2 x Xeon Gold 5220R Processor: 2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 12 x 32 GB DDR4-2933MT/s HMA84GR7CJR4N-WM, Disk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE
OS: Ubuntu 20.04, Kernel: 5.4.0-18-generic (x86_64), Desktop: GNOME Shell 3.36.0, Display Server: X Server 1.20.7, Display Driver: modesetting 1.20.7, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080
Compiler Notes: --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 -vProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002cJava Notes: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-2ubuntu2)Python Notes: + Python 3.8.2Security Notes: 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 Processor: Intel Xeon Gold 5220R @ 3.90GHz (18 Cores / 36 Threads)Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 6 x 32 GB DDR4-2933MT/s HMA84GR7CJR4N-WMDisk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE
OS: Ubuntu 20.04, Kernel: 5.4.0-18-generic (x86_64), Desktop: GNOME Shell 3.36.0, Display Server: X Server 1.20.7, Display Driver: modesetting 1.20.7, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1024x768
Xeon Platinum 8280 Changed Processor to Intel Xeon Platinum 8280 @ 4.00GHz (28 Cores / 56 Threads) .
2 x Xeon Platinum 8280 Changed Processor to 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads) .
Changed Memory to 12 x 32 GB DDR4-2933MT/s HMA84GR7CJR4N-WM .
Xeon Gold 5218 Processor: Intel Xeon Gold 5218 @ 3.90GHz (16 Cores / 32 Threads)Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 6 x 32 GB DDR4-2933MT/s HMA84GR7CJR4N-WMDisk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Monitor: 2 x VE228Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE
OS: Ubuntu 20.04, Kernel: 5.4.0-18-generic (x86_64), Desktop: GNOME Shell 3.36.0, Display Server: X Server 1.20.7, Display Driver: modesetting 1.20.7, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080
Xeon Silver 4216 Changed Processor to Intel Xeon Silver 4216 @ 3.20GHz (16 Cores / 32 Threads) .
Xeon Gold 6226R Changed Processor to Intel Xeon Gold 6226R @ 3.90GHz (16 Cores / 32 Threads) .
2 x Xeon Gold 6226R Changed Processor to 2 x Intel Xeon Gold 6226R @ 3.90GHz (32 Cores / 64 Threads) .
Changed Memory to 12 x 32 GB DDR4-2933MT/s HMA84GR7CJR4N-WM .
2 x Xeon Silver 4216 Changed Processor to 2 x Intel Xeon Silver 4216 @ 3.20GHz (32 Cores / 64 Threads) .
Xeon W-3275M Processor: Intel Xeon W-3275M @ 4.60GHz (28 Cores / 56 Threads)Motherboard: Supermicro X11SPA-T v1.01 (3.1 BIOS)Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 188GBDisk: 2 x 1024GB Samsung SSD 970 PRO 1TBGraphics: eVGA NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz)Audio: Realtek ALC888-VDMonitor: BenQ SW271Network: Intel I210 + Aquantia AQC107 NBase-T/IEEE
OS: Ubuntu 19.10, Kernel: 5.3.0-46-generic (x86_64), Desktop: GNOME Shell 3.34.3, Display Server: X Server 1.20.5, Display Driver: NVIDIA 430.50, OpenGL: 4.6.0, Compiler: GCC 9.2.1 20191008 + CUDA 10.1, File-System: ext4, Screen Resolution: 3840x2160
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,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 Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002cOpenCL Notes: GPU Compute Cores: 4352Java Notes: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-1ubuntu119.10.1)Python Notes: Python 2.7.17 + Python 3.7.5Security Notes: 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 Processor: 2 x Intel Xeon Platinum 8275CL @ 3.90GHz (48 Cores / 96 Threads)Motherboard: ASRockRack EP2C621D12 WS (P2.10 BIOS)Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 32 GB + 32 GB + 16384 MB + 32 GB + 16384 MB + 32 GB + 32 GB + 32 GB DDR4-3200MT/sDisk: 256GB TOSHIBA THNSNJ25 + 600GB INTEL SSDSC2BB60 + 6001GB HGST HUS726060ALGraphics: llvmpipe 220GBAudio: Creative Labs EMU20k2Monitor: DELL UP2516DNetwork: 4 x Intel X722 for 1GbE
OS: Ubuntu 19.10, Kernel: 5.3.0-55-generic (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server, OpenGL: 3.3 Mesa 19.2.1 (LLVM 9.0 256 bits), Compiler: GCC 9.2.1 20191008, File-System: ext4, Screen Resolution: 2560x1440
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,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 Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002bJava Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-2ubuntu219.10)Python Notes: Python 2.7.17 + Python 3.7.5Security Notes: 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 OS: Ubuntu 19.10, Kernel: 5.3.0-55-generic (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server, OpenGL: 3.3 Mesa 19.2.8 (LLVM 9.0 256 bits), Compiler: GCC 9.2.1 20191008, File-System: ext4, Screen Resolution: 2560x1440
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,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 Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002cJava Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-2ubuntu219.10)Python Notes: Python 2.7.17 + Python 3.7.5Security Notes: 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 Processor: AMD EPYC 7R32 48-Core @ 2.80GHz (48 Cores / 96 Threads)Motherboard: Supermicro H11SSL-i v2.00 (2.1 BIOS)Chipset: AMD Starship/MatisseMemory: 8 x 16384 MB DDR4-3200MT/s HMA82GR7CJR8N-XNDisk: 32GB Mass Storage + 256GB TOSHIBA THNSNJ25 + 600GB INTEL SSDSC2BB60 + 6001GB HGST HUS726060ALGraphics: llvmpipe 126GBMonitor: Crystal ViewNetwork: 2 x Intel I210
OS: Ubuntu 19.10, Kernel: 5.3.0-64-generic (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server, OpenGL: 3.3 Mesa 19.2.8 (LLVM 9.0 128 bits), Compiler: GCC 9.2.1 20191008, File-System: ext4, Screen Resolution: 800x600
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,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 Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301034Java Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-2ubuntu219.10)Python Notes: Python 2.7.17 + Python 3.7.5Security Notes: 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 Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,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 Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x4002f01Java Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-2ubuntu219.10)Python Notes: Python 2.7.17 + Python 3.7.5Security Notes: 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 Processor: 2 x Intel Xeon Platinum 8259L @ 3.50GHz (48 Cores / 96 Threads)Motherboard: ASRockRack EP2C621D16-4LP (P2.20 BIOS)Chipset: Intel Sky Lake-E DMI3 RegistersMemory: 12 x 16384 MB DDR4-3200MT/s Hynix HMA82GR7CJR8N-XNDisk: 256GB TOSHIBA THNSNJ25Graphics: llvmpipe 188GBAudio: NVIDIA Device 10f8Monitor: DELL UP2516DNetwork: 4 x Intel X722 for 1GbE
OS: Ubuntu 19.10, Kernel: 5.3.0-64-generic (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server, OpenGL: 3.3 Mesa 19.2.8 (LLVM 9.0 256 bits), Compiler: GCC 9.2.1 20191008, File-System: ext4, Screen Resolution: 2560x1440
Xeon Platinum 8259CL Changed Processor to Intel Xeon Platinum 8259L @ 3.50GHz (24 Cores / 48 Threads) .
Changed Memory to 6 x 16384 MB DDR4-3200MT/s Hynix HMA82GR7CJR8N-XN .
Changed Graphics to llvmpipe 93GB .
Xeon & EPYC Tests Processor Motherboard Chipset Memory Disk Graphics Monitor Network Audio OS Kernel Desktop Display Server Display Driver Compiler File-System Screen Resolution OpenGL 2 x Xeon Gold 5220R Xeon Gold 5220R Xeon Platinum 8280 2 x Xeon Platinum 8280 Xeon Gold 5218 Xeon Silver 4216 Xeon Gold 6226R 2 x Xeon Gold 6226R 2 x Xeon Silver 4216 Xeon W-3275M 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off EPYC 2 7R32 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off Xeon Platinum 8259CL 2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads) GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS) Intel Sky Lake-E DMI3 Registers 12 x 32 GB DDR4-2933MT/s HMA84GR7CJR4N-WM 280GB INTEL SSDPED1D280GA ASPEED VE228 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE Ubuntu 20.04 5.4.0-18-generic (x86_64) GNOME Shell 3.36.0 X Server 1.20.7 modesetting 1.20.7 GCC 9.3.0 ext4 1920x1080 Intel Xeon Gold 5220R @ 3.90GHz (18 Cores / 36 Threads) 6 x 32 GB DDR4-2933MT/s HMA84GR7CJR4N-WM 1024x768 Intel 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-WM Intel Xeon Gold 5218 @ 3.90GHz (16 Cores / 32 Threads) 6 x 32 GB DDR4-2933MT/s HMA84GR7CJR4N-WM 2 x VE228 1920x1080 Intel Xeon Silver 4216 @ 3.20GHz (16 Cores / 32 Threads) 3 x VE228 Intel Xeon Gold 6226R @ 3.90GHz (16 Cores / 32 Threads) 4 x VE228 2 x Intel Xeon Gold 6226R @ 3.90GHz (32 Cores / 64 Threads) 12 x 32 GB DDR4-2933MT/s HMA84GR7CJR4N-WM 5 x VE228 2 x Intel Xeon Silver 4216 @ 3.20GHz (32 Cores / 64 Threads) 6 x VE228 Intel Xeon W-3275M @ 4.60GHz (28 Cores / 56 Threads) Supermicro X11SPA-T v1.01 (3.1 BIOS) 188GB 2 x 1024GB Samsung SSD 970 PRO 1TB eVGA NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz) Realtek ALC888-VD BenQ SW271 Intel I210 + Aquantia AQC107 NBase-T/IEEE Ubuntu 19.10 5.3.0-46-generic (x86_64) GNOME Shell 3.34.3 X Server 1.20.5 NVIDIA 430.50 4.6.0 GCC 9.2.1 20191008 + CUDA 10.1 3840x2160 2 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/s 256GB TOSHIBA THNSNJ25 + 600GB INTEL SSDSC2BB60 + 6001GB HGST HUS726060AL llvmpipe 220GB Creative Labs EMU20k2 DELL UP2516D 4 x Intel X722 for 1GbE 5.3.0-55-generic (x86_64) GNOME Shell 3.34.1 X Server 3.3 Mesa 19.2.1 (LLVM 9.0 256 bits) GCC 9.2.1 20191008 2560x1440 3.3 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/Matisse 8 x 16384 MB DDR4-3200MT/s HMA82GR7CJR8N-XN 32GB Mass Storage + 256GB TOSHIBA THNSNJ25 + 600GB INTEL SSDSC2BB60 + 6001GB HGST HUS726060AL llvmpipe 126GB Crystal View 2 x Intel I210 5.3.0-64-generic (x86_64) 3.3 Mesa 19.2.8 (LLVM 9.0 128 bits) 800x600 2 x Intel Xeon Platinum 8259L @ 3.50GHz (48 Cores / 96 Threads) ASRockRack EP2C621D16-4LP (P2.20 BIOS) Intel Sky Lake-E DMI3 Registers 12 x 16384 MB DDR4-3200MT/s Hynix HMA82GR7CJR8N-XN 256GB TOSHIBA THNSNJ25 llvmpipe 188GB NVIDIA Device 10f8 DELL UP2516D 4 x Intel X722 for 1GbE 3.3 Mesa 19.2.8 (LLVM 9.0 256 bits) 2560x1440 Intel Xeon Platinum 8259L @ 3.50GHz (24 Cores / 48 Threads) 6 x 16384 MB DDR4-3200MT/s Hynix HMA82GR7CJR8N-XN llvmpipe 93GB OpenBenchmarking.org Compiler 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 -v Processor 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: 0x4002f01 Java 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 3.7.5 Security 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 disabled OpenCL Details - Xeon W-3275M: GPU Compute Cores: 4352
