0.00133, N = 3SE +/- 0.00193, N = 3SE +/- 0.00084, N = 3SE +/- 0.00100, N = 3SE +/- 0.00122, N = 3SE +/- 0.00117, N = 3SE +/- 0.00063, N = 3SE +/- 0.00060, N = 3SE +/- 0.00193, N = 3SE +/- 0.00775, N = 150.603330.582370.445510.454220.362260.769820.486141.511681.157451.135860.869250.707091.517210.81434

LuxCoreRender

LuxCoreRender is an open-source physically based renderer. This test profile is focused on running LuxCoreRender on the CPU as opposed to the OpenCL version. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.3Scene: DLSC2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M246810SE +/- 0.0120, N = 3SE +/- 0.0036, N = 3SE +/- 0.0353, N = 3SE +/- 0.0279, N = 3SE +/- 0.0262, N = 3SE +/- 0.0164, N = 3SE +/- 0.0948, N = 3SE +/- 0.0265, N = 3SE +/- 0.0970, N = 3SE +/- 0.0034, N = 3SE +/- 0.0243, N = 3SE +/- 0.0145, N = 3SE +/- 0.0050, N = 3SE +/- 0.0032, N = 3SE +/- 0.0165, N = 3SE +/- 0.0035, N = 34.44004.51835.88005.86006.73006.75007.19003.43007.28001.74002.32002.35003.04003.79001.77003.5300MIN: 4.34 / MAX: 4.63MIN: 4.4 / MAX: 4.76MIN: 5.75 / MAX: 6.19MIN: 5.7 / MAX: 6.16MIN: 6.54 / MAX: 7.08MIN: 6.62 / MAX: 7.08MIN: 6.83 / MAX: 7.6MIN: 3.33 / MAX: 3.63MIN: 7.01 / MAX: 7.86MIN: 1.67 / MAX: 1.79MIN: 2.2 / MAX: 2.43MIN: 2.24 / MAX: 2.46MIN: 2.93 / MAX: 3.16MIN: 3.65 / MAX: 3.94MIN: 1.68 / MAX: 1.85MIN: 3.46 / MAX: 3.66

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_1d - Data Type: bf16bf16bf162 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M48121620SE +/- 0.00772, N = 3SE +/- 0.00747, N = 3SE +/- 0.00489, N = 3SE +/- 0.00151, N = 3SE +/- 0.01030, N = 3SE +/- 0.00401, N = 3SE +/- 0.00661, N = 3SE +/- 0.01001, N = 3SE +/- 0.00105, N = 3SE +/- 0.04579, N = 3SE +/- 0.00392, N = 3SE +/- 0.02376, N = 3SE +/- 0.00167, N = 3SE +/- 0.00867, N = 3SE +/- 0.03740, N = 37.229755.384024.490394.465233.969063.965104.068478.8691316.5484013.142809.903627.982926.5537416.551607.61595MIN: 7.13MIN: 5.3MIN: 4.4MIN: 4.38MIN: 3.86MIN: 3.88MIN: 3.93MIN: 8.78MIN: 16.51MIN: 12.96MIN: 9.85MIN: 7.92MIN: 6.5MIN: 16.51MIN: 6.951. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: MD52 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M2M4M6M8M10MSE +/- 9643.65, N = 3SE +/- 17032.65, N = 3SE +/- 41921.89, N = 3SE +/- 11259.56, N = 3SE +/- 5783.12, N = 3SE +/- 39218.76, N = 3SE +/- 67263.16, N = 3SE +/- 4509.25, N = 3SE +/- 30550.50, N = 3SE +/- 8171.77, N = 3SE +/- 6806.86, N = 3SE +/- 11015.14, N = 3SE +/- 9073.77, N = 3SE +/- 14468.36, N = 3SE +/- 1452.97, N = 3SE +/- 14294.52, N = 348210004977667655466766083337388333735066778800003764000397200019126672506000258300033840004090000189333336540001. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Pabellon Barcelona - Compute: CPU-Only2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M120240360480600SE +/- 0.10, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.13, N = 3SE +/- 0.15, N = 3SE +/- 0.11, N = 3SE +/- 0.26, N = 3SE +/- 0.50, N = 3SE +/- 0.51, N = 3SE +/- 0.31, N = 3SE +/- 0.03, N = 3SE +/- 0.22, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.46, N = 3SE +/- 0.73, N = 3208.30207.41158.13157.99139.11139.00129.01272.72132.04531.98404.78400.96305.20246.31531.39265.41

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: Blowfish2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M20K40K60K80K100KSE +/- 12.50, N = 3SE +/- 111.31, N = 3SE +/- 107.83, N = 3SE +/- 24.01, N = 3SE +/- 465.66, N = 3SE +/- 78.50, N = 3SE +/- 700.53, N = 3SE +/- 91.33, N = 3SE +/- 203.51, N = 3SE +/- 6.03, N = 3SE +/- 77.98, N = 3SE +/- 60.93, N = 3SE +/- 8.37, N = 3SE +/- 99.39, N = 3SE +/- 24.29, N = 3SE +/- 149.28, N = 3513245348570888709557777178327840844102166475214032554727126355994286420424403261. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_3d - Data Type: u8s8f322 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M3K6K9K12K15KSE +/- 3.52, N = 3SE +/- 10.40, N = 3SE +/- 7.22, N = 3SE +/- 11.90, N = 3SE +/- 4.78, N = 3SE +/- 0.59, N = 3SE +/- 7.97, N = 3SE +/- 109.20, N = 3SE +/- 25.92, N = 3SE +/- 2.59, N = 3SE +/- 11.33, N = 3SE +/- 9.11, N = 3SE +/- 5.52, N = 3SE +/- 11.11, N = 3SE +/- 13.03, N = 3SE +/- 41.02, N = 34896.414821.243551.383548.603250.893252.483005.486329.943076.7611821.309696.929374.607095.625919.9412300.306183.11MIN: 4854.07MIN: 4760.44MIN: 3527.13MIN: 3529.41MIN: 3176.52MIN: 3175.14MIN: 2934.55MIN: 6190.58MIN: 3011.81MIN: 11811.3MIN: 9656.48MIN: 9350.22MIN: 7085.95MIN: 5895.99MIN: 12254MIN: 5934.011. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Intel MPI Benchmarks

Intel MPI Benchmarks for stressing MPI implementations. At this point the test profile aggregates results for some common MPI functionality. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage Msg/sec, More Is BetterIntel MPI Benchmarks 2019.3Test: IMB-P2P PingPong2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M8M16M24M32M40MSE +/- 12631.77, N = 3SE +/- 41319.75, N = 3SE +/- 80057.86, N = 3SE +/- 105849.64, N = 3SE +/- 12198.08, N = 3SE +/- 131246.22, N = 3SE +/- 66348.18, N = 3SE +/- 20273.79, N = 3SE +/- 40509.97, N = 3SE +/- 10529.89, N = 3SE +/- 20987.71, N = 3SE +/- 19484.28, N = 3SE +/- 30074.61, N = 3SE +/- 33688.94, N = 3SE +/- 7036.00, N = 3SE +/- 59477.15, N = 319650424.3320467429.5231988149.2532444647.4335954425.3635888907.9931821690.5517176230.5420348261.039066471.0410276849.5210620968.6116759832.2616653864.778923779.5520246604.62MIN: 8143 / MAX: 56362584MIN: 7824 / MAX: 55096192MIN: 9163 / MAX: 84595469MIN: 5770 / MAX: 85492119MIN: 2889 / MAX: 93907202MIN: 2551 / MAX: 94279351MIN: 9950 / MAX: 90956260MIN: 7391 / MAX: 46585428MIN: 6272 / MAX: 47546902MIN: 4962 / MAX: 43240261MIN: 5455 / MAX: 45833330MIN: 5167 / MAX: 521083361. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f322 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M2004006008001000SE +/- 0.002792, N = 3SE +/- 0.001915, N = 3SE +/- 0.000864, N = 3SE +/- 0.001016, N = 3SE +/- 0.001152, N = 3SE +/- 0.001652, N = 3SE +/- 0.006813, N = 3SE +/- 0.003675, N = 3SE +/- 4.136428, N = 3SE +/- 0.001460, N = 3SE +/- 0.001194, N = 3SE +/- 0.000358, N = 3SE +/- 0.000985, N = 3SE +/- 0.000361, N = 3SE +/- 0.001246, N = 3SE +/- 0.001267, N = 30.5608900.3690600.3762220.3614140.3553620.3547140.3944550.7703001131.1300000.9767300.8437090.5286320.4156140.3710361.2737500.458422MIN: 1118.791. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.D2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M13002600390052006500SE +/- 54.90, N = 4SE +/- 124.07, N = 12SE +/- 89.39, N = 3SE +/- 84.22, N = 3SE +/- 148.86, N = 12SE +/- 2.84, N = 3SE +/- 5.75, N = 3SE +/- 4.92, N = 3SE +/- 6.98, N = 3SE +/- 8.86, N = 3SE +/- 38.58, N = 4SE +/- 46.76, N = 4SE +/- 6.21, N = 3SE +/- 4.09, N = 33780.593969.605310.165284.346284.653144.703570.461635.781966.612094.532677.643283.381571.493210.521. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. 2 x Xeon Gold 5220R: Open MPI 4.0.3rc43. 2 x Xeon Gold 6226R: Open MPI 4.0.3rc44. 2 x Xeon Platinum 8259CL: Open MPI 3.1.35. 2 x Xeon Platinum 8259CL NUMA off: Open MPI 3.1.36. 2 x Xeon Platinum 8280: Open MPI 4.0.3rc47. 2 x Xeon Silver 4216: Open MPI 4.0.3rc48. EPYC 2 7R32: Open MPI 3.1.39. Xeon Gold 5218: Open MPI 4.0.3rc410. Xeon Gold 5220R: Open MPI 4.0.3rc411. Xeon Gold 6226R: Open MPI 4.0.3rc412. Xeon Platinum 8259CL: Open MPI 3.1.313. Xeon Platinum 8280: Open MPI 4.0.3rc414. Xeon Silver 4216: Open MPI 4.0.3rc415. Xeon W-3275M: Open MPI 3.1.3

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific 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.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: SciVis2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M1632486480SE +/- 0.00, N = 12SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.88, N = 3SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.27, N = 4SE +/- 0.00, N = 15SE +/- 0.00, N = 12SE +/- 0.16, N = 4SE +/- 0.00, N = 12SE +/- 0.60, N = 3SE +/- 0.08, N = 447.6245.4562.5062.5050.8858.8271.4332.5340.0022.2227.0325.4837.0442.8717.9440.00MIN: 16.67 / MAX: 50MIN: 20MIN: 18.52 / MAX: 66.67MIN: 58.82 / MAX: 66.67MIN: 16.95 / MAX: 55.56MIN: 52.63MIN: 15.87 / MAX: 76.92MIN: 14.93 / MAX: 33.33MIN: 38.46 / MAX: 41.67MIN: 21.28MIN: 24.39MIN: 24.39 / MAX: 25.64MIN: 33.33MIN: 38.46 / MAX: 43.48MIN: 16.95 / MAX: 18.18MIN: 37.04

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.C2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M13002600390052006500SE +/- 32.92, N = 3SE +/- 38.41, N = 3SE +/- 77.32, N = 3SE +/- 34.33, N = 3SE +/- 88.25, N = 3SE +/- 38.56, N = 4SE +/- 31.12, N = 3SE +/- 2.61, N = 3SE +/- 2.92, N = 3SE +/- 34.91, N = 3SE +/- 14.22, N = 3SE +/- 44.67, N = 3SE +/- 19.04, N = 5SE +/- 40.50, N = 33768.664005.265052.635059.026104.942984.023485.991621.481863.152044.242641.323194.181545.503025.111. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. 2 x Xeon Gold 5220R: Open MPI 4.0.3rc43. 2 x Xeon Gold 6226R: Open MPI 4.0.3rc44. 2 x Xeon Platinum 8259CL: Open MPI 3.1.35. 2 x Xeon Platinum 8259CL NUMA off: Open MPI 3.1.36. 2 x Xeon Platinum 8280: Open MPI 4.0.3rc47. 2 x Xeon Silver 4216: Open MPI 4.0.3rc48. EPYC 2 7R32: Open MPI 3.1.39. Xeon Gold 5218: Open MPI 4.0.3rc410. Xeon Gold 5220R: Open MPI 4.0.3rc411. Xeon Gold 6226R: Open MPI 4.0.3rc412. Xeon Platinum 8259CL: Open MPI 3.1.313. Xeon Platinum 8280: Open MPI 4.0.3rc414. Xeon Silver 4216: Open MPI 4.0.3rc415. Xeon W-3275M: Open MPI 3.1.3

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_all - Data Type: bf16bf16bf162 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M14002800420056007000SE +/- 3.03, N = 3SE +/- 5.08, N = 3SE +/- 0.13, N = 3SE +/- 0.44, N = 3SE +/- 16.35, N = 3SE +/- 3.70, N = 3SE +/- 0.87, N = 3SE +/- 3.93, N = 3SE +/- 0.83, N = 3SE +/- 3.12, N = 3SE +/- 1.02, N = 3SE +/- 0.16, N = 3SE +/- 5.43, N = 3SE +/- 0.10, N = 3SE +/- 4.61, N = 33152.412169.931904.281904.451730.801705.351779.153600.956721.025695.583966.733368.212935.996721.543293.94MIN: 3140.75MIN: 2158.31MIN: 1898.87MIN: 1899.24MIN: 1701.4MIN: 1696.57MIN: 1772.45MIN: 3588.76MIN: 6716.04MIN: 5644.95MIN: 3962.44MIN: 3365.01MIN: 2926MIN: 6717.72MIN: 3137.481. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f322 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M16003200480064008000SE +/- 3.26, N = 3SE +/- 2.41, N = 3SE +/- 3.00, N = 3SE +/- 22.00, N = 3SE +/- 0.43, N = 3SE +/- 2.13, N = 3SE +/- 5.70, N = 3SE +/- 2.28, N = 3SE +/- 3.22, N = 3SE +/- 2.58, N = 3SE +/- 5.71, N = 3SE +/- 5.07, N = 3SE +/- 0.90, N = 3SE +/- 2.14, N = 3SE +/- 0.67, N = 3SE +/- 48.27, N = 33112.362987.082238.052252.672059.032057.931893.723849.131899.247189.036072.575864.264426.063716.987457.863852.37MIN: 3107.3MIN: 2977.12MIN: 2230.65MIN: 2229.49MIN: 2054.86MIN: 2050.62MIN: 1871.79MIN: 3842.7MIN: 1888.24MIN: 7180.23MIN: 6048.56MIN: 5830.88MIN: 4423.17MIN: 3705.72MIN: 7454.84MIN: 3728.621. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: BMW27 - Compute: CPU-Only2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M306090120150SE +/- 0.13, N = 3SE +/- 0.04, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.15, N = 3SE +/- 0.10, N = 3SE +/- 0.28, N = 3SE +/- 0.23, N = 3SE +/- 0.17, N = 3SE +/- 0.14, N = 3SE +/- 0.09, N = 3SE +/- 0.29, N = 3SE +/- 0.12, N = 360.6759.4547.6348.0041.6841.7238.7978.7241.76149.39113.30111.8286.8969.80149.0274.96

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: Crown2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M1122334455SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.17, N = 3SE +/- 0.15, N = 3SE +/- 0.12, N = 3SE +/- 0.17, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 329.5228.9638.1238.1041.7941.3945.6123.2747.6512.3916.0515.9921.3826.2812.4324.55MIN: 29.05 / MAX: 30.15MIN: 28.49 / MAX: 29.56MIN: 37.03 / MAX: 39.42MIN: 37.24 / MAX: 39.22MIN: 40.7 / MAX: 42.99MIN: 40.34 / MAX: 42.73MIN: 44.2 / MAX: 47.35MIN: 23 / MAX: 23.64MIN: 46.77 / MAX: 49.17MIN: 12.32 / MAX: 12.5MIN: 15.89 / MAX: 16.22MIN: 15.9 / MAX: 16.17MIN: 21.05 / MAX: 21.63MIN: 25.64 / MAX: 26.64MIN: 12.35 / MAX: 12.55MIN: 24.09 / MAX: 24.98

Stockfish

This is a test of Stockfish, an advanced C++11 chess benchmark that can scale up to 128 CPU cores. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 9Total Time2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M30M60M90M120M150MSE +/- 316618.77, N = 3SE +/- 956232.23, N = 3SE +/- 336693.20, N = 3SE +/- 102308.18, N = 3SE +/- 734636.23, N = 3SE +/- 996126.46, N = 3SE +/- 902995.35, N = 3SE +/- 553774.93, N = 3SE +/- 1223161.47, N = 3SE +/- 188043.56, N = 3SE +/- 184471.68, N = 3SE +/- 324752.06, N = 3SE +/- 114508.53, N = 3SE +/- 829358.84, N = 3SE +/- 406404.40, N = 3SE +/- 709349.35, N = 3742358297520372910351385310410667610987430710841251411971579560569696116765028324243323816732639776292544371176289131231174576611706511. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto

asmFish

This is a test of asmFish, an advanced chess benchmark written in Assembly. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 Depth2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M30M60M90M120M150MSE +/- 107032.55, N = 3SE +/- 983078.22, N = 3SE +/- 1707658.59, N = 3SE +/- 1538634.72, N = 3SE +/- 1547569.18, N = 3SE +/- 669620.24, N = 3SE +/- 491864.96, N = 3SE +/- 49212.27, N = 3SE +/- 617926.69, N = 3SE +/- 274137.19, N = 3SE +/- 375245.33, N = 3SE +/- 606619.65, N = 3SE +/- 95127.60, N = 3SE +/- 450047.19, N = 3SE +/- 274506.10, N = 3SE +/- 845752.34, N = 485501851838945141199123571050706061195499011030339551338398966689581011327897736561817432179394461492559350794687620753508549666225641