2 x Xeon Gold 5220R Xeon Gold 5220R Xeon Platinum 8280 2 x Xeon Platinum 8280 Xeon Gold 5218 Xeon Silver 4216 Xeon Gold 6226R 2 x Xeon Gold 6226R 2 x Xeon Silver 4216 Xeon W-3275M 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off EPYC 2 7R32 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off Xeon Platinum 8259CL Logarithmic Result Overview Phoronix Test Suite MKL-DNN DNNL ArrayFire OSPray High Performance Conjugate Gradient LuxCoreRender John The Ripper Embree Intel MPI Benchmarks Stockfish asmFish Chaos Group V-RAY Blender PostgreSQL pgbench LAMMPS Molecular Dynamics Simulator Timed Linux Kernel Compilation dav1d Intel Open Image Denoise Timed LLVM Compilation SVT-AV1 Timed MrBayes Analysis Tungsten Renderer Appleseed Basis Universal DeepSpeech Build2 SVT-VP9 Timed GCC Compilation Timed GDB GNU Debugger Compilation Mlpack Benchmark PHPBench Nettle Scikit-Learn PyBench Numpy Benchmark lzbench Zstd Compression Renaissance Himeno Benchmark Radiance Benchmark DaCapo Benchmark
Xeon & EPYC Tests build-gcc: Time To Compile mkl-dnn: Convolution Batch conv_all - bf16bf16bf16 mkl-dnn: Convolution Batch conv_all - u8s8f32 mkl-dnn: Convolution Batch conv_all - f32 mkl-dnn: Deconvolution Batch deconv_all - bf16bf16bf16 mkl-dnn: Deconvolution Batch deconv_all - f32 blender: Barbershop - CPU-Only build-llvm: Time To Compile hpcg: pgbench: Buffer Test - Normal Load - Read Write blender: Pabellon Barcelona - CPU-Only radiance: Serial mlpack: scikit_linearridgeregression numpy: pgbench: Buffer Test - Normal Load - Read Only renaissance: Savina Reactors.IO blender: Classroom - CPU-Only mlpack: scikit_qda dav1d: Chimera 1080p 10-bit asmfish: 1024 Hash Memory, 26 Depth ospray: San Miguel - Path Tracer luxcorerender: Rainbow Colors and Prism mrbayes: Primate Phylogeny Analysis build-gdb: Time To Compile appleseed: Emily ospray: XFrog Forest - SciVis mkl-dnn: Convolution Batch conv_googlenet_v3 - bf16bf16bf16 ospray: XFrog Forest - Path Tracer mkl-dnn: Convolution Batch conv_googlenet_v3 - u8s8f32 mkl-dnn: Convolution Batch conv_googlenet_v3 - f32 blender: Fishy Cat - CPU-Only deepspeech: CPU ospray: San Miguel - SciVis appleseed: Material Tester build-linux-kernel: Time To Compile mlpack: scikit_ica pyperformance: python_startup radiance: SMP Parallel build2: Time To Compile blender: BMW27 - CPU-Only ospray: NASA Streamlines - Path Tracer appleseed: Disney Material stockfish: Total Time v-ray: CPU npb: EP.D renaissance: Apache Spark PageRank luxcorerender: DLSC renaissance: Apache Spark Bayes john-the-ripper: MD5 namd: ATPase Simulation - 327,506 Atoms mkl-dnn: Convolution Batch conv_3d - u8s8f32 basis: ETC1S pyperformance: float himeno: Poisson Pressure Solver mkl-dnn: IP Batch All - u8s8f32 mkl-dnn: IP Batch All - f32 pyperformance: regex_compile npb: BT.C mkl-dnn: Convolution Batch conv_3d - bf16bf16bf16 embree: Pathtracer - Asian Dragon Obj embree: Pathtracer ISPC - Asian Dragon Obj pyperformance: django_template basis: UASTC Level 3 mkl-dnn: IP Batch 1D - f32 john-the-ripper: Blowfish ospray: NASA Streamlines - SciVis lzbench: Crush 0 - Decompression lzbench: Crush 0 - Compression npb: LU.C tungsten: Water Caustic intel-mpi: IMB-P2P PingPong embree: Pathtracer ISPC - Crown pybench: Total For Average Test Times embree: Pathtracer - Crown lzbench: Zstd 8 - Decompression lzbench: Zstd 8 - Compression lzbench: Brotli 2 - Decompression lzbench: Brotli 2 - Compression lzbench: Zstd 1 - Decompression lzbench: Zstd 1 - Compression mlpack: scikit_svm mkl-dnn: Deconvolution Batch deconv_3d - u8s8f32 embree: Pathtracer - Asian Dragon svt-av1: Enc Mode 4 - 1080p mkl-dnn: Convolution Batch conv_alexnet - bf16bf16bf16 mkl-dnn: Deconvolution Batch deconv_1d - u8s8f32 mkl-dnn: Deconvolution Batch deconv_1d - bf16bf16bf16 compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 mkl-dnn: Deconvolution Batch deconv_1d - f32 embree: Pathtracer ISPC - Asian Dragon dav1d: Summer Nature 4K mkl-dnn: Convolution Batch conv_alexnet - u8s8f32 arrayfire: BLAS CPU phpbench: PHP Benchmark Suite mkl-dnn: Convolution Batch conv_alexnet - f32 renaissance: Scala Dotty ospray: Magnetic Reconnection - SciVis mkl-dnn: IP Batch 1D - bf16bf16bf16 dav1d: Summer Nature 1080p arrayfire: Conjugate Gradient CPU tungsten: Hair npb: SP.B svt-av1: Enc Mode 8 - 1080p smhasher: wyhash smhasher: wyhash scikit-learn: dacapobench: Jython svt-vp9: Visual Quality Optimized - Bosphorus 1080p npb: MG.C oidn: Memorial nettle: aes256 npb: EP.C lammps: Rhodopsin Protein mkl-dnn: Deconvolution Batch deconv_3d - bf16bf16bf16 mkl-dnn: Deconvolution Batch deconv_3d - f32 cloverleaf: Lagrangian-Eulerian Hydrodynamics nettle: sha512 nettle: chacha nettle: poly1305-aes 2 x Xeon Gold 5220R Xeon Gold 5220R Xeon Platinum 8280 2 x Xeon Platinum 8280 Xeon Gold 5218 Xeon Silver 4216 Xeon Gold 6226R 2 x Xeon Gold 6226R 2 x Xeon Silver 4216 Xeon W-3275M 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off EPYC 2 7R32 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off Xeon Platinum 8259CL 1060.578 3917.52 2479.28 999.544 3152.41 1278.25 260.56 286.782 25.6303 34227.724903 208.30 746.918 2.39 300.73 598798.571324 26257.008 165.96 42.69 70.81 85501851 3.95 4.46 134.928 146.439 180.645797 7.19 187.168 3.98 15.7542 54.8190 98.24 125.11863 43.48 189.459653 36.699 77.41 11.2 230.561 72.151 60.67 10.42 88.856634 74235829 40270 3780.59 24540.720 4.44 3662.767 4821000 0.60333 4896.41 54.554 113 3404.690861 4.08605 10.6348 167 100761.29 15.2177 32.3301 37.1498 47.3 27.981 2.23009 51324 55.56 419 93 108883.40 23.3367 19650424.333333 33.4469 1100 29.5153 1101 74 613 172 1147 437 17.92 3112.36 35.8757 5.302 712.201 0.560890 7.22975 10.449 2.12680 43.0983 177.89 35.9778 2359.13 631283 122.761 7414.619 47.62 5.72791 321.84 9.898 11.0726 50932.88 49.209 18.806 10.458 4877 237.57 58984.18 27.97 6159.21 3768.66 17.378 9.42591 2.69700 1.06 489.15 1024.975 2797.22 1167.683 7839.95 4826.71 1948.77 5695.58 1920.74 456.47 430.426 13.3529 45518.593515 404.78 749.923 2.25 313.76 383120.690509 22776.295 328.81 34.24 58.05 43217939 2.14 2.48 134.483 151.909 284.27974 3.70 369.287 2.06 28.4532 108.161 175.95 126.07801 23.26 162.860353 59.012 68.19 11.3 242.515 91.641 113.30 5.38 158.77238 38167326 21886 1966.61 21704.485 2.32 3150.096 2506000 1.15745 9696.92 56.018 114 3398.397455 4.61054 8.90795 168 50787.79 29.9173 17.7957 20.3418 47.1 46.708 4.49985 25547 28.57 428 98 56744.87 25.0080 10276849.521739 17.6604 1114 16.0514 1194 76 651 176 1180 444 17.82 6072.57 19.6105 4.285 1433.47 0.843709 13.1428 10.355 3.36432 23.6042 160.59 66.7352 1201.54 629690 244.745 7556.329 27.03 8.68590 274.98 6.409 18.9840 23346.56 33.088 18.815 10.112 4834 224.01 31197.22 18.41 6133.91 1863.15 9.535 16.8253 4.88966 1.28 485.86 1020.093 2779.78 1063.705 3497.47 2846.12 765.745 2935.99 1113.54 287.80 308.741 14.9097 53139.057777 246.31 728.361 1.67 330.33 560887.766696 21975.122 198.25 30.45 65.40 68762075 3.52 4.11 128.848 144.643 197.649505 6.25 166.984 3.46 11.2900 42.0758 110.67 118.09377 38.46 123.979103 40.898 67.36 11.2 235 74.118 69.80 9.49 103.833099 62891312 34710 3283.38 20621.229 3.79 2674.175 4090000 0.70709 5919.94 51.446 109 3510.205159 3.23121 6.79509 164 71842.34 14.0780 29.2061 33.0490 46.2 30.689 2.39451 42864 50 440 101 74255.67 22.0167 16653864.768116 28.7730 1076 26.2800 1224 77 673 181 1212 457 17.19 3716.98 32.2474 6.030 637.374 0.371036 6.55374 8.203 1.46232 38.3100 199.08 26.8391 3432.16 649164 94.1937 6664.254 42.87 4.83170 323.20 4.115 12.6863 32682.14 51.917 22.678 9.127 4547 265.40 37089.05 31.10 6313.16 3194.18 15.314 7.69605 1.96279 0.96 501.98 1051.111 2867.48 1005.530 1766.35 1517.44 496.816 1779.15 881.783 187.33 221.515 28.8542 24466.911227 129.01 728.246 1.82 321.82 909916.490086 26764.941 100.47 38.35 85.14 133839896 6.53 7.15 129.986 142.695 154.980752 12.05 86.5391 6.67 7.46050 23.1772 66.39 122.22468 69.52 193.44241 27.309 63.35 11.2 226.076 62.776 38.79 18.18 68.618272 119715795 64331 6284.65 23588.397 7.19 3228.633 7880000 0.36226 3005.48 52.694 109 3514.604106 3.11002 9.52466 164 136046.53 7.92912 51.7853 58.6945 45.9 19.885 1.63986 84084 90.91 428 96 140090.32 21.5896 31821690.550725 53.2304 1073 45.6121 1124 75 623 176 1168 449 17.19 1893.72 57.4870 7.033 320.060 0.394455 4.06847 9.137 1.24029 68.4241 221.31 19.8143 3430.28 649693 49.8437 6890.606 71.43 3.65964 409.88 7.481 7.82706 70893.41 56.982 22.677 9.392 4711 233.17 69175.12 34.49 6320.00 6104.94 24.788 4.35817 1.13608 0.69 500.98 1051.936 2868.69 1218.874 10255.2 5840.26 2363.00 6721.02 1699.69 589.07 501.218 13.0138 40894.896756 531.98 747.844 2.46 315.14 322051.631187 27198.080 433.42 37.41 55.88 36561817 1.75 1.88 147.734 156.299 328.139133 3.01 484.594 1.68 34.6031 131.088 229.28 128.40692 18.87 179.751505 67.156 68.78 11.1 241.897 101.716 149.39 4.37 182.557972 32424332 16981 1635.78 23703.029 