Chaos Group V-RAY

This is a test of Chaos Group's V-RAY benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgKsamples, More Is BetterChaos Group V-RAY 4.10.07Mode: CPU2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M14K28K42K56K70KSE +/- 178.87, N = 3SE +/- 369.19, N = 3SE +/- 332.60, N = 3SE +/- 48.95, N = 3SE +/- 223.71, N = 3SE +/- 399.24, N = 3SE +/- 474.70, N = 3SE +/- 223.28, N = 3SE +/- 183.86, N = 3SE +/- 69.72, N = 3SE +/- 50.25, N = 3SE +/- 58.00, N = 3SE +/- 88.49, N = 3SE +/- 306.00, N = 3SE +/- 34.43, N = 3SE +/- 401.71, N = 340270347495180353051583265852564331275926289716981218862207429061347101710533014

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: Asian Dragon2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M1326395265SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.38, N = 3SE +/- 0.08, N = 3SE +/- 0.32, N = 3SE +/- 0.19, N = 3SE +/- 0.16, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 335.8834.6946.7946.9140.0845.7757.4928.2052.9515.3119.6119.3526.0632.2515.2830.11MIN: 35.51 / MAX: 36.33MIN: 34.44 / MAX: 35.19MIN: 44.43 / MAX: 47.97MIN: 46.17 / MAX: 47.87MIN: 37.64 / MAX: 43.58MIN: 44.89 / MAX: 47.26MIN: 55.98 / MAX: 58.87MIN: 27.97 / MAX: 28.53MIN: 52.3 / MAX: 53.84MIN: 15.25 / MAX: 15.4MIN: 19.5 / MAX: 19.79MIN: 19.28 / MAX: 19.48MIN: 25.85 / MAX: 26.28MIN: 32 / MAX: 32.54MIN: 15.18 / MAX: 15.39MIN: 29.8 / MAX: 30.54

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: Asian Dragon Obj2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M1224364860SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.34, N = 3SE +/- 0.09, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 332.3331.3142.7642.4935.6740.8551.7925.5047.5813.8517.8017.4223.7229.2113.8827.20MIN: 31.97 / MAX: 32.83MIN: 31.07 / MAX: 31.76MIN: 42.06 / MAX: 43.59MIN: 41.76 / MAX: 43.28MIN: 34.25 / MAX: 38.16MIN: 40.1 / MAX: 42.54MIN: 50.62 / MAX: 53.17MIN: 25.3 / MAX: 25.83MIN: 46.92 / MAX: 48.74MIN: 13.79 / MAX: 13.97MIN: 17.67 / MAX: 17.93MIN: 17.34 / MAX: 17.59MIN: 23.57 / MAX: 23.92MIN: 28.89 / MAX: 29.61MIN: 13.82 / MAX: 13.97MIN: 26.82 / MAX: 27.54

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Fishy Cat - Compute: CPU-Only2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M50100150200250SE +/- 0.06, N = 3SE +/- 0.20, N = 3SE +/- 0.11, N = 3SE +/- 0.14, N = 3SE +/- 0.05, N = 3SE +/- 0.13, N = 3SE +/- 0.03, N = 3SE +/- 0.19, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.16, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 398.2496.4179.0079.2269.9370.0466.39125.3565.67229.28175.95173.95134.22110.67229.71118.09

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: IP Batch 1D - Data Type: bf16bf16bf162 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M3691215SE +/- 0.02081, N = 3SE +/- 0.00482, N = 3SE +/- 0.00431, N = 3SE +/- 0.00913, N = 3SE +/- 0.00988, N = 3SE +/- 0.00386, N = 3SE +/- 0.01183, N = 3SE +/- 0.01534, N = 3SE +/- 0.00212, N = 3SE +/- 0.02077, N = 3SE +/- 0.00265, N = 3SE +/- 0.00262, N = 3SE +/- 0.00377, N = 3SE +/- 0.02765, N = 3SE +/- 0.02664, N = 35.727913.212814.489184.464404.103694.060413.659645.565008.827108.685905.714395.699004.8317010.901405.56304MIN: 5.56MIN: 2.99MIN: 4.31MIN: 4.28MIN: 3.91MIN: 3.85MIN: 3.47MIN: 5.18MIN: 8.65MIN: 8.38MIN: 5.6MIN: 5.57MIN: 4.76MIN: 10.12MIN: 5.041. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: IP Batch 1D - Data Type: f322 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M1.16252.3253.48754.655.8125SE +/- 0.02205, N = 15SE +/- 0.01296, N = 3SE +/- 0.01483, N = 15SE +/- 0.01953, N = 3SE +/- 0.02693, N = 15SE +/- 0.00571, N = 3SE +/- 0.01437, N = 15SE +/- 0.01245, N = 3SE +/- 0.00673, N = 3SE +/- 0.02145, N = 3SE +/- 0.01148, N = 3SE +/- 0.00644, N = 3SE +/- 0.00893, N = 3SE +/- 0.01072, N = 3SE +/- 0.01398, N = 3SE +/- 0.00575, N = 32.230092.189751.576871.537291.959921.635991.639862.666991.675604.756964.499854.413662.699772.394515.166582.86715MIN: 1.82MIN: 1.86MIN: 1.29MIN: 1.39MIN: 1.37MIN: 1.41MIN: 1.39MIN: 2.31MIN: 1.59MIN: 4.33MIN: 4.19MIN: 3.68MIN: 2.46MIN: 2.28MIN: 4.71MIN: 2.531. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.B2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M15K30K45K60K75KSE +/- 31.12, N = 3SE +/- 190.70, N = 3SE +/- 77.17, N = 3SE +/- 42.29, N = 3SE +/- 115.61, N = 3SE +/- 157.62, N = 3SE +/- 520.84, N = 15SE +/- 13.76, N = 3SE +/- 54.67, N = 3SE +/- 23.98, N = 3SE +/- 28.87, N = 3SE +/- 151.80, N = 3SE +/- 57.24, N = 3SE +/- 146.25, N = 350932.8849232.2453978.9038493.5770893.4142220.9451225.1822329.3423346.5623859.7924288.3432682.1421149.6831426.531. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. 2 x Xeon Gold 5220R: Open MPI 4.0.3rc43. 2 x Xeon Gold 6226R: Open MPI 4.0.3rc44. 2 x Xeon Platinum 8259CL: Open MPI 3.1.35. 2 x Xeon Platinum 8259CL NUMA off: Open MPI 3.1.36. 2 x Xeon Platinum 8280: Open MPI 4.0.3rc47. 2 x Xeon Silver 4216: Open MPI 4.0.3rc48. EPYC 2 7R32: Open MPI 3.1.39. Xeon Gold 5218: Open MPI 4.0.3rc410. Xeon Gold 5220R: Open MPI 4.0.3rc411. Xeon Gold 6226R: Open MPI 4.0.3rc412. Xeon Platinum 8259CL: Open MPI 3.1.313. Xeon Platinum 8280: Open MPI 4.0.3rc414. Xeon Silver 4216: Open MPI 4.0.3rc415. Xeon W-3275M: Open MPI 3.1.3

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Barbershop - Compute: CPU-Only2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M130260390520650SE +/- 0.30, N = 3SE +/- 0.25, N = 3SE +/- 0.16, N = 3SE +/- 0.10, N = 3SE +/- 0.15, N = 3SE +/- 0.12, N = 3SE +/- 0.40, N = 3SE +/- 0.10, N = 3SE +/- 0.49, N = 3SE +/- 0.20, N = 3SE +/- 0.20, N = 3SE +/- 0.44, N = 3SE +/- 0.10, N = 3SE +/- 0.20, N = 3SE +/- 0.17, N = 3SE +/- 0.22, N = 3260.56257.01211.33211.37189.55190.01187.33333.40177.79589.07456.47453.22350.47287.80593.13304.79

LAMMPS Molecular Dynamics Simulator

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 9Jan2020Model: Rhodopsin Protein2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M612182430SE +/- 0.046, N = 3SE +/- 0.055, N = 3SE +/- 0.332, N = 3SE +/- 0.324, N = 3SE +/- 0.155, N = 3SE +/- 0.178, N = 3SE +/- 0.251, N = 14SE +/- 0.014, N = 3SE +/- 0.372, N = 15SE +/- 0.006, N = 3SE +/- 0.018, N = 3SE +/- 0.024, N = 3SE +/- 0.083, N = 3SE +/- 0.192, N = 3SE +/- 0.021, N = 3SE +/- 0.127, N = 1517.37818.15022.53521.88722.30120.98424.78814.16120.8218.1589.53510.32513.04015.3147.81014.562-lpng -lz-lpng -lz-lpng -lz-lpng -lz-lpng -lz-lpng -lz-lpng -lz-lpng -lz-lpng -lz-ljpeg -lpng -lz1. (CXX) g++ options: -O3 -rdynamic -lfftw3 -lm

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Disney Material2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M408012016020088.8684.8473.5873.2268.6168.2068.62107.5062.43182.56158.77155.23120.17103.83194.40106.64

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_all - Data Type: f322 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M5001000150020002500SE +/- 1.51, N = 3SE +/- 0.89, N = 3SE +/- 0.85, N = 3SE +/- 0.88, N = 3SE +/- 2.10, N = 3SE +/- 0.18, N = 3SE +/- 0.39, N = 3SE +/- 0.28, N = 3SE +/- 1.29, N = 3SE +/- 0.44, N = 3SE +/- 0.74, N = 3SE +/- 0.49, N = 3SE +/- 0.97, N = 3SE +/- 0.33, N = 3SE +/- 7.40, N = 3SE +/- 16.26, N = 51278.25711.39739.16743.70981.06910.14881.781364.261485.471699.691920.74983.911029.241113.542201.041292.62MIN: 1270.58MIN: 703.37MIN: 731.99MIN: 737.27MIN: 965.05MIN: 903.49MIN: 874.01MIN: 1356.18MIN: 1462.15MIN: 1694.75MIN: 1902.55MIN: 975.96MIN: 1023.45MIN: 1108.65MIN: 2184.66MIN: 1177.91. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Tungsten Renderer

Tungsten is a C++ physically based renderer that makes use of Intel's Embree ray tracing library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Hair2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M612182430SE +/- 0.03810, N = 3SE +/- 0.05690, N = 3SE +/- 0.05659, N = 3SE +/- 0.05235, N = 3SE +/- 0.03608, N = 3SE +/- 0.03939, N = 3SE +/- 0.11249, N = 3SE +/- 0.06619, N = 3SE +/- 0.05445, N = 3SE +/- 0.02235, N = 3SE +/- 0.03525, N = 3SE +/- 0.06005, N = 3SE +/- 0.03318, N = 3SE +/- 0.03914, N = 3SE +/- 0.12220, N = 3SE +/- 0.05256, N = 311.0726010.665309.262179.090738.290678.193377.8270613.603107.6745522.4866018.9840018.6129014.8046012.6863023.6129012.71040-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a -ljpeg1. (CXX) g++ options: -std=c++0x -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512pf -mno-avx512er -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lpthread -ldl

Basis Universal

Basis Universal is a GPU texture codoec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 32 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M1326395265SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.18, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 327.9827.2323.0923.1521.0620.9919.8934.6319.1955.2146.7144.9435.9830.6958.2530.631. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.C2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M30K60K90K120K150KSE +/- 135.16, N = 3SE +/- 50.65, N = 3SE +/- 55.32, N = 3SE +/- 32.58, N = 3SE +/- 188.25, N = 3SE +/- 91.80, N = 3SE +/- 139.53, N = 3SE +/- 41.33, N = 3SE +/- 45.25, N = 3SE +/- 30.22, N = 3SE +/- 7.82, N = 3SE +/- 82.95, N = 3SE +/- 38.08, N = 3SE +/- 35.10, N = 3108883.40106268.33120961.9194642.99140090.3285606.5399821.8948143.4956744.8758594.5065522.4674255.6746723.0169606.841. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. 2 x Xeon Gold 5220R: Open MPI 4.0.3rc43. 2 x Xeon Gold 6226R: Open MPI 4.0.3rc44. 2 x Xeon Platinum 8259CL: Open MPI 3.1.35. 2 x Xeon Platinum 8259CL NUMA off: Open MPI 3.1.36. 2 x Xeon Platinum 8280: Open MPI 4.0.3rc47. 2 x Xeon Silver 4216: Open MPI 4.0.3rc48. EPYC 2 7R32: Open MPI 3.1.39. Xeon Gold 5218: Open MPI 4.0.3rc410. Xeon Gold 5220R: Open MPI 4.0.3rc411. Xeon Gold 6226R: Open MPI 4.0.3rc412. Xeon Platinum 8259CL: Open MPI 3.1.313. Xeon Platinum 8280: Open MPI 4.0.3rc414. Xeon Silver 4216: Open MPI 4.0.3rc415. Xeon W-3275M: Open MPI 3.1.3

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To Compile2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M1632486480SE +/- 0.34, N = 10SE +/- 0.37, N = 8SE +/- 0.23, N = 14SE +/- 0.37, N = 14SE +/- 0.24, N = 13SE +/- 0.38, N = 14SE +/- 0.25, N = 14SE +/- 0.41, N = 10SE +/- 0.19, N = 13SE +/- 0.88, N = 4SE +/- 0.87, N = 4SE +/- 0.88, N = 3SE +/- 0.44, N = 7SE +/- 0.42, N = 8SE +/- 0.99, N = 4SE +/- 0.35, N = 936.7036.6027.5829.2827.1029.2627.3145.3224.0167.1659.0157.7741.1440.9071.7736.37

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.C2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M30K60K90K120K150KSE +/- 42.06, N = 3SE +/- 86.40, N = 3SE +/- 107.83, N = 3SE +/- 64.74, N = 3SE +/- 78.84, N = 3SE +/- 124.40, N = 3SE +/- 500.22, N = 3SE +/- 54.74, N = 3SE +/- 44.99, N = 3SE +/- 27.55, N = 3SE +/- 15.49, N = 3SE +/- 52.95, N = 3SE +/- 4.15, N = 3SE +/- 127.07, N = 3100761.2977470.67104107.9984766.14136046.5365509.98106415.5348617.0550787.7956576.1251975.3571842.3446389.7969347.581. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. 2 x Xeon Gold 5220R: Open MPI 4.0.3rc43. 2 x Xeon Gold 6226R: Open MPI 4.0.3rc44. 2 x Xeon Platinum 8259CL: Open MPI 3.1.35. 2 x Xeon Platinum 8259CL NUMA off: Open MPI 3.1.36. 2 x Xeon Platinum 8280: Open MPI 4.0.3rc47. 2 x Xeon Silver 4216: Open MPI 4.0.3rc48. EPYC 2 7R32: Open MPI 3.1.39. Xeon Gold 5218: Open MPI 4.0.3rc410. Xeon Gold 5220R: Open MPI 4.0.3rc411. Xeon Gold 6226R: Open MPI 4.0.3rc412. Xeon Platinum 8259CL: Open MPI 3.1.313. Xeon Platinum 8280: Open MPI 4.0.3rc414. Xeon Silver 4216: Open MPI 4.0.3rc415. Xeon W-3275M: Open MPI 3.1.3

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.6.0Video Input: Summer Nature 1080p2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M150300450600750SE +/- 3.79, N = 6SE +/- 1.84, N = 3SE +/- 3.67, N = 3SE +/- 3.77, N = 15SE +/- 4.96, N = 3SE +/- 3.42, N = 3SE +/- 3.74, N = 15SE +/- 4.57, N = 3SE +/- 2.19, N = 3SE +/- 1.26, N = 3SE +/- 2.31, N = 3SE +/- 0.97, N = 3SE +/- 1.73, N = 3SE +/- 0.52, N = 3SE +/- 1.97, N = 3SE +/- 2.32, N = 3321.84358.62431.76400.24422.89406.66409.88272.55676.16265.46274.98307.75353.78323.20232.35537.84MIN: 175.96 / MAX: 365.43MIN: 196.53 / MAX: 395.24MIN: 205.51 / MAX: 479.42MIN: 106.81 / MAX: 466.09MIN: 175.85 / MAX: 474MIN: 144.68 / MAX: 463.23MIN: 126.27 / MAX: 481.12MIN: 156.69 / MAX: 307.87MIN: 302.17 / MAX: 751.14MIN: 166.24 / MAX: 288.23MIN: 160.24 / MAX: 299.46MIN: 179.63 / MAX: 337.24MIN: 207.11 / MAX: 387.94MIN: 200.79 / MAX: 358.32MIN: 133.23 / MAX: 255.75MIN: 317.28 / MAX: 605.871. (CC) gcc options: -pthread

PostgreSQL pgbench

This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read Only2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M200K400K600K800K1000KSE +/- 2029.20, N = 3SE +/- 494.87, N = 3SE +/- 2473.02, N = 3SE +/- 1194.42, N = 3SE +/- 13693.01, N = 9SE +/- 1557.39, N = 3SE +/- 10457.35, N = 3SE +/- 568.07, N = 3SE +/- 953.22, N = 3SE +/- 198.36, N = 3SE +/- 474.33, N = 3SE +/- 358.06, N = 3SE +/- 194.45, N = 3SE +/- 1625.61, N = 3SE +/- 517.49, N = 3SE +/- 3571.60, N = 3598798.57587882.23795715.31790827.57629984.51725740.72909916.49501697.24891303.12322051.63383120.69376860.32512031.42560887.77313376.78567696.511. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: IP Batch All - Data Type: f322 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M510152025SE +/- 0.02232, N = 3SE +/- 0.06373, N = 3SE +/- 0.03588, N = 3SE +/- 0.00603, N = 3SE +/- 0.07053, N = 3SE +/- 0.00546, N = 3SE +/- 0.01419, N = 3SE +/- 0.05182, N = 3SE +/- 0.01277, N = 3SE +/- 0.02892, N = 3SE +/- 0.00905, N = 3SE +/- 0.01593, N = 3SE +/- 0.03341, N = 3SE +/- 0.00854, N = 3SE +/- 0.01401, N = 3SE +/- 0.10112, N = 310.6348010.523909.976696.6584219.1030012.682009.5246611.421508.883909.309598.907958.842337.890716.7950910.193007.54439MIN: 10.26MIN: 10.17MIN: 9.62MIN: 6.25MIN: 18.63MIN: 12.39MIN: 9.28MIN: 11.02MIN: 8.36MIN: 9.16MIN: 8.69MIN: 8.73MIN: 7.76MIN: 6.68MIN: 9.79MIN: 6.711. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.6.0Video Input: Chimera 1080p 10-bit2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M306090120150SE +/- 0.47, N = 3SE +/- 0.16, N = 3SE +/- 0.04, N = 3SE +/- 0.56, N = 3SE +/- 0.44, N = 3SE +/- 0.30, N = 3SE +/- 0.07, N = 3SE +/- 0.16, N = 3SE +/- 0.60, N = 3SE +/- 0.05, N = 3SE +/- 0.14, N = 3SE +/- 0.24, N = 3SE +/- 0.13, N = 3SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 370.8173.9589.5588.6690.2890.7885.1459.51140.1455.8858.0562.3267.3365.4050.1081.60MIN: 54.24 / MAX: 115.34MIN: 55.51 / MAX: 119.74MIN: 69.22 / MAX: 130.8MIN: 69.45 / MAX: 129.53MIN: 71.05 / MAX: 131.54MIN: 71.49 / MAX: 131.32MIN: 66.74 / MAX: 126.85MIN: 45.13 / MAX: 93.29MIN: 101.2 / MAX: 212.94MIN: 40.96 / MAX: 112.64MIN: 42.73 / MAX: 119.59MIN: 45.27 / MAX: 134.22MIN: 49.41 / MAX: 122.02MIN: 49.2 / MAX: 111MIN: 36.69 / MAX: 102.49MIN: 55.07 / MAX: 147.521. (CC) gcc options: -pthread