1.74 3477.331 1912667 1.51168 11821.3 58.473 114 3405.035897 4.83875 9.30959 167 48617.05 39.9985 13.8526 16.7685 47.2 55.209 4.75696 21403 23.26 430 96 48143.49 25.9635 9066471.0434783 14.4163 1101 12.3882 1195 74 655 176 1184 446 17.98 7189.03 15.3104 3.339 1874.47 0.976730 16.5484 11.122 3.99488 19.4321 136.86 81.0705 1002.09 632455 298.300 8286.123 22.22 8.8271 265.46 7.042 22.4866 22329.34 27.193 19.806 10.286 5096 172.82 30328.65 15.80 6164.79 1621.48 8.158 21.4290 5.80420 1.37 489.51 1024.493 2798.56 1398.020 10258.0 6241.16 3129.93 6721.54 2201.04 593.13 531.152 11.8883 40373.304894 531.39 909.318 2.97 272.12 313376.779917 22798.382 432.11 40.75 50.10 35085496 1.40 1.88 193.466 177.772 345.389961 2.34 484.895 1.31 45.0502 171.428 229.71 135.99744 14.71 188.776756 71.770 81.36 15.4 299.739 109.699 149.02 3.41 194.401843 31174576 17105 1571.49 25271.433 1.77 3588.692 1893333 1.51721 12300.3 67.461 137 2823.595364 5.59275 10.1930 204 46389.79 40.0192 13.8827 13.4918 57.5 58.246 5.16658 20424 18.18 353 82 46723.01 28.8979 8923779.5507246 11.3827 1342 12.4316 998 64 542 146 973 365 20.89 7457.86 15.2796 3.309 1875.23 1.27375 16.5516 11.430 5.31087 15.5911 132.46 105.826 765.491 515697 395.441 8634.691 17.94 10.9014 232.35 7.819 23.6129 21149.68 26.460 22004.08 22.131 12.030 5768 173.18 28301.13 12.85 5024.39 1545.50 7.810 21.4755 7.63646 1.49 399.99 837.612 2291.69 1092.587 5709.17 4478.93 1227.07 3966.73 983.913 453.22 433.191 13.9581 46503.283040 400.96 746.687 1.93 318.87 376860.318615 27198.856 321.53 31.96 62.32 44614925 2.02 2.51 123.702 139.120 276.768654 3.68 269.991 2.02 17.9735 69.1431 173.95 119.78717 22.69 156.605614 57.772 61.82 11.0 242.002 88.977 111.82 5.52 155.228014 39776292 22074 2094.53 21743.019 2.35 2856.850 2583000 1.13586 9374.60 54.790 115 3401.157135 4.53821 8.84233 168 56576.12 22.4243 17.4223 19.3228 47.3 44.943 4.41366 27126 29.41 429 95 58594.50 24.0874 10620968.608695 16.8099 1103 15.9943 1193 74 653 176 1182 445 17.92 5864.26 19.3472 4.340 1042.34 0.528632 9.90362 10.330 2.23126 22.4598 170.07 42.2202 2137.03 632431 155.368 6999.497 25.48 5.71439 307.75 6.451 18.6129 23859.79 34.636 19429.87 25.134 9.924 4609 221.95 31633.6 22.01 6161.42 2044.24 10.325 12.3271 3.13006 1.27 488.81 1024.992 2795.49 996.904 2871.11 2377.91 694.324 2169.93 711.389 257.01 279.682 26.5910 37715.216271 207.41 745.686 2.08 304.16 587882.232699 27972.998 163.32 44.53 73.95 83894514 3.71 4.32 124.258 133.444 177.661148 7.09 137.734 3.88 11.3282 36.3716 96.41 123.38702 42.27 185.357154 36.595 74.63 10.9 233.042 70.608 59.45 10.56 84.844108 75203729 34749 3969.60 24522.220 4.5183 3405.414 4977667 0.58237 4821.24 54.947 113 3410.383938 4.11779 10.5239 167 77470.67 11.6076 31.3117 34.8030 47.1 27.226 2.18975 53485 55.56 418 91 106268.33 23.1916 20467429.521739 31.7318 1104 28.9602 1100 72 608 172 1141 437 17.77 2987.08 34.6919 5.431 527.017 0.369060 5.38402 10.206 1.49724 40.4325 203.10 26.5363 3912.30 632601 81.1400 7231.014 45.45 3.21281 358.62 7.155 10.6653 49232.24 51.710 19424.11 25.129 10.449 4806 256.91 58681.42 33.06 6157.49 4005.26 18.150 6.29647 1.70749 0.93 489.42 1025.384 2797.43 1268.815 5156.69 3215.17 1578.24 3600.95 1364.26 333.40 347.827 23.1574 34916.030852 272.72 907.757 2.99 262.78 501697.238231 28596.105 218.06 50.10 59.51 66895810 2.63 3.65 194.504 169.704 222.968514 4.57 246.446 2.55 23.7028 87.5434 125.35 133.01160 27.84 197.740442 45.315 94.45 15.4 281.251 86.325 78.72 6.62 107.498089 60569696 27592 3144.70 28045.920 3.43 4199.411 3764000 0.76982 6329.94 65.644 137 2817.673053 4.82603 11.4215 204 65509.98 20.5163 25.4971 25.0678 57.5 34.632 2.66699 41021 34.48 344 80 85606.53 27.3948 17176230.536232 21.7468 1343 23.2674 930 63 509 142 943 359 21.09 3849.13 28.2032 4.216 938.910 0.770300 8.86913 10.978 3.06590 28.9732 159.60 55.3361 1497.75 519964 197.914 8583.014 32.53 5.56500 272.55 16.92 13.6031 42220.94 40.548 22011.20 22.129 12.549 5802 206.42 52832.47 20.43 5061.60 2984.02 14.161 10.9379 3.85512 1.00 401.13 841.649 2294.74 994.583 3880.44 2967.92 878.390 3293.94 1292.62 304.79 281.678 14.1623 11704.231804 265.41 665.7 1.99 367.56 567696.505912 25186.666 213.36 32.65 81.60 66225641 3.25 3.79 143.348 134.824 196.929786 5.72 188.611 3.17 13.4504 49.8744 118.09 123.85252 34.48 124.147301 36.367 54.91 17.7 219.836 66.415 74.96 8.69 106.643392 61170651 33014 3210.52 21015.543 3.53 2743.623 3654000 0.81434 6183.11 47.653 94.5 3866.090988 3.59218 7.54439 157 69347.58 16.5906 27.1952 30.3458 49.9 30.634 2.86715 40326 45.45 509 109 69606.84 21.5517 20246604.623188 26.4010 951 24.5503 1298 84 721 196 1299 508 15.78 3852.37 30.1057 6.389 702.065 0.458422 7.61595 8.380 1.74515 35.1495 256.60 31.9893 3128.39 734339 108.568 6970.904 40 5.56304 537.84 4.423 12.7104 31426.53 53.819 26298.77 18.508 9.661 4321 282.18 35376.11 27.35 7070.60 3025.11 14.562 8.46273 2.27526 1.14 550.93 1172.153 3207.98 966.599 1919.50 2023.47 1206.22 1730.80 981.058 189.55 218.050 8.41405 3890.770882 139.11 753.635 2.36 338.44 629984.514253 26906.886 108.97 62.02 90.28 119549901 5.82 7.09 125.867 128.950 152.902049 11.36 93.3596 6.25 17.7549 33.6305 69.93 113.14396 63.54 189.296166 27.100 53.50 232.695 64.503 41.68 17.02 68.606542 109874307 58326 24505.962 6.73 5185.621 7388333 3250.89 52.608 3440.518277 5.36708 19.1030 8.71234 35.6676 36.6652 21.060 1.95992 77771 82.62 434 94 22.7599 35954425.362319 49.0461 1133 41.7899 1053 73 592 170 1099 439 16.87 2059.03 40.0787 5.243 348.243 0.355362 3.96906 10.945 1.33109 38.7658 218.14 59.9040 6259.01 640173 79.1109 6733.160 50.88 4.10369 422.89 13.22 8.29067 55.374 18770.15 26.086 11.065 4685 191.66 15.06 6172.55 22.301 4.37952 1.17385 487.55 1025.603 2785.99 1032.978 1918.28 1708.05 650.981 1705.35 910.142 190.01 244.910 6.32971 3197.742954 139.00 753.433 2.46 315.66 725740.723795 27361.597 108.94 57.25 90.78 103033955 5.87 7.31 124.297 145.510 152.093681 11.36 93.2842 6.24 10.4841 25.0533 70.04 138.25629 66.67 194.846861 29.258 53.66 227.159 64.421 41.72 16.95 68.202167 108412514 58525 24666.363 6.75 4510.830 7350667 3252.48 53.135 3430.766164 3.84746 12.6820 8.64707 40.8502 44.7151 20.994 1.63599 78327 83.33 432 95 22.7088 35888907.985507 49.9559 1123 41.3944 999 75 582 172 1090 443 18.42 2057.93 45.7674 5.942 348.326 0.354714 3.96510 10.289 1.25116 51.8741 216.86 30.6427 6325.07 639026 57.5111 7042.354 58.82 4.06041 406.66 9.654 8.19337 56.122 18775.94 26.129 11.490 4759 228.38 19.55 6184.20 20.984 4.36002 1.17278 490.26 1027.592 2803.55 849.192 11728.8 710.140 1485.47 177.79 200.039 17.0608 6105.728957 132.04 730.7 1.79 323.58 891303.121943 19303.561 101.34 39.54 140.14 113278977 4.73 8.12 92.361 108.675 147.685856 11.03 5.85 730.306 42.5413 65.67 72.81599 58.82 175.193708 24.005 49.47 16.3 219.652 59.956 41.76 16.60 62.431047 116765028 62897 3570.46 21641.954 7.28 3057.059 3972000 0.48614 3076.76 54.310 3769.723664 149.339 8.88390 213 106415.53 47.5806 45.4330 66.4 19.193 1.67560 66475 76.92 380 81 99821.89 22.3247 20348261.028985 45.1869 1226 47.6464 1266 83 564 165 1148 418 15.16 1899.24 52.9532 5.714 1131.13 9.230 2.22540 52.3541 321.17 1301.36 990.798 500524 96.6881 6577.343 40 676.16 35.13 7.67455 51225.18 54.472 10.419 5246 291.17 49330.15 28.71 4665.33 3485.99 20.821 2.20471 0.36 478.09 750.357 2046.35 1012.035 2197.81 1793.75 559.468 1904.28 739.163 211.33 232.053 27.1060 4009.405331 158.13 841.647 2.30 310.40 795715.311355 28107.036 124.59 42.88 89.55 119912357 5.58 6.40 139.750 129.689 161.846314 10.42 106.893 5.71 8.74794 25.7722 79.00 117.72613 62.5 185.229734 27.581 58.48 11.3 258.343 66.667 47.63 15.625 73.581913 103513853 51803 5310.16 25275.159 5.88 3495.612 6554667 0.44551 3551.38 57.826 123 3147.907521 3.04866 9.97669 200 104107.99 9.20665 42.7613 50.9769 64.2 23.088 1.57687 70888 76.92 394 88 120961.91 24.5437 31988149.246377 46.1757 1252 38.1222 1011 69 551 157 1027 399 18.76 2238.05 46.7920 5.955 399.298 0.376222 4.49039 9.949 1.25795 59.0563 215.64 22.3830 5319.58 573483 56.6465 7256.920 62.5 4.48918 431.76 8.430 9.26217 53978.90 53.040 20225.18 24.151 12.459 5172 229.91 63393.35 33.89 5513.08 5052.63 22.535 4.87194 1.26649 0.78 437.62 917.750 2497.86 1073.762 2198.18 1734.20 461.935 1904.45 743.695 211.37 244.940 16.5171 3168.732081 157.99 841.323 2.42 293.53 790827.572464 28251.828 124.67 41.29 88.66 105070606 5.54 5.52 141.898 146.435 163.707232 10.32 106.714 5.71 7.63651 25.0672 79.22 135.05100 61.58 197.293774 29.276 57.69 22.6 255.588 69.195 48.00 15.54 73.216224 104106676 53051 5284.34 25636.694 5.86 3813.746 6608333 0.45422 3548.60 58.280 123 3130.858713 2.78193 6.65842 200 84766.14 9.18751 42.4946 50.8648 64.1 23.147 1.53729 70955 76.92 396 86 94642.99 24.7792 32444647.434783 46.4184 1253 38.1033 966 71 543 159 1032 407 19.62 2252.67 46.9084 5.996 399.308 0.361414 4.46523 10.294 1.22589 59.0502 212.99 19.3723 5650.71 574348 55.3565 7566.342 62.5 4.46440 400.24 7.604 9.09073 38493.57 52.314 20231.58 24.154 12.954 5161 229.53 43490.15 33.10 5523.31 5059.02 21.887 4.85689 1.26395 0.63 438.23 917.505 2516.87 1067.641 4364.00 3402.07 874.201 3368.21 1029.24 350.47 317.610 13.6425 5941.318141 305.20 842.099 2.00 321.13 512031.419231 26711.173 246.81 31.98 67.33 59350794 3.00 3.30 138.846 132.228 219.3197 5.38 207.911 2.96 12.7059 48.0640 134.22 117.35692 32.97 127.996296 41.137 61.20 11.4 273.125 76.147 86.89 8.09 120.169346 54437117 29061 2677.64 22226.845 3.04 3017.325 3384000 0.86925 7095.62 57.399 122 3152.501437 3.43236 7.89071 200 51975.35 17.3217 23.7192 28.2928 64.1 35.983 2.69977 35599 43.48 404 91 65522.46 25.3555 16759832.26087 24.7267 1250 21.3829 1089 71 587 160 1061 410 18.67 4426.06 26.0638 5.112 796.753 0.415614 7.98292 9.672 1.63928 32.9088 205.63 30.8800 2950.16 569793 107.804 7200.752 37.04 5.69900 353.78 4.677 14.8046 24288.34 46.873 20221.25 24.187 12.088 5012 256.24 33490.03 27.99 5517.02 2641.32 13.040 9.37107 2.20053 1.11 436.73 920.513 2492.48 OpenBenchmarking.org
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.org Seconds, Fewer Is Better Timed GCC Compilation 9.3.0 Time To Compile EPYC 2 7R32 2 x Xeon Platinum 8275CL Xeon W-3275M 2 x Xeon Gold 6226R 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Gold 5220R Xeon Platinum 8280 Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 2 x Xeon Silver 4216 Xeon Silver 4216 300 600 900 1200 1500 SE +/- 0.63, N = 3 SE +/- 5.92, N = 3 SE +/- 0.44, N = 3 SE +/- 0.70, N = 3 SE +/- 0.24, N = 3 SE +/- 0.68, N = 3 SE +/- 1.25, N = 3 SE +/- 1.42, N = 3 SE +/- 0.29, N = 3 SE +/- 0.67, N = 3 SE +/- 1.08, N = 3 SE +/- 0.43, N = 3 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.64, N = 3 SE +/- 1.02, N = 3 849.19 966.60 994.58 996.90 1005.53 1012.04 1032.98 1060.58 1063.71 1067.64 1073.76 1092.59 1167.68 1218.87 1268.82 1398.02
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.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_all - Data Type: bf16bf16bf16 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 6226R Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Gold 5220R Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 2K 4K 6K 8K 10K SE +/- 1.13, N = 3 SE +/- 0.26, N = 3 SE +/- 0.16, N = 3 SE +/- 0.11, N = 3 SE +/- 0.30, N = 3 SE +/- 2.73, N = 3 SE +/- 0.26, N = 3 SE +/- 0.11, N = 3 SE +/- 3.93, N = 3 SE +/- 0.11, N = 3 SE +/- 6.81, N = 3 SE +/- 0.12, N = 3 SE +/- 4.68, N = 3 SE +/- 0.34, N = 3 SE +/- 0.35, N = 3 1766.35 1918.28 1919.50 2197.81 2198.18 2871.11 3497.47 3880.44 3917.52 4364.00 5156.69 5709.17 7839.95 10255.20 10258.00 MIN: 1911.42 MIN: 1911.94 MIN: 2191.04 MIN: 2191.82 MIN: 2860.81 MIN: 3490.41 MIN: 3767 MIN: 3906.67 MIN: 4358.26 MIN: 5142.07 MIN: 5699.77 MIN: 7795.37 MIN: 10250.1 MIN: 10250.4 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_all - Data Type: u8s8f32 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 EPYC 2 7R32 3K 6K 9K 12K 15K SE +/- 3.12, N = 3 SE +/- 0.40, N = 3 SE +/- 0.82, N = 3 SE +/- 1.51, N = 3 SE +/- 3.97, N = 3 SE +/- 10.67, N = 3 SE +/- 2.07, N = 3 SE +/- 1.24, N = 3 SE +/- 15.10, N = 3 SE +/- 23.72, N = 3 SE +/- 4.13, N = 3 SE +/- 7.74, N = 3 SE +/- 4.48, N = 3 SE +/- 1.57, N = 3 SE +/- 4.87, N = 3 SE +/- 19.01, N = 3 1517.44 1708.05 1734.20 1793.75 2023.47 2377.91 2479.28 2846.12 2967.92 3215.17 3402.07 4478.93 4826.71 5840.26 6241.16 11728.80 MIN: 2813.78 MIN: 2893.12 MIN: 3181.24 MIN: 3393.59 MIN: 4461.44 MIN: 4806.63 MIN: 5831.48 MIN: 6214.68 MIN: 11565.1 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_all - Data Type: f32 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Gold 6226R EPYC 2 7R32 Xeon Platinum 8280 Xeon Platinum 8259CL Xeon W-3275M 2 x Xeon Gold 5220R 2 x Xeon Platinum 8275CL Xeon Gold 6226R 2 x Xeon Silver 4216 Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 700 1400 2100 2800 3500 SE +/- 0.29, N = 3 SE +/- 0.78, N = 3 SE +/- 0.29, N = 3 SE +/- 5.95, N = 3 SE +/- 0.79, N = 3 SE +/- 2.05, N = 3 SE +/- 0.39, N = 3 SE +/- 0.32, N = 3 SE +/- 0.68, N = 3 SE +/- 0.29, N = 3 SE +/- 7.07, N = 3 SE +/- 0.59, N = 3 SE +/- 1.69, N = 3 SE +/- 1.16, N = 3 SE +/- 0.47, N = 3 SE +/- 1.30, N = 3 461.94 496.82 559.47 650.98 694.32 710.14 765.75 874.20 878.39 999.54 1206.22 1227.07 1578.24 1948.77 2363.00 3129.93 MIN: 553.8 MIN: 639.1 MIN: 686.24 MIN: 700.52 MIN: 755.35 MIN: 868.41 MIN: 819.94 MIN: 995.71 MIN: 1181.19 MIN: 1218.34 MIN: 1571.3 MIN: 1927.2 MIN: 2357.87 MIN: 3085.85 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_all - Data Type: bf16bf16bf16 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 6226R Xeon Platinum 8280 2 x Xeon Gold 5220R Xeon W-3275M Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 1400 2800 4200 5600 7000 SE +/- 3.70, N = 3 SE +/- 16.35, N = 3 SE +/- 0.87, N = 3 SE +/- 0.13, N = 3 SE +/- 0.44, N = 3 SE +/- 5.08, N = 3 SE +/- 5.43, N = 3 SE +/- 3.03, N = 3 SE +/- 4.61, N = 3 SE +/- 0.16, N = 3 SE +/- 3.93, N = 3 SE +/- 1.02, N = 3 SE +/- 3.12, N = 3 SE +/- 0.83, N = 3 SE +/- 0.10, N = 3 1705.35 1730.80 1779.15 1904.28 1904.45 2169.93 2935.99 3152.41 3293.94 3368.21 3600.95 3966.73 5695.58 6721.02 6721.54 MIN: 1696.57 MIN: 1701.4 MIN: 1772.45 MIN: 1898.87 MIN: 1899.24 MIN: 2158.31 MIN: 2926 MIN: 3140.75 MIN: 3137.48 MIN: 3365.01 MIN: 3588.76 MIN: 3962.44 MIN: 5644.95 MIN: 6716.04 MIN: 6717.72 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_all - Data Type: f32 2 x Xeon Gold 6226R 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL Xeon Gold 6226R Xeon Platinum 8259CL Xeon Platinum 8280 2 x Xeon Gold 5220R Xeon W-3275M 2 x Xeon Silver 4216 EPYC 2 7R32 Xeon Gold 5218 Xeon Gold 5220R Xeon Silver 4216 500 1000 1500 2000 2500 SE +/- 0.89, N = 3 SE +/- 0.85, N = 3 SE +/- 0.88, N = 3 SE +/- 0.39, N = 3 SE +/- 0.18, N = 3 SE +/- 2.10, N = 3 SE +/- 0.49, N = 3 SE +/- 0.97, N = 3 SE +/- 0.33, N = 3 SE +/- 1.51, N = 3 SE +/- 16.26, N = 5 SE +/- 0.28, N = 3 SE +/- 1.29, N = 3 SE +/- 0.44, N = 3 SE +/- 0.74, N = 3 SE +/- 7.40, N = 3 711.39 739.16 743.70 881.78 910.14 981.06 983.91 1029.24 1113.54 1278.25 1292.62 1364.26 1485.47 1699.69 1920.74 2201.04 MIN: 703.37 MIN: 731.99 MIN: 737.27 MIN: 874.01 MIN: 903.49 MIN: 965.05 MIN: 975.96 MIN: 1023.45 MIN: 1108.65 MIN: 1270.58 MIN: 1177.9 MIN: 1356.18 MIN: 1462.15 MIN: 1694.75 MIN: 1902.55 MIN: 2184.66 1. (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.org Seconds, Fewer Is Better Blender 2.82 Blend File: Barbershop - Compute: CPU-Only EPYC 2 7R32 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 130 260 390 520 650 SE +/- 0.49, N = 3 SE +/- 0.40, N = 3 SE +/- 0.15, N = 3 SE +/- 0.12, N = 3 SE +/- 0.16, N = 3 SE +/- 0.10, N = 3 SE +/- 0.25, N = 3 SE +/- 0.30, N = 3 SE +/- 0.20, N = 3 SE +/- 0.22, N = 3 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 SE +/- 0.44, N = 3 SE +/- 0.20, N = 3 SE +/- 0.20, N = 3 SE +/- 0.17, N = 3 177.79 187.33 189.55 190.01 211.33 211.37 257.01 260.56 287.80 304.79 333.40 350.47 453.22 456.47 589.07 593.13
Timed LLVM Compilation This test times how long it takes to build the LLVM compiler. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 10.0 Time To Compile EPYC 2 7R32 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 6226R Xeon W-3275M 2 x Xeon Gold 5220R Xeon Platinum 8280 Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 5220R Xeon Gold 6226R Xeon Gold 5218 Xeon Silver 4216 110 220 330 440 550 SE +/- 0.72, N = 3 SE +/- 1.63, N = 3 SE +/- 1.01, N = 3 SE +/- 1.13, N = 3 SE +/- 3.50, N = 3 SE +/- 1.40, N = 3 SE +/- 3.51, N = 3 SE +/- 2.68, N = 3 SE +/- 2.03, N = 3 SE +/- 4.79, N = 3 SE +/- 5.07, N = 3 SE +/- 1.73, N = 3 SE +/- 1.84, N = 3 SE +/- 2.13, N = 3 SE +/- 3.37, N = 3 SE +/- 2.53, N = 3 200.04 218.05 221.52 232.05 244.91 244.94 279.68 281.68 286.78 308.74 317.61 347.83 430.43 433.19 501.22 531.15
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.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R 2 x Xeon Silver 4216 EPYC 2 7R32 2 x Xeon Platinum 8259CL NUMA off Xeon Platinum 8280 Xeon W-3275M Xeon Gold 6226R Xeon Platinum 8259CL Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off 7 14 21 28 35 SE +/- 0.24605, N = 3 SE +/- 0.12742, N = 3 SE +/- 0.12533, N = 3 SE +/- 0.15366, N = 3 SE +/- 0.00847, N = 3 SE +/- 0.00395, N = 3 SE +/- 0.00225, N = 3 SE +/- 0.04073, N = 3 SE +/- 0.15186, N = 3 SE +/- 0.02780, N = 3 SE +/- 0.03425, N = 3 SE +/- 0.08231, N = 3 SE +/- 0.01417, N = 3 SE +/- 0.03282, N = 3 SE +/- 0.60187, N = 9 SE +/- 0.06827, N = 7 28.85420 27.10600 26.59100 25.63030 23.15740 17.06080 16.51710 14.90970 14.16230 13.95810 13.64250 13.35290 13.01380 11.88830 8.41405 6.32971 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi
PostgreSQL pgbench This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write Xeon Platinum 8280 Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 2 x Xeon Gold 6226R 2 x Xeon Silver 4216 2 x Xeon Gold 5220R 2 x Xeon Platinum 8280 Xeon W-3275M EPYC 2 7R32 Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8259CL NUMA off 11K 22K 33K 44K 55K SE +/- 370.72, N = 3 SE +/- 56.97, N = 3 SE +/- 54.71, N = 3 SE +/- 1.34, N = 3 SE +/- 132.22, N = 3 SE +/- 119.26, N = 3 SE +/- 220.44, N = 3 SE +/- 158.35, N = 3 SE +/- 19.82, N = 3 SE +/- 85.02, N = 3 SE +/- 319.58, N = 12 SE +/- 245.15, N = 12 SE +/- 56.30, N = 3 SE +/- 141.57, N = 6 SE +/- 38.08, N = 3 SE +/- 408.27, N = 6 53139.06 46503.28 45518.59 40894.90 40373.30 37715.22 34916.03 34227.72 24466.91 11704.23 6105.73 5941.32 4009.41 3890.77 3197.74 3168.73 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
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.org Seconds, Fewer Is Better Blender 2.82 Blend File: Pabellon Barcelona - Compute: CPU-Only 2 x Xeon Platinum 8280 EPYC 2 7R32 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Silver 4216 Xeon Gold 5218 120 240 360 480 600 SE +/- 0.26, N = 3 SE +/- 0.51, N = 3 SE +/- 0.11, N = 3 SE +/- 0.15, N = 3 SE +/- 0.13, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 SE +/- 0.73, N = 3 SE +/- 0.50, N = 3 SE +/- 0.07, N = 3 SE +/- 0.22, N = 3 SE +/- 0.03, N = 3 SE +/- 0.46, N = 3 SE +/- 0.31, N = 3 129.01 132.04 139.00 139.11 157.99 158.13 207.41 208.30 246.31 265.41 272.72 305.20 400.96 404.78 531.39 531.98