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.0.0Scene: Memorial2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M816243240SE +/- 0.05, N = 3SE +/- 0.36, N = 3SE +/- 0.12, N = 3SE +/- 0.21, N = 3SE +/- 0.13, N = 3SE +/- 0.04, N = 3SE +/- 0.17, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.30, N = 327.9733.0633.8933.1015.0619.5534.4920.4328.7115.8018.4122.0127.9931.1012.8527.35

Timed LLVM Compilation

This test times how long it takes to build the LLVM compiler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 10.0Time To Compile2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M110220330440550SE +/- 2.03, N = 3SE +/- 3.51, N = 3SE +/- 1.13, N = 3SE +/- 1.40, N = 3SE +/- 1.63, N = 3SE +/- 3.50, N = 3SE +/- 1.01, N = 3SE +/- 1.73, N = 3SE +/- 0.72, N = 3SE +/- 3.37, N = 3SE +/- 1.84, N = 3SE +/- 2.13, N = 3SE +/- 5.07, N = 3SE +/- 4.79, N = 3SE +/- 2.53, N = 3SE +/- 2.68, N = 3286.78279.68232.05244.94218.05244.91221.52347.83200.04501.22430.43433.19317.61308.74531.15281.68

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.C2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M15K30K45K60K75KSE +/- 464.43, N = 3SE +/- 193.70, N = 3SE +/- 304.73, N = 3SE +/- 420.94, N = 3SE +/- 860.82, N = 5SE +/- 151.51, N = 3SE +/- 796.48, N = 3SE +/- 36.97, N = 3SE +/- 114.95, N = 3SE +/- 27.89, N = 3SE +/- 114.90, N = 3SE +/- 129.93, N = 3SE +/- 69.19, N = 3SE +/- 40.04, N = 358984.1858681.4263393.3543490.1569175.1252832.4749330.1530328.6531197.2231633.6033490.0337089.0528301.1335376.111. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. 2 x Xeon Gold 5220R: Open MPI 4.0.3rc43. 2 x Xeon Gold 6226R: Open MPI 4.0.3rc44. 2 x Xeon Platinum 8259CL: Open MPI 3.1.35. 2 x Xeon Platinum 8259CL NUMA off: Open MPI 3.1.36. 2 x Xeon Platinum 8280: Open MPI 4.0.3rc47. 2 x Xeon Silver 4216: Open MPI 4.0.3rc48. EPYC 2 7R32: Open MPI 3.1.39. Xeon Gold 5218: Open MPI 4.0.3rc410. Xeon Gold 5220R: Open MPI 4.0.3rc411. Xeon Gold 6226R: Open MPI 4.0.3rc412. Xeon Platinum 8259CL: Open MPI 3.1.313. Xeon Platinum 8280: Open MPI 4.0.3rc414. Xeon Silver 4216: Open MPI 4.0.3rc415. Xeon W-3275M: Open MPI 3.1.3

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.6.0Video Input: Summer Nature 4K2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M70140210280350SE +/- 0.84, N = 3SE +/- 1.66, N = 3SE +/- 1.73, N = 3SE +/- 1.78, N = 3SE +/- 1.14, N = 3SE +/- 0.62, N = 3SE +/- 3.68, N = 3SE +/- 1.81, N = 3SE +/- 0.98, N = 3SE +/- 0.30, N = 3SE +/- 0.78, N = 3SE +/- 1.20, N = 3SE +/- 1.31, N = 3SE +/- 1.15, N = 3SE +/- 0.15, N = 3SE +/- 1.20, N = 3177.89203.10215.64212.99218.14216.86221.31159.60321.17136.86160.59170.07205.63199.08132.46256.60MIN: 103.41 / MAX: 190.93MIN: 119.16 / MAX: 222.17MIN: 93.88 / MAX: 236.99MIN: 89.5 / MAX: 233.99MIN: 105.24 / MAX: 238.99MIN: 97.39 / MAX: 239.16MIN: 81.4 / MAX: 247.6MIN: 100.88 / MAX: 178.21MIN: 150.11 / MAX: 347.95MIN: 107.86 / MAX: 153.94MIN: 110.85 / MAX: 181MIN: 115.59 / MAX: 193.75MIN: 134.32 / MAX: 229.88MIN: 121.12 / MAX: 214.69MIN: 104.21 / MAX: 150.6MIN: 164.1 / MAX: 284.351. (CC) gcc options: -pthread

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Emily2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M80160240320400180.65177.66161.85163.71152.90152.09154.98222.97147.69328.14284.28276.77219.32197.65345.39196.93

SVT-AV1

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080p2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M1326395265SE +/- 0.18, N = 3SE +/- 0.25, N = 3SE +/- 0.13, N = 3SE +/- 0.29, N = 3SE +/- 0.17, N = 3SE +/- 0.48, N = 3SE +/- 0.67, N = 3SE +/- 0.11, N = 3SE +/- 0.77, N = 3SE +/- 0.06, N = 3SE +/- 0.13, N = 3SE +/- 0.09, N = 3SE +/- 0.35, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.46, N = 349.2151.7153.0452.3155.3756.1256.9840.5554.4727.1933.0934.6446.8751.9226.4653.821. (CXX) g++ options: -fPIE -fPIC -pie

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080p2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M246810SE +/- 0.019, N = 3SE +/- 0.009, N = 3SE +/- 0.002, N = 3SE +/- 0.075, N = 4SE +/- 0.041, N = 3SE +/- 0.046, N = 3SE +/- 0.064, N = 3SE +/- 0.010, N = 3SE +/- 0.072, N = 5SE +/- 0.003, N = 3SE +/- 0.014, N = 3SE +/- 0.018, N = 3SE +/- 0.052, N = 3SE +/- 0.032, N = 3SE +/- 0.021, N = 3SE +/- 0.023, N = 35.3025.4315.9555.9965.2435.9427.0334.2165.7143.3394.2854.3405.1126.0303.3096.3891. (CXX) g++ options: -fPIE -fPIC -pie

Timed MrBayes Analysis

This test performs a bayesian analysis of a set of primate genome sequences in order to estimate their phylogeny. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny Analysis2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M4080120160200SE +/- 0.27, N = 3SE +/- 0.25, N = 3SE +/- 0.32, N = 3SE +/- 1.87, N = 3SE +/- 1.63, N = 5SE +/- 0.03, N = 3SE +/- 0.37, N = 3SE +/- 0.67, N = 3SE +/- 0.68, N = 3SE +/- 0.44, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.18, N = 3SE +/- 0.01, N = 3SE +/- 0.15, N = 3SE +/- 0.13, N = 3134.93124.26139.75141.90125.87124.30129.99194.5092.36147.73134.48123.70138.85128.85193.47143.35-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mmpx-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mmpx-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mmpx-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mmpx-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mmpx-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mmpx-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mmpx-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mmpx-msse4a -msha-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mmpx-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mmpx-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mmpx-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mmpx-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mmpx-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mmpx-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mmpx -lreadline1. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: python_startup2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M510152025SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 3SE +/- 0.00, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 311.210.911.322.611.215.416.311.111.311.011.411.215.417.7

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qda2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M1428425670SE +/- 0.63, N = 3SE +/- 0.21, N = 3SE +/- 0.54, N = 12SE +/- 0.19, N = 3SE +/- 1.16, N = 9SE +/- 0.54, N = 3SE +/- 0.34, N = 3SE +/- 0.51, N = 12SE +/- 0.28, N = 3SE +/- 0.43, N = 6SE +/- 0.49, N = 4SE +/- 0.46, N = 3SE +/- 0.12, N = 3SE +/- 0.29, N = 3SE +/- 0.39, N = 3SE +/- 0.18, N = 342.6944.5342.8841.2962.0257.2538.3550.1039.5437.4134.2431.9631.9830.4540.7532.65