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.org Seconds, Fewer Is Better Radiance Benchmark 5.0 Test: Serial Xeon W-3275M 2 x Xeon Platinum 8280 Xeon Platinum 8280 EPYC 2 7R32 2 x Xeon Gold 6226R Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Gold 5218 Xeon Gold 5220R 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Silver 4216 200 400 600 800 1000 665.70 728.25 728.36 730.70 745.69 746.69 746.92 747.84 749.92 753.43 753.64 841.32 841.65 842.10 907.76 909.32
Mlpack Benchmark Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_linearridgeregression Xeon Platinum 8280 EPYC 2 7R32 2 x Xeon Platinum 8280 Xeon Gold 6226R Xeon W-3275M Xeon Platinum 8259CL 2 x Xeon Gold 6226R Xeon Gold 5220R 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL 2 x Xeon Gold 5220R 2 x Xeon Platinum 8259CL NUMA off Xeon Gold 5218 2 x Xeon Platinum 8275CL NUMA off Xeon Silver 4216 2 x Xeon Silver 4216 0.6728 1.3456 2.0184 2.6912 3.364 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 15 SE +/- 0.04, N = 15 SE +/- 0.03, N = 3 SE +/- 0.02, N = 15 SE +/- 0.04, N = 15 SE +/- 0.06, N = 12 SE +/- 0.02, N = 12 SE +/- 0.03, N = 7 SE +/- 0.03, N = 15 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 1.67 1.79 1.82 1.93 1.99 2.00 2.08 2.25 2.30 2.36 2.39 2.42 2.46 2.46 2.97 2.99
Numpy Benchmark This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Score, More Is Better Numpy Benchmark Xeon W-3275M 2 x Xeon Platinum 8275CL Xeon Platinum 8280 EPYC 2 7R32 2 x Xeon Platinum 8280 Xeon Platinum 8259CL Xeon Gold 6226R 2 x Xeon Platinum 8275CL NUMA off Xeon Gold 5218 Xeon Gold 5220R 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R 2 x Xeon Platinum 8259CL NUMA off Xeon Silver 4216 2 x Xeon Silver 4216 80 160 240 320 400 SE +/- 2.73, N = 3 SE +/- 2.37, N = 3 SE +/- 2.42, N = 3 SE +/- 1.14, N = 3 SE +/- 3.00, N = 3 SE +/- 0.75, N = 3 SE +/- 0.54, N = 3 SE +/- 4.26, N = 3 SE +/- 2.01, N = 3 SE +/- 3.23, N = 3 SE +/- 0.76, N = 3 SE +/- 1.46, N = 3 SE +/- 0.65, N = 3 SE +/- 3.32, N = 3 SE +/- 0.89, N = 3 SE +/- 1.91, N = 3 367.56 338.44 330.33 323.58 321.82 321.13 318.87 315.66 315.14 313.76 310.40 304.16 300.73 293.53 272.12 262.78
PostgreSQL pgbench This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Only 2 x Xeon Platinum 8280 EPYC 2 7R32 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R Xeon W-3275M Xeon Platinum 8280 Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 5220R Xeon Gold 6226R Xeon Gold 5218 Xeon Silver 4216 200K 400K 600K 800K 1000K SE +/- 10457.35, N = 3 SE +/- 953.22, N = 3 SE +/- 2473.02, N = 3 SE +/- 1194.42, N = 3 SE +/- 1557.39, N = 3 SE +/- 13693.01, N = 9 SE +/- 2029.20, N = 3 SE +/- 494.87, N = 3 SE +/- 3571.60, N = 3 SE +/- 1625.61, N = 3 SE +/- 194.45, N = 3 SE +/- 568.07, N = 3 SE +/- 474.33, N = 3 SE +/- 358.06, N = 3 SE +/- 198.36, N = 3 SE +/- 517.49, N = 3 909916.49 891303.12 795715.31 790827.57 725740.72 629984.51 598798.57 587882.23 567696.51 560887.77 512031.42 501697.24 383120.69 376860.32 322051.63 313376.78 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
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.org ms, Fewer Is Better Renaissance 0.10.0 Test: Savina Reactors.IO EPYC 2 7R32 Xeon Platinum 8280 Xeon Gold 5220R Xeon Silver 4216 Xeon W-3275M 2 x Xeon Gold 5220R Xeon Platinum 8259CL 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL Xeon Gold 5218 Xeon Gold 6226R 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Gold 6226R 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Silver 4216 6K 12K 18K 24K 30K SE +/- 365.25, N = 20 SE +/- 593.14, N = 25 SE +/- 389.39, N = 25 SE +/- 251.20, N = 25 SE +/- 599.32, N = 25 SE +/- 496.64, N = 25 SE +/- 428.64, N = 25 SE +/- 474.27, N = 25 SE +/- 568.00, N = 25 SE +/- 516.85, N = 25 SE +/- 426.81, N = 25 SE +/- 504.51, N = 25 SE +/- 633.76, N = 25 SE +/- 482.43, N = 25 SE +/- 502.20, N = 25 SE +/- 436.95, N = 25 19303.56 21975.12 22776.30 22798.38 25186.67 26257.01 26711.17 26764.94 26906.89 27198.08 27198.86 27361.60 27973.00 28107.04 28251.83 28596.11
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.org Seconds, Fewer Is Better Blender 2.82 Blend File: Classroom - Compute: CPU-Only 2 x Xeon Platinum 8280 EPYC 2 7R32 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Silver 4216 Xeon Gold 5218 90 180 270 360 450 SE +/- 0.26, N = 3 SE +/- 0.40, N = 3 SE +/- 0.29, N = 3 SE +/- 0.11, N = 3 SE +/- 0.06, N = 3 SE +/- 0.17, N = 3 SE +/- 0.52, N = 3 SE +/- 0.18, N = 3 SE +/- 0.36, N = 3 SE +/- 0.32, N = 3 SE +/- 0.19, N = 3 SE +/- 0.14, N = 3 SE +/- 0.16, N = 3 SE +/- 0.39, N = 3 SE +/- 0.20, N = 3 SE +/- 0.29, N = 3 100.47 101.34 108.94 108.97 124.59 124.67 163.32 165.96 198.25 213.36 218.06 246.81 321.53 328.81 432.11 433.42
Mlpack Benchmark Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_qda Xeon Platinum 8280 Xeon Gold 6226R Xeon Platinum 8259CL Xeon W-3275M Xeon Gold 5220R Xeon Gold 5218 2 x Xeon Platinum 8280 EPYC 2 7R32 Xeon Silver 4216 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 5220R 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R 2 x Xeon Silver 4216 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 14 28 42 56 70 SE +/- 0.29, N = 3 SE +/- 0.46, N = 3 SE +/- 0.12, N = 3 SE +/- 0.18, N = 3 SE +/- 0.49, N = 4 SE +/- 0.43, N = 6 SE +/- 0.34, N = 3 SE +/- 0.28, N = 3 SE +/- 0.39, N = 3 SE +/- 0.19, N = 3 SE +/- 0.63, N = 3 SE +/- 0.54, N = 12 SE +/- 0.21, N = 3 SE +/- 0.51, N = 12 SE +/- 0.54, N = 3 SE +/- 1.16, N = 9 30.45 31.96 31.98 32.65 34.24 37.41 38.35 39.54 40.75 41.29 42.69 42.88 44.53 50.10 57.25 62.02
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.org FPS, More Is Better dav1d 0.6.0 Video Input: Chimera 1080p 10-bit EPYC 2 7R32 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8259CL Xeon Platinum 8280 Xeon Gold 6226R 2 x Xeon Silver 4216 Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 30 60 90 120 150 SE +/- 0.60, N = 3 SE +/- 0.30, N = 3 SE +/- 0.44, N = 3 SE +/- 0.04, N = 3 SE +/- 0.56, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.16, N = 3 SE +/- 0.47, N = 3 SE +/- 0.13, N = 3 SE +/- 0.12, N = 3 SE +/- 0.24, N = 3 SE +/- 0.16, N = 3 SE +/- 0.14, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 140.14 90.78 90.28 89.55 88.66 85.14 81.60 73.95 70.81 67.33 65.40 62.32 59.51 58.05 55.88 50.10 MIN: 101.2 / MAX: 212.94 MIN: 71.49 / MAX: 131.32 MIN: 71.05 / MAX: 131.54 MIN: 69.22 / MAX: 130.8 MIN: 69.45 / MAX: 129.53 MIN: 66.74 / MAX: 126.85 MIN: 55.07 / MAX: 147.52 MIN: 55.51 / MAX: 119.74 MIN: 54.24 / MAX: 115.34 MIN: 49.41 / MAX: 122.02 MIN: 49.2 / MAX: 111 MIN: 45.27 / MAX: 134.22 MIN: 45.13 / MAX: 93.29 MIN: 42.73 / MAX: 119.59 MIN: 40.96 / MAX: 112.64 MIN: 36.69 / MAX: 102.49 1. (CC) gcc options: -pthread
asmFish This is a test of asmFish, an advanced chess benchmark written in Assembly. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes/second, More Is Better asmFish 2018-07-23 1024 Hash Memory, 26 Depth 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL EPYC 2 7R32 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R Xeon Platinum 8280 2 x Xeon Silver 4216 Xeon W-3275M Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 30M 60M 90M 120M 150M SE +/- 491864.96, N = 3 SE +/- 1707658.59, N = 3 SE +/- 1547569.18, N = 3 SE +/- 617926.69, N = 3 SE +/- 1538634.72, N = 3 SE +/- 669620.24, N = 3 SE +/- 107032.55, N = 3 SE +/- 983078.22, N = 3 SE +/- 450047.19, N = 3 SE +/- 49212.27, N = 3 SE +/- 845752.34, N = 4 SE +/- 95127.60, N = 3 SE +/- 606619.65, N = 3 SE +/- 375245.33, N = 3 SE +/- 274137.19, N = 3 SE +/- 274506.10, N = 3 133839896 119912357 119549901 113278977 105070606 103033955 85501851 83894514 68762075 66895810 66225641 59350794 44614925 43217939 36561817 35085496
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.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: Path Tracer 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off EPYC 2 7R32 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R Xeon Platinum 8280 Xeon W-3275M Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 5220R Xeon Gold 6226R Xeon Gold 5218 Xeon Silver 4216 2 4 6 8 10 SE +/- 0.01, N = 5 SE +/- 0.01, N = 4 SE +/- 0.00, N = 12 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 7 SE +/- 0.00, N = 8 SE +/- 0.00, N = 3 SE +/- 0.00, N = 12 SE +/- 0.00, N = 3 SE +/- 0.00, N = 4 SE +/- 0.00, N = 4 SE +/- 0.00, N = 3 SE +/- 0.00, N = 6 SE +/- 0.00, N = 3 6.53 5.87 5.82 5.58 5.54 4.73 3.95 3.71 3.52 3.25 3.00 2.63 2.14 2.02 1.75 1.40 MIN: 5.18 / MAX: 6.58 MIN: 5.75 / MAX: 5.92 MIN: 4.69 / MAX: 5.88 MIN: 4.61 / MAX: 5.62 MIN: 5.49 / MAX: 5.59 MIN: 4.69 / MAX: 4.78 MIN: 3.41 / MAX: 3.98 MIN: 2.99 / MAX: 3.73 MIN: 3.48 / MAX: 3.53 MIN: 3.16 / MAX: 3.28 MIN: 2.99 / MAX: 3.01 MIN: 2.35 / MAX: 2.64 MIN: 2.13 / MAX: 2.15 MAX: 2.03 MIN: 1.74 / MAX: 1.76 MAX: 1.41
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.org M samples/sec, More Is Better LuxCoreRender 2.3 Scene: Rainbow Colors and Prism EPYC 2 7R32 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Silver 4216 Xeon Gold 5218 2 4 6 8 10 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.40, N = 15 SE +/- 0.11, N = 15 SE +/- 0.04, N = 3 SE +/- 0.37, N = 15 SE +/- 0.30, N = 12 SE +/- 0.13, N = 15 SE +/- 0.04, N = 3 SE +/- 0.03, N = 15 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 8.12 7.31 7.15 7.09 6.40 5.52 4.46 4.32 4.11 3.79 3.65 3.30 2.51 2.48 1.88 1.88 MIN: 7.87 / MAX: 8.3 MIN: 6.62 / MAX: 7.52 MIN: 2.92 / MAX: 8.11 MIN: 5.64 / MAX: 7.47 MIN: 5.65 / MAX: 6.54 MIN: 2.11 / MAX: 6.54 MIN: 1.23 / MAX: 4.91 MIN: 2.71 / MAX: 4.87 MIN: 3.96 / MAX: 4.16 MIN: 3.45 / MAX: 3.89 MIN: 3.56 / MAX: 3.67 MIN: 3.24 / MAX: 3.33 MIN: 2.44 / MAX: 2.56 MIN: 2.4 / MAX: 2.53 MIN: 1.84 / MAX: 1.92 MIN: 1.85 / MAX: 1.92
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.org Seconds, Fewer Is Better Timed MrBayes Analysis 3.2.7 Primate Phylogeny Analysis EPYC 2 7R32 Xeon Gold 6226R 2 x Xeon Gold 6226R 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL Xeon Platinum 8280 2 x Xeon Platinum 8280 Xeon Gold 5220R 2 x Xeon Gold 5220R Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off Xeon W-3275M Xeon Gold 5218 Xeon Silver 4216 2 x Xeon Silver 4216 40 80 120 160 200 SE +/- 0.68, N = 3 SE +/- 0.09, N = 3 SE +/- 0.25, N = 3 SE +/- 0.03, N = 3 SE +/- 1.63, N = 5 SE +/- 0.01, N = 3 SE +/- 0.37, N = 3 SE +/- 0.03, N = 3 SE +/- 0.27, N = 3 SE +/- 0.18, N = 3 SE +/- 0.32, N = 3 SE +/- 1.87, N = 3 SE +/- 0.13, N = 3 SE +/- 0.44, N = 3 SE +/- 0.15, N = 3 SE +/- 0.67, N = 3 92.36 123.70 124.26 124.30 125.87 128.85 129.99 134.48 134.93 138.85 139.75 141.90 143.35 147.73 193.47 194.50 -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 -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 -lreadline -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mmpx -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mmpx -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mmpx 1. (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
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.org Seconds, Fewer Is Better Timed GDB GNU Debugger Compilation 9.1 Time To Compile EPYC 2 7R32 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL Xeon Platinum 8259CL 2 x Xeon Gold 6226R Xeon W-3275M Xeon Gold 6226R 2 x Xeon Platinum 8280 Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 5220R Xeon Gold 5220R Xeon Gold 5218 2 x Xeon Silver 4216 Xeon Silver 4216 40 80 120 160 200 SE +/- 0.08, N = 3 SE +/- 0.37, N = 3 SE +/- 0.45, N = 3 SE +/- 0.11, N = 3 SE +/- 0.16, N = 3 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 SE +/- 0.17, N = 3 SE +/- 0.17, N = 3 SE +/- 0.25, N = 3 SE +/- 0.27, N = 3 SE +/- 0.09, N = 3 SE +/- 0.11, N = 3 SE +/- 0.09, N = 3 SE +/- 0.18, N = 3 SE +/- 0.07, N = 3 108.68 128.95 129.69 132.23 133.44 134.82 139.12 142.70 144.64 145.51 146.44 146.44 151.91 156.30 169.70 177.77
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.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Emily EPYC 2 7R32 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon W-3275M Xeon Platinum 8280 Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 80 160 240 320 400 147.69 152.09 152.90 154.98 161.85 163.71 177.66 180.65 196.93 197.65 219.32 222.97 276.77 284.28 328.14 345.39
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.org FPS, More Is Better OSPray 1.8.5 Demo: XFrog Forest - Renderer: SciVis 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL EPYC 2 7R32 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R Xeon Platinum 8280 Xeon W-3275M Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 5220R Xeon Gold 6226R Xeon Gold 5218 Xeon Silver 4216 3 6 9 12 15 SE +/- 0.00, N = 12 SE +/- 0.00, N = 13 SE +/- 0.00, N = 13 SE +/- 0.04, N = 3 SE +/- 0.00, N = 12 SE +/- 0.02, N = 7 SE +/- 0.00, N = 6 SE +/- 0.00, N = 12 SE +/- 0.00, N = 3 SE +/- 0.00, N = 8 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 6 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 12.05 11.36 11.36 11.03 10.42 10.32 7.19 7.09 6.25 5.72 5.38 4.57 3.70 3.68 3.01 2.34 MIN: 9.71 / MAX: 12.2 MIN: 10.99 / MAX: 11.49 MIN: 9.8 / MAX: 11.49 MIN: 10.75 / MAX: 11.24 MIN: 8.2 / MAX: 10.53 MIN: 10.1 / MAX: 10.42 MIN: 6.45 / MAX: 7.25 MIN: 6.37 / MAX: 7.14 MIN: 6.13 / MAX: 6.29 MIN: 5.56 / MAX: 5.78 MIN: 5.29 / MAX: 5.41 MIN: 4.08 / MAX: 4.61 MIN: 3.66 / MAX: 3.73 MIN: 3.64 / MAX: 3.7 MIN: 2.98 / MAX: 3.05 MIN: 2.3 / MAX: 2.36
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.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_googlenet_v3 - Data Type: bf16bf16bf16 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R Xeon Platinum 8280 2 x Xeon Gold 5220R Xeon W-3275M Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 100 200 300 400 500 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.20, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 SE +/- 0.42, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 86.54 93.28 93.36 106.71 106.89 137.73 166.98 187.17 188.61 207.91 246.45 269.99 369.29 484.59 484.90 MIN: 85.56 MIN: 92.44 MIN: 92.35 MIN: 105.9 MIN: 105.9 MIN: 136.67 MIN: 166.21 MIN: 186.33 MIN: 178.56 MIN: 207.27 MIN: 245.49 MIN: 268.99 MIN: 365.68 MIN: 484.13 MIN: 484.15 1. (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.org FPS, More Is Better OSPray 1.8.5 Demo: XFrog Forest - Renderer: Path Tracer 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off EPYC 2 7R32 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R Xeon Platinum 8280 Xeon W-3275M Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 5220R Xeon Gold 6226R Xeon Gold 5218 Xeon Silver 4216 2 4 6 8 10 SE +/- 0.00, N = 12 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 6 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 4 SE +/- 0.00, N = 7 SE +/- 0.00, N = 6 SE +/- 0.00, N = 5 SE +/- 0.00, N = 6 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 6.67 6.25 6.24 5.85 5.71 5.71 3.98 3.88 3.46 3.17 2.96 2.55 2.06 2.02 1.68 1.31 MIN: 5.85 / MAX: 6.76 MIN: 5.68 / MAX: 6.29 MIN: 6.1 / MAX: 6.29 MIN: 5.65 / MAX: 5.99 MIN: 5.59 / MAX: 5.75 MIN: 5.08 / MAX: 5.78 MIN: 3.64 / MAX: 4.02 MIN: 3.57 / MAX: 3.92 MIN: 3.41 / MAX: 3.47 MIN: 3.09 / MAX: 3.19 MIN: 2.92 / MAX: 2.99 MIN: 2.28 / MAX: 2.57 MIN: 2.04 / MAX: 2.07 MIN: 2 / MAX: 2.04 MIN: 1.67 MIN: 1.3 / MAX: 1.32
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.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_googlenet_v3 - Data Type: u8s8f32 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL NUMA off Xeon Platinum 8280 2 x Xeon Gold 6226R Xeon Platinum 8259CL Xeon W-3275M 2 x Xeon Gold 5220R 2 x Xeon Platinum 8275CL Xeon Gold 6226R 2 x Xeon Silver 4216 Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 EPYC 2 7R32 160 320 480 640 800 SE +/- 0.03597, N = 3 SE +/- 0.01740, N = 3 SE +/- 0.02555, N = 3 SE +/- 0.02611, N = 3 SE +/- 0.01386, N = 3 SE +/- 0.01218, N = 3 SE +/- 0.00834, N = 3 SE +/- 0.01662, N = 3 SE +/- 0.00643, N = 3 SE +/- 0.29660, N = 3 SE +/- 0.01762, N = 3 SE +/- 0.01146, N = 3 SE +/- 0.02138, N = 3 SE +/- 0.01482, N = 3 SE +/- 0.02504, N = 3 SE +/- 7.24186, N = 3 7.46050 7.63651 8.74794 10.48410 11.29000 11.32820 12.70590 13.45040 15.75420 17.75490 17.97350 23.70280 28.45320 34.60310 45.05020 730.30600 MIN: 698.32 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL 2 x Xeon Gold 6226R Xeon Platinum 8280 EPYC 2 7R32 Xeon Platinum 8259CL Xeon W-3275M 2 x Xeon Gold 5220R Xeon Gold 6226R 2 x Xeon Silver 4216 Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 40 80 120 160 200 SE +/- 0.09, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.10, N = 3 SE +/- 0.17, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.19, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.24, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 23.18 25.05 25.07 25.77 33.63 36.37 42.08 42.54 48.06 49.87 54.82 69.14 87.54 108.16 131.09 171.43 MIN: 32.49 MIN: 34.65 MIN: 41.31 MIN: 40.72 MIN: 47.62 MIN: 44.78 MIN: 54.08 MIN: 68.48 MIN: 86.64 MIN: 106.43 MIN: 130.56 MIN: 170.75 1. (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.org Seconds, Fewer Is Better Blender 2.82 Blend File: Fishy Cat - Compute: CPU-Only EPYC 2 7R32 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 50 100 150 200 250 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.13, N = 3 SE +/- 0.11, N = 3 SE +/- 0.14, N = 3 SE +/- 0.20, N = 3 SE +/- 0.06, N = 3 SE +/- 0.16, N = 3 SE +/- 0.05, N = 3 SE +/- 0.19, N = 3 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 65.67 66.39 69.93 70.04 79.00 79.22 96.41 98.24 110.67 118.09 125.35 134.22 173.95 175.95 229.28 229.71
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.org Seconds, Fewer Is Better DeepSpeech 0.6 Acceleration: CPU EPYC 2 7R32 2 x Xeon Platinum 8275CL Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL Xeon Platinum 8280 Xeon Gold 6226R 2 x Xeon Platinum 8280 2 x Xeon Gold 6226R Xeon W-3275M 2 x Xeon Gold 5220R Xeon Gold 5220R Xeon Gold 5218 2 x Xeon Silver 4216 2 x Xeon Platinum 8259CL NUMA off Xeon Silver 4216 2 x Xeon Platinum 8275CL NUMA off 30 60 90 120 150 SE +/- 0.08, N = 3 SE +/- 1.06, N = 3 SE +/- 1.18, N = 8 SE +/- 0.65, N = 3 SE +/- 1.60, N = 3 SE +/- 1.84, N = 3 SE +/- 1.16, N = 3 SE +/- 0.89, N = 3 SE +/- 0.15, N = 3 SE +/- 0.47, N = 3 SE +/- 1.11, N = 3 SE +/- 0.75, N = 3 SE +/- 0.71, N = 3 SE +/- 1.04, N = 3 SE +/- 1.22, N = 3 SE +/- 2.07, N = 4 72.82 113.14 117.36 117.73 118.09 119.79 122.22 123.39 123.85 125.12 126.08 128.41 133.01 135.05 136.00 138.26
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.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: SciVis 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off EPYC 2 7R32 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R Xeon Platinum 8280 Xeon W-3275M Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 5220R Xeon Gold 6226R Xeon Gold 5218 Xeon Silver 4216 15 30 45 60 75 SE +/- 0.62, N = 15 SE +/- 0.00, N = 12 SE +/- 0.54, N = 12 SE +/- 0.00, N = 3 SE +/- 0.92, N = 4 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.60, N = 3 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.36, N = 3 SE +/- 0.07, N = 12 SE +/- 0.00, N = 12 SE +/- 0.04, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 69.52 66.67 63.54 62.50 61.58 58.82 43.48 42.27 38.46 34.48 32.97 27.84 23.26 22.69 18.87 14.71 MIN: 37.04 / MAX: 71.43 MIN: 55.56 MIN: 35.71 / MAX: 66.67 MIN: 35.71 MIN: 55.56 / MAX: 62.5 MIN: 52.63 / MAX: 62.5 MIN: 28.57 / MAX: 45.45 MIN: 28.57 / MAX: 43.48 MIN: 37.04 MIN: 30.3 / MAX: 35.71 MIN: 32.26 / MAX: 33.33 MIN: 17.86 / MAX: 28.57 MIN: 21.74 / MAX: 23.81 MIN: 21.74 / MAX: 22.73 MIN: 18.52 / MAX: 19.23 MIN: 14.29 / MAX: 14.93