PostgreSQL pgbench

This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read Write2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M11K22K33K44K55KSE +/- 158.35, N = 3SE +/- 119.26, N = 3SE +/- 56.30, N = 3SE +/- 408.27, N = 6SE +/- 141.57, N = 6SE +/- 38.08, N = 3SE +/- 19.82, N = 3SE +/- 220.44, N = 3SE +/- 319.58, N = 12SE +/- 1.34, N = 3SE +/- 54.71, N = 3SE +/- 56.97, N = 3SE +/- 245.15, N = 12SE +/- 370.72, N = 3SE +/- 132.22, N = 3SE +/- 85.02, N = 334227.7237715.224009.413168.733890.773197.7424466.9134916.036105.7340894.9045518.5946503.285941.3253139.0640373.3011704.231. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_ica2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M20406080100SE +/- 1.07, N = 4SE +/- 0.30, N = 3SE +/- 0.80, N = 3SE +/- 0.35, N = 3SE +/- 0.51, N = 15SE +/- 0.26, N = 3SE +/- 0.59, N = 3SE +/- 1.29, N = 3SE +/- 0.48, N = 15SE +/- 0.44, N = 3SE +/- 0.25, N = 3SE +/- 0.45, N = 3SE +/- 0.34, N = 3SE +/- 0.21, N = 3SE +/- 0.80, N = 3SE +/- 0.11, N = 377.4174.6358.4857.6953.5053.6663.3594.4549.4768.7868.1961.8261.2067.3681.3654.91

DeepSpeech

Mozilla DeepSpeech is a speech-to-text engine powered by TensorFlow for machine learning and derived from Baidu's Deep Speech research paper. This test profile times the speech-to-text process for a roughly three minute audio recording. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPU2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M306090120150SE +/- 0.47, N = 3SE +/- 0.89, N = 3SE +/- 0.65, N = 3SE +/- 1.04, N = 3SE +/- 1.06, N = 3SE +/- 2.07, N = 4SE +/- 1.16, N = 3SE +/- 0.71, N = 3SE +/- 0.08, N = 3SE +/- 0.75, N = 3SE +/- 1.11, N = 3SE +/- 1.84, N = 3SE +/- 1.18, N = 8SE +/- 1.60, N = 3SE +/- 1.22, N = 3SE +/- 0.15, N = 3125.12123.39117.73135.05113.14138.26122.22133.0172.82128.41126.08119.79117.36118.09136.00123.85

Build2

This test profile measures the time to bootstrap/install the build2 C++ build toolchain from source. Build2 is a cross-platform build toolchain for C/C++ code and features Cargo-like features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.12Time To Compile2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M20406080100SE +/- 0.13, N = 3SE +/- 0.09, N = 3SE +/- 0.49, N = 3SE +/- 0.19, N = 3SE +/- 0.75, N = 6SE +/- 0.09, N = 3SE +/- 0.09, N = 3SE +/- 0.11, N = 3SE +/- 0.40, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.13, N = 3SE +/- 0.15, N = 3SE +/- 0.14, N = 372.1570.6166.6769.2064.5064.4262.7886.3359.96101.7291.6488.9876.1574.12109.7066.42

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregression2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M0.67281.34562.01842.69123.364SE +/- 0.06, N = 12SE +/- 0.04, N = 15SE +/- 0.02, N = 15SE +/- 0.02, N = 12SE +/- 0.04, N = 15SE +/- 0.03, N = 15SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 7SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 15SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 32.392.082.302.422.362.461.822.991.792.462.251.932.001.672.971.99

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: Visual Quality Optimized - Input: Bosphorus 1080p2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M60120180240300SE +/- 2.14, N = 3SE +/- 3.77, N = 4SE +/- 8.04, N = 12SE +/- 8.15, N = 12SE +/- 5.20, N = 12SE +/- 8.25, N = 12SE +/- 2.89, N = 4SE +/- 1.51, N = 3SE +/- 2.49, N = 3SE +/- 1.79, N = 3SE +/- 1.23, N = 3SE +/- 3.10, N = 3SE +/- 1.36, N = 3SE +/- 3.65, N = 4SE +/- 2.39, N = 3SE +/- 0.97, N = 3237.57256.91229.91229.53191.66228.38233.17206.42291.17172.82224.01221.95256.24265.40173.18282.181. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -lm

Timed GCC Compilation

This test times how long it takes to build the GNU Compiler Collection (GCC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GCC Compilation 9.3.0Time To Compile2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M30060090012001500SE +/- 1.42, N = 3SE +/- 0.70, N = 3SE +/- 0.68, N = 3SE +/- 1.08, N = 3SE +/- 5.92, N = 3SE +/- 1.25, N = 3SE +/- 0.24, N = 3SE +/- 0.64, N = 3SE +/- 0.63, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.43, N = 3SE +/- 0.67, N = 3SE +/- 0.29, N = 3SE +/- 1.02, N = 3SE +/- 0.44, N = 31060.58996.901012.041073.76966.601032.981005.531268.82849.191218.871167.681092.591067.641063.711398.02994.58

Timed GDB GNU Debugger Compilation

This test times how long it takes to build the GNU Debugger (GDB) in a default configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 9.1Time To Compile2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M4080120160200SE +/- 0.09, N = 3SE +/- 0.16, N = 3SE +/- 0.45, N = 3SE +/- 0.27, N = 3SE +/- 0.37, N = 3SE +/- 0.25, N = 3SE +/- 0.17, N = 3SE +/- 0.18, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.11, N = 3SE +/- 0.17, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 3146.44133.44129.69146.44128.95145.51142.70169.70108.68156.30151.91139.12132.23144.64177.77134.82

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Material Tester2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M4080120160200189.46185.36185.23197.29189.30194.85193.44197.74175.19179.75162.86156.61128.00123.98188.78124.15

Nettle

GNU Nettle is a low-level cryptographic library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.5.1Test: poly1305-aes2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M7001400210028003500SE +/- 0.92, N = 3SE +/- 0.50, N = 3SE +/- 15.23, N = 3SE +/- 0.36, N = 3SE +/- 17.33, N = 3SE +/- 1.01, N = 3SE +/- 1.10, N = 3SE +/- 1.74, N = 3SE +/- 0.71, N = 3SE +/- 0.60, N = 3SE +/- 5.86, N = 3SE +/- 2.79, N = 3SE +/- 12.50, N = 3SE +/- 0.87, N = 3SE +/- 3.38, N = 3SE +/- 24.77, N = 32797.222797.432497.862516.872785.992803.552868.692294.742046.352798.562779.782795.492492.482867.482291.693207.981. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.5.1Test: chacha2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M30060090012001500SE +/- 0.41, N = 3SE +/- 0.61, N = 3SE +/- 4.50, N = 3SE +/- 4.18, N = 3SE +/- 1.27, N = 3SE +/- 0.48, N = 3SE +/- 0.37, N = 3SE +/- 0.18, N = 3SE +/- 0.08, N = 3SE +/- 0.76, N = 3SE +/- 1.02, N = 3SE +/- 0.49, N = 3SE +/- 1.52, N = 3SE +/- 0.86, N = 3SE +/- 0.91, N = 3SE +/- 5.99, N = 31024.981025.38917.75917.511025.601027.591051.94841.65750.361024.491020.091024.99920.511051.11837.611172.15MIN: 518.14 / MAX: 2797.53MIN: 522.31 / MAX: 2798.89MIN: 461.99 / MAX: 2517.41MIN: 463.47 / MAX: 2517.16MIN: 515.88 / MAX: 2805.16MIN: 523.28 / MAX: 2803.78MIN: 535.04 / MAX: 2870.94MIN: 428.69 / MAX: 2296.48MIN: 382.32 / MAX: 2047.21MIN: 507.67 / MAX: 2797.4MIN: 519.31 / MAX: 2788.96MIN: 521.91 / MAX: 2799.45MIN: 461.1 / MAX: 2517.2MIN: 532.77 / MAX: 2871.25MIN: 423.28 / MAX: 2294.55MIN: 567.45 / MAX: 3234.291. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.5.1Test: aes2562 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M15003000450060007500SE +/- 2.26, N = 3SE +/- 8.42, N = 3SE +/- 24.71, N = 3SE +/- 5.89, N = 3SE +/- 4.53, N = 3SE +/- 1.10, N = 3SE +/- 3.29, N = 3SE +/- 1.63, N = 3SE +/- 0.67, N = 3SE +/- 1.48, N = 3SE +/- 2.03, N = 3SE +/- 6.01, N = 3SE +/- 20.53, N = 3SE +/- 7.98, N = 3SE +/- 11.26, N = 3SE +/- 39.45, N = 36159.216157.495513.085523.316172.556184.206320.005061.604665.336164.796133.916161.425517.026313.165024.397070.60MIN: 4154.94 / MAX: 10200.04MIN: 4104.14 / MAX: 10212.45MIN: 3744.15 / MAX: 9173.02MIN: 3739.77 / MAX: 9132.41MIN: 4118.12 / MAX: 10228.73MIN: 4170.96 / MAX: 10241.48MIN: 4254.97 / MAX: 10469.4MIN: 3412.46 / MAX: 8379.01MIN: 3372.31 / MAX: 7239.74MIN: 4152.92 / MAX: 10208.98MIN: 4136.23 / MAX: 10160.8MIN: 4158.08 / MAX: 10213.08MIN: 3740.26 / MAX: 9153.64MIN: 4256.89 / MAX: 10467.36MIN: 3388.65 / MAX: 8334.48MIN: 4721.3 / MAX: 11806.111. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Crush 0 - Process: Decompression2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M110220330440550SE +/- 0.33, N = 34194183943964344324283443804304284294044403535091. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

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. The number of iterations used is 1,000,000. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark Suite2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M160K320K480K640K800KSE +/- 914.97, N = 3SE +/- 164.78, N = 3SE +/- 961.65, N = 3SE +/- 377.70, N = 3SE +/- 144.16, N = 3SE +/- 312.21, N = 3SE +/- 884.68, N = 3SE +/- 200.00, N = 3SE +/- 1283.26, N = 3SE +/- 786.96, N = 3SE +/- 862.18, N = 3SE +/- 752.01, N = 3SE +/- 778.31, N = 3SE +/- 425.09, N = 3SE +/- 1865.15, N = 3SE +/- 1014.34, N = 3631283632601573483574348640173639026649693519964500524632455629690632431569793649164515697734339

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: float2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M306090120150SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.12, N = 3113.0113.0123.0123.0109.0137.0114.0114.0115.0122.0109.0137.094.5

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: django_template2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M1530456075SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.00, N = 3SE +/- 0.67, N = 347.347.164.264.145.957.566.447.247.147.364.146.257.549.9

Scikit-Learn

Scikit-learn is a Python module for machine learning Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.22.12 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M3691215SE +/- 0.024, N = 3SE +/- 0.055, N = 3SE +/- 0.039, N = 3SE +/- 0.043, N = 3SE +/- 0.052, N = 3SE +/- 0.032, N = 3SE +/- 0.122, N = 3SE +/- 0.035, N = 3SE +/- 0.037, N = 3SE +/- 0.041, N = 3SE +/- 0.034, N = 3SE +/- 0.029, N = 3SE +/- 0.056, N = 3SE +/- 0.042, N = 3SE +/- 0.028, N = 3SE +/- 0.035, N = 310.45810.44912.45912.95411.06511.4909.39212.54910.41910.28610.1129.92412.0889.12712.0309.661

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Brotli 2 - Process: Decompression2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M160320480640800SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 1.20, N = 3SE +/- 1.00, N = 3SE +/- 1.33, N = 3SE +/- 0.88, N = 3SE +/- 0.67, N = 3SE +/- 5.03, N = 3SE +/- 0.88, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 1.45, N = 36136085515435925826235095646556516535876735427211. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

Basis Universal

Basis Universal is a GPU texture codoec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: ETC1S2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M1530456075SE +/- 0.21, N = 3SE +/- 0.18, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.15, N = 3SE +/- 0.04, N = 3SE +/- 0.11, N = 3SE +/- 0.14, N = 3SE +/- 0.03, N = 3SE +/- 0.31, N = 3SE +/- 0.23, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.12, N = 3SE +/- 0.08, N = 3SE +/- 0.48, N = 354.5554.9557.8358.2852.6153.1452.6965.6454.3158.4756.0254.7957.4051.4567.4647.651. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Zstd 1 - Process: Compression2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M110220330440550SE +/- 2.33, N = 3SE +/- 2.33, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 1.00, N = 34374373994074394434493594184464444454104573655081. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

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 Times2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M30060090012001500SE +/- 1.45, N = 3SE +/- 0.67, N = 3SE +/- 1.00, N = 3SE +/- 1.33, N = 3SE +/- 4.73, N = 3SE +/- 0.88, N = 3SE +/- 1.00, N = 3SE +/- 0.67, N = 3SE +/- 3.18, N = 3SE +/- 12.17, N = 3SE +/- 3.06, N = 3SE +/- 0.67, N = 3SE +/- 1.15, N = 3SE +/- 0.58, N = 3SE +/- 1.45, N = 3110011041252125311331123107313431226110111141103125010761342951

SMHasher

SMHasher is a hash function tester. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: wyhash2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M612182430SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 318.8125.1324.1524.1526.0926.1322.6822.1319.8118.8225.1324.1922.6822.1318.511. (CXX) g++ options: -march=native -O3 -lpthread

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: wyhash2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Silver 4216Xeon Gold 6226RXeon Platinum 8259CLXeon Silver 4216Xeon W-3275M6K12K18K24K30KSE +/- 4.48, N = 3SE +/- 6.86, N = 3SE +/- 0.70, N = 3SE +/- 4.38, N = 3SE +/- 4.81, N = 3SE +/- 4.76, N = 3SE +/- 5.65, N = 3SE +/- 8.73, N = 3SE +/- 0.31, N = 3SE +/- 105.54, N = 319424.1120225.1820231.5818770.1518775.9422011.2019429.8720221.2522004.0826298.771. (CXX) g++ options: -march=native -O3 -lpthread

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy Benchmark2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M80160240320400SE +/- 0.65, N = 3SE +/- 1.46, N = 3SE +/- 0.76, N = 3SE +/- 3.32, N = 3SE +/- 2.37, N = 3SE +/- 4.26, N = 3SE +/- 3.00, N = 3SE +/- 1.91, N = 3SE +/- 1.14, N = 3SE +/- 2.01, N = 3SE +/- 3.23, N = 3SE +/- 0.54, N = 3SE +/- 0.75, N = 3SE +/- 2.42, N = 3SE +/- 0.89, N = 3SE +/- 2.73, N = 3300.73304.16310.40293.53338.44315.66321.82262.78323.58315.14313.76318.87321.13330.33272.12367.56

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Zstd 8 - Process: Decompression2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M30060090012001500SE +/- 1.53, N = 3SE +/- 1.53, N = 3SE +/- 11.50, N = 3SE +/- 0.67, N = 3SE +/- 1.53, N = 3SE +/- 1.86, N = 3SE +/- 1.33, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.58, N = 3SE +/- 1.53, N = 3SE +/- 1.45, N = 31101110010119661053999112493012661195119411931089122499812981. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

Zstd Compression

This test measures the time needed to compress a sample file (an Ubuntu file-system image) using Zstd compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterZstd Compression 1.3.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 192 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M3691215SE +/- 0.117, N = 3SE +/- 0.096, N = 3SE +/- 0.094, N = 15SE +/- 0.128, N = 5SE +/- 0.114, N = 15SE +/- 0.138, N = 5SE +/- 0.148, N = 3SE +/- 0.104, N = 15SE +/- 0.062, N = 15SE +/- 0.029, N = 3SE +/- 0.021, N = 3SE +/- 0.056, N = 3SE +/- 0.128, N = 3SE +/- 0.016, N = 3SE +/- 0.075, N = 3SE +/- 0.023, N = 310.44910.2069.94910.29410.94510.2899.13710.9789.23011.12210.35510.3309.6728.20311.4308.380-llzma1. (CC) gcc options: -O3 -pthread -lz

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svm2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M510152025SE +/- 0.04, N = 3SE +/- 0.13, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.19, N = 317.9217.7718.7619.6216.8718.4217.1921.0915.1617.9817.8217.9218.6717.1920.8915.78

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Brotli 2 - Process: Compression2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M4080120160200SE +/- 1.33, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 31721721571591701721761421651761761761601811461961. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Zstd 1 - Process: Decompression2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M30060090012001500SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 2.00, N = 3SE +/- 1.33, N = 3SE +/- 0.33, N = 3SE +/- 2.65, N = 3114711411027103210991090116894311481184118011821061121297312991. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

Nettle

GNU Nettle is a low-level cryptographic library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.5.1Test: sha5122 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M120240360480600SE +/- 0.19, N = 3SE +/- 0.11, N = 3SE +/- 2.61, N = 3SE +/- 1.80, N = 3SE +/- 2.94, N = 3SE +/- 0.61, N = 3SE +/- 0.97, N = 3SE +/- 0.28, N = 3SE +/- 0.28, N = 3SE +/- 0.19, N = 3SE +/- 1.03, N = 3SE +/- 0.77, N = 3SE +/- 2.12, N = 3SE +/- 0.15, N = 3SE +/- 0.56, N = 3SE +/- 2.72, N = 3489.15489.42437.62438.23487.55490.26500.98401.13478.09489.51485.86488.81436.73501.98399.99550.931. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto

Himeno Benchmark

The Himeno benchmark is a linear solver of pressure Poisson using a point-Jacobi method. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure Solver2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M8001600240032004000SE +/- 5.10, N = 3SE +/- 0.77, N = 3SE +/- 1.57, N = 3SE +/- 2.97, N = 3SE +/- 0.96, N = 3SE +/- 1.27, N = 3SE +/- 5.39, N = 3SE +/- 1.18, N = 3SE +/- 22.45, N = 3SE +/- 1.15, N = 3SE +/- 1.90, N = 3SE +/- 1.26, N = 3SE +/- 1.29, N = 3SE +/- 4.11, N = 3SE +/- 1.23, N = 3SE +/- 3.72, N = 33404.693410.383147.913130.863440.523430.773514.602817.673769.723405.043398.403401.163152.503510.212823.603866.091. (CC) gcc options: -O3 -mavx2

Radiance Benchmark

This is a benchmark of NREL Radiance, a synthetic imaging system that is open-source and developed by the Lawrence Berkeley National Laboratory in California. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRadiance Benchmark 5.0Test: Serial2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M2004006008001000746.92745.69841.65841.32753.64753.43728.25907.76730.70747.84749.92746.69842.10728.36909.32665.70