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.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Material Tester Xeon Platinum 8280 Xeon W-3275M Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R EPYC 2 7R32 Xeon Gold 5218 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R Xeon Silver 4216 2 x Xeon Platinum 8275CL 2 x Xeon Gold 5220R 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Silver 4216 40 80 120 160 200 123.98 124.15 128.00 156.61 162.86 175.19 179.75 185.23 185.36 188.78 189.30 189.46 193.44 194.85 197.29 197.74
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.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.4 Time To Compile EPYC 2 7R32 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8259CL NUMA off Xeon W-3275M 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 16 32 48 64 80 SE +/- 0.19, N = 13 SE +/- 0.24, N = 13 SE +/- 0.25, N = 14 SE +/- 0.23, N = 14 SE +/- 0.38, N = 14 SE +/- 0.37, N = 14 SE +/- 0.35, N = 9 SE +/- 0.37, N = 8 SE +/- 0.34, N = 10 SE +/- 0.42, N = 8 SE +/- 0.44, N = 7 SE +/- 0.41, N = 10 SE +/- 0.88, N = 3 SE +/- 0.87, N = 4 SE +/- 0.88, N = 4 SE +/- 0.99, N = 4 24.01 27.10 27.31 27.58 29.26 29.28 36.37 36.60 36.70 40.90 41.14 45.32 57.77 59.01 67.16 71.77
Mlpack Benchmark Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_ica EPYC 2 7R32 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off Xeon W-3275M 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL Xeon Platinum 8259CL Xeon Gold 6226R 2 x Xeon Platinum 8280 Xeon Platinum 8280 Xeon Gold 5220R Xeon Gold 5218 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Silver 4216 2 x Xeon Silver 4216 20 40 60 80 100 SE +/- 0.48, N = 15 SE +/- 0.51, N = 15 SE +/- 0.26, N = 3 SE +/- 0.11, N = 3 SE +/- 0.35, N = 3 SE +/- 0.80, N = 3 SE +/- 0.34, N = 3 SE +/- 0.45, N = 3 SE +/- 0.59, N = 3 SE +/- 0.21, N = 3 SE +/- 0.25, N = 3 SE +/- 0.44, N = 3 SE +/- 0.30, N = 3 SE +/- 1.07, N = 4 SE +/- 0.80, N = 3 SE +/- 1.29, N = 3 49.47 53.50 53.66 54.91 57.69 58.48 61.20 61.82 63.35 67.36 68.19 68.78 74.63 77.41 81.36 94.45
PyPerformance PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: python_startup 2 x Xeon Gold 6226R Xeon Gold 6226R Xeon Gold 5218 2 x Xeon Gold 5220R Xeon Platinum 8280 2 x Xeon Platinum 8280 Xeon Gold 5220R 2 x Xeon Platinum 8259CL Xeon Platinum 8259CL Xeon Silver 4216 2 x Xeon Silver 4216 EPYC 2 7R32 Xeon W-3275M 2 x Xeon Platinum 8259CL NUMA off 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 SE +/- 0.00, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 10.9 11.0 11.1 11.2 11.2 11.2 11.3 11.3 11.4 15.4 15.4 16.3 17.7 22.6
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.org Seconds, Fewer Is Better Radiance Benchmark 5.0 Test: SMP Parallel EPYC 2 7R32 Xeon W-3275M 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Gold 5220R 2 x Xeon Platinum 8275CL 2 x Xeon Gold 6226R Xeon Platinum 8280 Xeon Gold 5218 Xeon Gold 6226R Xeon Gold 5220R 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Silver 4216 70 140 210 280 350 219.65 219.84 226.08 227.16 230.56 232.70 233.04 235.00 241.90 242.00 242.52 255.59 258.34 273.13 281.25 299.74
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.org Seconds, Fewer Is Better Build2 0.12 Time To Compile EPYC 2 7R32 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL Xeon W-3275M 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 20 40 60 80 100 SE +/- 0.40, N = 3 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 SE +/- 0.75, N = 6 SE +/- 0.14, N = 3 SE +/- 0.49, N = 3 SE +/- 0.19, N = 3 SE +/- 0.09, N = 3 SE +/- 0.13, N = 3 SE +/- 0.13, N = 3 SE +/- 0.03, N = 3 SE +/- 0.11, N = 3 SE +/- 0.05, N = 3 SE +/- 0.15, N = 3 SE +/- 0.08, N = 3 SE +/- 0.15, N = 3 59.96 62.78 64.42 64.50 66.42 66.67 69.20 70.61 72.15 74.12 76.15 86.33 88.98 91.64 101.72 109.70
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.org Seconds, Fewer Is Better Blender 2.82 Blend File: BMW27 - Compute: CPU-Only 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off EPYC 2 7R32 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Silver 4216 Xeon Gold 5218 30 60 90 120 150 SE +/- 0.09, N = 3 SE +/- 0.14, N = 3 SE +/- 0.08, N = 3 SE +/- 0.10, N = 3 SE +/- 0.11, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.13, N = 3 SE +/- 0.09, N = 3 SE +/- 0.12, N = 3 SE +/- 0.15, N = 3 SE +/- 0.14, N = 3 SE +/- 0.17, N = 3 SE +/- 0.23, N = 3 SE +/- 0.29, N = 3 SE +/- 0.28, N = 3 38.79 41.68 41.72 41.76 47.63 48.00 59.45 60.67 69.80 74.96 78.72 86.89 111.82 113.30 149.02 149.39
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.org FPS, More Is Better OSPray 1.8.5 Demo: NASA Streamlines - Renderer: Path Tracer 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off EPYC 2 7R32 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 Xeon W-3275M Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 4 8 12 16 20 SE +/- 0.000, N = 12 SE +/- 0.073, N = 4 SE +/- 0.000, N = 12 SE +/- 0.068, N = 4 SE +/- 0.000, N = 3 SE +/- 0.080, N = 3 SE +/- 0.037, N = 3 SE +/- 0.000, N = 12 SE +/- 0.030, N = 3 SE +/- 0.006, N = 12 SE +/- 0.022, N = 3 SE +/- 0.000, N = 12 SE +/- 0.008, N = 4 SE +/- 0.000, N = 12 SE +/- 0.006, N = 3 SE +/- 0.000, N = 15 18.180 17.020 16.950 16.600 15.625 15.540 10.560 10.420 9.490 8.690 8.090 6.620 5.520 5.380 4.370 3.410 MIN: 12.2 / MAX: 18.52 MIN: 11.76 / MAX: 17.54 MIN: 16.13 / MAX: 17.54 MIN: 15.87 / MAX: 16.95 MIN: 11.11 / MAX: 15.87 MIN: 14.93 / MAX: 15.87 MIN: 8.77 / MAX: 10.75 MIN: 8.47 / MAX: 10.53 MIN: 9.26 / MAX: 9.62 MIN: 8.33 / MAX: 9.01 MIN: 7.94 / MAX: 8.2 MIN: 5.52 / MAX: 6.76 MIN: 5.43 / MAX: 5.62 MIN: 5.29 / MAX: 5.46 MIN: 4.29 / MAX: 4.44 MIN: 3.33 / MAX: 3.45
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.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Disney Material EPYC 2 7R32 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 40 80 120 160 200 62.43 68.20 68.61 68.62 73.22 73.58 84.84 88.86 103.83 106.64 107.50 120.17 155.23 158.77 182.56 194.40
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.org Nodes Per Second, More Is Better Stockfish 9 Total Time 2 x Xeon Platinum 8280 EPYC 2 7R32 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 30M 60M 90M 120M 150M SE +/- 902995.35, N = 3 SE +/- 1223161.47, N = 3 SE +/- 734636.23, N = 3 SE +/- 996126.46, N = 3 SE +/- 102308.18, N = 3 SE +/- 336693.20, N = 3 SE +/- 956232.23, N = 3 SE +/- 316618.77, N = 3 SE +/- 829358.84, N = 3 SE +/- 709349.35, N = 3 SE +/- 553774.93, N = 3 SE +/- 114508.53, N = 3 SE +/- 324752.06, N = 3 SE +/- 184471.68, N = 3 SE +/- 188043.56, N = 3 SE +/- 406404.40, N = 3 119715795 116765028 109874307 108412514 104106676 103513853 75203729 74235829 62891312 61170651 60569696 54437117 39776292 38167326 32424332 31174576 1. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto
Chaos Group V-RAY This is a test of Chaos Group's V-RAY benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ksamples, More Is Better Chaos Group V-RAY 4.10.07 Mode: CPU 2 x Xeon Platinum 8280 EPYC 2 7R32 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R Xeon Platinum 8280 Xeon W-3275M Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 6226R Xeon Gold 5220R Xeon Silver 4216 Xeon Gold 5218 14K 28K 42K 56K 70K SE +/- 474.70, N = 3 SE +/- 183.86, N = 3 SE +/- 399.24, N = 3 SE +/- 223.71, N = 3 SE +/- 48.95, N = 3 SE +/- 332.60, N = 3 SE +/- 178.87, N = 3 SE +/- 369.19, N = 3 SE +/- 306.00, N = 3 SE +/- 401.71, N = 3 SE +/- 88.49, N = 3 SE +/- 223.28, N = 3 SE +/- 58.00, N = 3 SE +/- 50.25, N = 3 SE +/- 34.43, N = 3 SE +/- 69.72, N = 3 64331 62897 58525 58326 53051 51803 40270 34749 34710 33014 29061 27592 22074 21886 17105 16981
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.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R EPYC 2 7R32 Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 1300 2600 3900 5200 6500 SE +/- 148.86, N = 12 SE +/- 89.39, N = 3 SE +/- 84.22, N = 3 SE +/- 124.07, N = 12 SE +/- 54.90, N = 4 SE +/- 5.75, N = 3 SE +/- 46.76, N = 4 SE +/- 4.09, N = 3 SE +/- 2.84, N = 3 SE +/- 38.58, N = 4 SE +/- 8.86, N = 3 SE +/- 6.98, N = 3 SE +/- 4.92, N = 3 SE +/- 6.21, N = 3 6284.65 5310.16 5284.34 3969.60 3780.59 3570.46 3283.38 3210.52 3144.70 2677.64 2094.53 1966.61 1635.78 1571.49 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. 2 x Xeon Platinum 8280: Open MPI 4.0.3rc4 3. 2 x Xeon Platinum 8259CL: Open MPI 3.1.3 4. 2 x Xeon Platinum 8259CL NUMA off: Open MPI 3.1.3 5. 2 x Xeon Gold 6226R: Open MPI 4.0.3rc4 6. 2 x Xeon Gold 5220R: Open MPI 4.0.3rc4 7. EPYC 2 7R32: Open MPI 3.1.3 8. Xeon Platinum 8280: Open MPI 4.0.3rc4 9. Xeon W-3275M: Open MPI 3.1.3 10. 2 x Xeon Silver 4216: Open MPI 4.0.3rc4 11. Xeon Platinum 8259CL: Open MPI 3.1.3 12. Xeon Gold 6226R: Open MPI 4.0.3rc4 13. Xeon Gold 5220R: Open MPI 4.0.3rc4 14. Xeon Gold 5218: Open MPI 4.0.3rc4 15. Xeon Silver 4216: Open MPI 4.0.3rc4
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.org ms, Fewer Is Better Renaissance 0.10.0 Test: Apache Spark PageRank Xeon Platinum 8280 Xeon W-3275M EPYC 2 7R32 Xeon Gold 5220R Xeon Gold 6226R Xeon Platinum 8259CL 2 x Xeon Platinum 8280 Xeon Gold 5218 2 x Xeon Platinum 8275CL 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R 2 x Xeon Platinum 8275CL NUMA off Xeon Silver 4216 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Silver 4216 6K 12K 18K 24K 30K SE +/- 169.44, N = 5 SE +/- 165.27, N = 5 SE +/- 198.48, N = 5 SE +/- 217.63, N = 5 SE +/- 29.95, N = 5 SE +/- 154.16, N = 5 SE +/- 286.23, N = 6 SE +/- 172.76, N = 5 SE +/- 181.72, N = 25 SE +/- 165.91, N = 5 SE +/- 255.27, N = 5 SE +/- 286.23, N = 5 SE +/- 195.96, N = 5 SE +/- 278.82, N = 5 SE +/- 232.21, N = 5 SE +/- 374.59, N = 5 20621.23 21015.54 21641.95 21704.49 21743.02 22226.85 23588.40 23703.03 24505.96 24522.22 24540.72 24666.36 25271.43 25275.16 25636.69 28045.92