OpenBenchmarking.orgSeconds, Fewer Is BetterRadiance Benchmark 5.0Test: SMP Parallel2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M70140210280350230.56233.04258.34255.59232.70227.16226.08281.25219.65241.90242.52242.00273.13235.00299.74219.84

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Crush 0 - Process: Compression2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M20406080100SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 1.00, N = 393918886949596808196989591101821091. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark PageRank2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M6K12K18K24K30KSE +/- 255.27, N = 5SE +/- 165.91, N = 5SE +/- 278.82, N = 5SE +/- 232.21, N = 5SE +/- 181.72, N = 25SE +/- 286.23, N = 5SE +/- 286.23, N = 6SE +/- 374.59, N = 5SE +/- 198.48, N = 5SE +/- 172.76, N = 5SE +/- 217.63, N = 5SE +/- 29.95, N = 5SE +/- 154.16, N = 5SE +/- 169.44, N = 5SE +/- 195.96, N = 5SE +/- 165.27, N = 524540.7224522.2225275.1625636.6924505.9624666.3623588.4028045.9221641.9523703.0321704.4921743.0222226.8520621.2325271.4321015.54

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: regex_compile2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M50100150200250SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 1.20, N = 3167167200200164204213167168168200164204157

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Jython2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M12002400360048006000SE +/- 23.48, N = 4SE +/- 35.02, N = 4SE +/- 56.00, N = 4SE +/- 11.32, N = 4SE +/- 21.20, N = 4SE +/- 14.64, N = 4SE +/- 19.30, N = 4SE +/- 36.99, N = 4SE +/- 10.59, N = 4SE +/- 26.49, N = 4SE +/- 11.58, N = 4SE +/- 22.03, N = 4SE +/- 15.39, N = 4SE +/- 10.79, N = 4SE +/- 10.08, N = 44877480651725161468547594711580252465096483446095012454757684321

Tungsten Renderer

Tungsten is a C++ physically based renderer that makes use of Intel's Embree ray tracing library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Water Caustic2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M714212835SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.17, N = 3SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 323.3423.1924.5424.7822.7622.7121.5927.3922.3225.9625.0124.0925.3622.0228.9021.55-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a -ljpeg1. (CXX) g++ options: -std=c++0x -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512pf -mno-avx512er -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lpthread -ldl

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Zstd 8 - Process: Compression2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M20406080100747269717375756383747674717764841. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Scala Dotty2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M2K4K6K8K10KSE +/- 62.31, N = 5SE +/- 78.90, N = 5SE +/- 20.56, N = 5SE +/- 54.97, N = 5SE +/- 21.19, N = 5SE +/- 19.51, N = 5SE +/- 56.89, N = 13SE +/- 82.66, N = 9SE +/- 29.54, N = 5SE +/- 41.65, N = 5SE +/- 50.08, N = 5SE +/- 46.73, N = 5SE +/- 35.89, N = 5SE +/- 19.31, N = 5SE +/- 17.62, N = 5SE +/- 31.93, N = 57414.627231.017256.927566.346733.167042.356890.618583.016577.348286.127556.336999.507200.756664.258634.696970.90

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Savina Reactors.IO2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M6K12K18K24K30KSE +/- 496.64, N = 25SE +/- 633.76, N = 25SE +/- 482.43, N = 25SE +/- 502.20, N = 25SE +/- 568.00, N = 25SE +/- 504.51, N = 25SE +/- 474.27, N = 25SE +/- 436.95, N = 25SE +/- 365.25, N = 20SE +/- 516.85, N = 25SE +/- 389.39, N = 25SE +/- 426.81, N = 25SE +/- 428.64, N = 25SE +/- 593.14, N = 25SE +/- 251.20, N = 25SE +/- 599.32, N = 2526257.0127973.0028107.0428251.8326906.8927361.6026764.9428596.1119303.5627198.0822776.3027198.8626711.1721975.1222798.3825186.67

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark Bayes2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 8275CL2 x Xeon Platinum 8275CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M11002200330044005500SE +/- 42.87, N = 25SE +/- 38.94, N = 25SE +/- 47.41, N = 25SE +/- 55.66, N = 25SE +/- 90.85, N = 25SE +/- 57.72, N = 25SE +/- 36.17, N = 25SE +/- 65.14, N = 25SE +/- 26.28, N = 25SE +/- 26.06, N = 25SE +/- 38.41, N = 5SE +/- 28.09, N = 25SE +/- 26.07, N = 25SE +/- 19.41, N = 5SE +/- 37.40, N = 25SE +/- 30.38, N = 73662.773405.413495.613813.755185.624510.833228.634199.413057.063477.333150.102856.853017.332674.183588.692743.62

CloverLeaf

CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version and benchmarked with the clover_bm8192.in input file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeafLagrangian-Eulerian Hydrodynamics2 x Xeon Gold 5220R2 x Xeon Gold 6226R2 x Xeon Platinum 8259CL2 x Xeon Platinum 8259CL NUMA off2 x Xeon Platinum 82802 x Xeon Silver 4216EPYC 2 7R32Xeon Gold 5218Xeon Gold 5220RXeon Gold 6226RXeon Platinum 8259CLXeon Platinum 8280Xeon Silver 4216Xeon W-3275M0.33530.67061.00591.34121.6765SE +/- 0.01, N = 3SE +/- 0.04, N = 15SE +/- 0.03, N = 15SE +/- 0.00, N = 3SE +/- 0.02, N = 15SE +/- 0.04, N = 15SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 151.060.930.780.630.691.000.361.371.281.271.110.961.491.141. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

119 Results Shown

MKL-DNN DNNL
ArrayFire:
  Conjugate Gradient CPU
  BLAS CPU
MKL-DNN DNNL:
  Convolution Batch conv_alexnet - f32
  Convolution Batch conv_all - u8s8f32
  Convolution Batch conv_googlenet_v3 - f32
  Convolution Batch conv_alexnet - u8s8f32
  Convolution Batch conv_all - f32
  Deconvolution Batch deconv_3d - f32
  IP Batch All - u8s8f32
  Convolution Batch conv_alexnet - bf16bf16bf16
  Convolution Batch conv_all - bf16bf16bf16
  Convolution Batch conv_googlenet_v3 - bf16bf16bf16
OSPray:
  NASA Streamlines - Path Tracer
  XFrog Forest - SciVis
  XFrog Forest - Path Tracer
MKL-DNN DNNL
OSPray
MKL-DNN DNNL
OSPray
Embree
OSPray
High Performance Conjugate Gradient
Embree:
  Pathtracer ISPC - Asian Dragon
  Pathtracer ISPC - Asian Dragon Obj
MKL-DNN DNNL
LuxCoreRender
Blender
NAMD
LuxCoreRender
MKL-DNN DNNL
John The Ripper
Blender
John The Ripper
MKL-DNN DNNL
Intel MPI Benchmarks
MKL-DNN DNNL
NAS Parallel Benchmarks
OSPray
NAS Parallel Benchmarks
MKL-DNN DNNL:
  Deconvolution Batch deconv_all - bf16bf16bf16
  Deconvolution Batch deconv_3d - u8s8f32
Blender
Embree
Stockfish
asmFish
Chaos Group V-RAY
Embree:
  Pathtracer - Asian Dragon
  Pathtracer - Asian Dragon Obj
Blender
MKL-DNN DNNL:
  IP Batch 1D - bf16bf16bf16
  IP Batch 1D - f32
NAS Parallel Benchmarks
Blender
LAMMPS Molecular Dynamics Simulator
Appleseed
MKL-DNN DNNL
Tungsten Renderer
Basis Universal
NAS Parallel Benchmarks
Timed Linux Kernel Compilation
NAS Parallel Benchmarks
dav1d
PostgreSQL pgbench
MKL-DNN DNNL
dav1d
Intel Open Image Denoise
Timed LLVM Compilation
NAS Parallel Benchmarks
dav1d
Appleseed
SVT-AV1:
  Enc Mode 8 - 1080p
  Enc Mode 4 - 1080p
Timed MrBayes Analysis
PyPerformance
Mlpack Benchmark
PostgreSQL pgbench
Mlpack Benchmark
DeepSpeech
Build2
Mlpack Benchmark
SVT-VP9
Timed GCC Compilation
Timed GDB GNU Debugger Compilation
Appleseed
Nettle:
  poly1305-aes
  chacha
  aes256
lzbench
PHPBench
PyPerformance:
  float
  django_template
Scikit-Learn
lzbench
Basis Universal
lzbench
PyBench
SMHasher:
  wyhash:
    cycles/hash
    MiB/sec
Numpy Benchmark
lzbench
Zstd Compression
Mlpack Benchmark
lzbench:
  Brotli 2 - Compression
  Zstd 1 - Decompression
Nettle
Himeno Benchmark
Radiance Benchmark:
  Serial
  SMP Parallel
lzbench
Renaissance
PyPerformance
DaCapo Benchmark
Tungsten Renderer
lzbench
Renaissance:
  Scala Dotty
  Savina Reactors.IO
  Apache Spark Bayes
CloverLeaf