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.org M samples/sec, More Is Better LuxCoreRender 2.3 Scene: DLSC EPYC 2 7R32 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Silver 4216 Xeon Gold 5218 2 4 6 8 10 SE +/- 0.0970, N = 3 SE +/- 0.0948, N = 3 SE +/- 0.0164, N = 3 SE +/- 0.0262, N = 3 SE +/- 0.0353, N = 3 SE +/- 0.0279, N = 3 SE +/- 0.0036, N = 3 SE +/- 0.0120, N = 3 SE +/- 0.0032, N = 3 SE +/- 0.0035, N = 3 SE +/- 0.0265, N = 3 SE +/- 0.0050, N = 3 SE +/- 0.0145, N = 3 SE +/- 0.0243, N = 3 SE +/- 0.0165, N = 3 SE +/- 0.0034, N = 3 7.2800 7.1900 6.7500 6.7300 5.8800 5.8600 4.5183 4.4400 3.7900 3.5300 3.4300 3.0400 2.3500 2.3200 1.7700 1.7400 MIN: 7.01 / MAX: 7.86 MIN: 6.83 / MAX: 7.6 MIN: 6.62 / MAX: 7.08 MIN: 6.54 / MAX: 7.08 MIN: 5.75 / MAX: 6.19 MIN: 5.7 / MAX: 6.16 MIN: 4.4 / MAX: 4.76 MIN: 4.34 / MAX: 4.63 MIN: 3.65 / MAX: 3.94 MIN: 3.46 / MAX: 3.66 MIN: 3.33 / MAX: 3.63 MIN: 2.93 / MAX: 3.16 MIN: 2.24 / MAX: 2.46 MIN: 2.2 / MAX: 2.43 MIN: 1.68 / MAX: 1.85 MIN: 1.67 / MAX: 1.79
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.org ms, Fewer Is Better Renaissance 0.10.0 Test: Apache Spark Bayes Xeon Platinum 8280 Xeon W-3275M Xeon Gold 6226R Xeon Platinum 8259CL EPYC 2 7R32 Xeon Gold 5220R 2 x Xeon Platinum 8280 2 x Xeon Gold 6226R Xeon Gold 5218 2 x Xeon Platinum 8259CL Xeon Silver 4216 2 x Xeon Gold 5220R 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Silver 4216 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 1100 2200 3300 4400 5500 SE +/- 19.41, N = 5 SE +/- 30.38, N = 7 SE +/- 28.09, N = 25 SE +/- 26.07, N = 25 SE +/- 26.28, N = 25 SE +/- 38.41, N = 5 SE +/- 36.17, N = 25 SE +/- 38.94, N = 25 SE +/- 26.06, N = 25 SE +/- 47.41, N = 25 SE +/- 37.40, N = 25 SE +/- 42.87, N = 25 SE +/- 55.66, N = 25 SE +/- 65.14, N = 25 SE +/- 57.72, N = 25 SE +/- 90.85, N = 25 2674.18 2743.62 2856.85 3017.33 3057.06 3150.10 3228.63 3405.41 3477.33 3495.61 3588.69 3662.77 3813.75 4199.41 4510.83 5185.62
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.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: MD5 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 EPYC 2 7R32 2 x Xeon Silver 4216 Xeon W-3275M Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 2M 4M 6M 8M 10M SE +/- 67263.16, N = 3 SE +/- 5783.12, N = 3 SE +/- 39218.76, N = 3 SE +/- 11259.56, N = 3 SE +/- 41921.89, N = 3 SE +/- 17032.65, N = 3 SE +/- 9643.65, N = 3 SE +/- 14468.36, N = 3 SE +/- 30550.50, N = 3 SE +/- 4509.25, N = 3 SE +/- 14294.52, N = 3 SE +/- 9073.77, N = 3 SE +/- 11015.14, N = 3 SE +/- 6806.86, N = 3 SE +/- 8171.77, N = 3 SE +/- 1452.97, N = 3 7880000 7388333 7350667 6608333 6554667 4977667 4821000 4090000 3972000 3764000 3654000 3384000 2583000 2506000 1912667 1893333 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
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.org days/ns, Fewer Is Better NAMD 2.13 ATPase Simulation - 327,506 Atoms 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off EPYC 2 7R32 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 2 x Xeon Silver 4216 Xeon W-3275M Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 0.3414 0.6828 1.0242 1.3656 1.707 SE +/- 0.00133, N = 3 SE +/- 0.00038, N = 3 SE +/- 0.00012, N = 3 SE +/- 0.00084, N = 3 SE +/- 0.00104, N = 3 SE +/- 0.00612, N = 3 SE +/- 0.00060, N = 3 SE +/- 0.00193, N = 3 SE +/- 0.00775, N = 15 SE +/- 0.00063, N = 3 SE +/- 0.00117, N = 3 SE +/- 0.00122, N = 3 SE +/- 0.00100, N = 3 SE +/- 0.00193, N = 3 0.36226 0.44551 0.45422 0.48614 0.58237 0.60333 0.70709 0.76982 0.81434 0.86925 1.13586 1.15745 1.51168 1.51721
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.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_3d - Data Type: u8s8f32 2 x Xeon Platinum 8280 EPYC 2 7R32 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 3K 6K 9K 12K 15K SE +/- 7.97, N = 3 SE +/- 25.92, N = 3 SE +/- 4.78, N = 3 SE +/- 0.59, N = 3 SE +/- 11.90, N = 3 SE +/- 7.22, N = 3 SE +/- 10.40, N = 3 SE +/- 3.52, N = 3 SE +/- 11.11, N = 3 SE +/- 41.02, N = 3 SE +/- 109.20, N = 3 SE +/- 5.52, N = 3 SE +/- 9.11, N = 3 SE +/- 11.33, N = 3 SE +/- 2.59, N = 3 SE +/- 13.03, N = 3 3005.48 3076.76 3250.89 3252.48 3548.60 3551.38 4821.24 4896.41 5919.94 6183.11 6329.94 7095.62 9374.60 9696.92 11821.30 12300.30 MIN: 2934.55 MIN: 3011.81 MIN: 3176.52 MIN: 3175.14 MIN: 3529.41 MIN: 3527.13 MIN: 4760.44 MIN: 4854.07 MIN: 5895.99 MIN: 5934.01 MIN: 6190.58 MIN: 7085.95 MIN: 9350.22 MIN: 9656.48 MIN: 11811.3 MIN: 12254 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -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.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: ETC1S Xeon W-3275M Xeon Platinum 8280 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off EPYC 2 7R32 2 x Xeon Gold 5220R Xeon Gold 6226R 2 x Xeon Gold 6226R Xeon Gold 5220R Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off Xeon Gold 5218 2 x Xeon Silver 4216 Xeon Silver 4216 15 30 45 60 75 SE +/- 0.48, N = 3 SE +/- 0.12, N = 3 SE +/- 0.15, N = 3 SE +/- 0.11, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.21, N = 3 SE +/- 0.05, N = 3 SE +/- 0.18, N = 3 SE +/- 0.23, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 SE +/- 0.31, N = 3 SE +/- 0.14, N = 3 SE +/- 0.08, N = 3 47.65 51.45 52.61 52.69 53.14 54.31 54.55 54.79 54.95 56.02 57.40 57.83 58.28 58.47 65.64 67.46 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
PyPerformance PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: float Xeon W-3275M Xeon Platinum 8280 2 x Xeon Platinum 8280 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Gold 6226R Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off Xeon Silver 4216 2 x Xeon Silver 4216 30 60 90 120 150 SE +/- 0.12, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 94.5 109.0 109.0 113.0 113.0 114.0 114.0 115.0 122.0 123.0 123.0 137.0 137.0
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.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver Xeon W-3275M EPYC 2 7R32 2 x Xeon Platinum 8280 Xeon Platinum 8280 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Gold 6226R Xeon Gold 5218 2 x Xeon Gold 5220R Xeon Gold 6226R Xeon Gold 5220R Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off Xeon Silver 4216 2 x Xeon Silver 4216 800 1600 2400 3200 4000 SE +/- 3.72, N = 3 SE +/- 22.45, N = 3 SE +/- 5.39, N = 3 SE +/- 4.11, N = 3 SE +/- 0.96, N = 3 SE +/- 1.27, N = 3 SE +/- 0.77, N = 3 SE +/- 1.15, N = 3 SE +/- 5.10, N = 3 SE +/- 1.26, N = 3 SE +/- 1.90, N = 3 SE +/- 1.29, N = 3 SE +/- 1.57, N = 3 SE +/- 2.97, N = 3 SE +/- 1.23, N = 3 SE +/- 1.18, N = 3 3866.09 3769.72 3514.60 3510.21 3440.52 3430.77 3410.38 3405.04 3404.69 3401.16 3398.40 3152.50 3147.91 3130.86 2823.60 2817.67 1. (CC) gcc options: -O3 -mavx2
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.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch All - Data Type: u8s8f32 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8280 Xeon Platinum 8280 Xeon Platinum 8259CL Xeon W-3275M 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R Xeon Gold 6226R Xeon Gold 5220R 2 x Xeon Silver 4216 Xeon Gold 5218 2 x Xeon Platinum 8275CL Xeon Silver 4216 EPYC 2 7R32 30 60 90 120 150 SE +/- 0.00908, N = 3 SE +/- 0.01481, N = 3 SE +/- 0.04146, N = 4 SE +/- 0.00398, N = 3 SE +/- 0.00119, N = 3 SE +/- 0.03226, N = 3 SE +/- 0.01731, N = 3 SE +/- 0.03777, N = 3 SE +/- 0.03959, N = 3 SE +/- 0.01160, N = 3 SE +/- 0.02448, N = 3 SE +/- 0.04012, N = 3 SE +/- 0.00870, N = 3 SE +/- 0.06319, N = 3 SE +/- 0.03131, N = 3 SE +/- 0.23997, N = 3 2.78193 3.04866 3.11002 3.23121 3.43236 3.59218 3.84746 4.08605 4.11779 4.53821 4.61054 4.82603 4.83875 5.36708 5.59275 149.33900 MIN: 144.74 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch All - Data Type: f32 2 x Xeon Platinum 8259CL NUMA off Xeon Platinum 8280 Xeon W-3275M Xeon Platinum 8259CL Xeon Gold 6226R EPYC 2 7R32 Xeon Gold 5220R Xeon Gold 5218 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL Xeon Silver 4216 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R 2 x Xeon Silver 4216 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 5 10 15 20 25 SE +/- 0.00603, N = 3 SE +/- 0.00854, N = 3 SE +/- 0.10112, N = 3 SE +/- 0.03341, N = 3 SE +/- 0.01593, N = 3 SE +/- 0.01277, N = 3 SE +/- 0.00905, N = 3 SE +/- 0.02892, N = 3 SE +/- 0.01419, N = 3 SE +/- 0.03588, N = 3 SE +/- 0.01401, N = 3 SE +/- 0.06373, N = 3 SE +/- 0.02232, N = 3 SE +/- 0.05182, N = 3 SE +/- 0.00546, N = 3 SE +/- 0.07053, N = 3 6.65842 6.79509 7.54439 7.89071 8.84233 8.88390 8.90795 9.30959 9.52466 9.97669 10.19300 10.52390 10.63480 11.42150 12.68200 19.10300 MIN: 6.25 MIN: 6.68 MIN: 6.71 MIN: 7.76 MIN: 8.73 MIN: 8.36 MIN: 8.69 MIN: 9.16 MIN: 9.28 MIN: 9.62 MIN: 9.79 MIN: 10.17 MIN: 10.26 MIN: 11.02 MIN: 12.39 MIN: 18.63 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
PyPerformance PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: regex_compile Xeon W-3275M Xeon Platinum 8280 2 x Xeon Platinum 8280 2 x Xeon Gold 5220R Xeon Gold 5218 2 x Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 6226R 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off Xeon Platinum 8259CL Xeon Silver 4216 2 x Xeon Silver 4216 EPYC 2 7R32 50 100 150 200 250 SE +/- 1.20, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 157 164 164 167 167 167 168 168 200 200 200 204 204 213
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.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C 2 x Xeon Platinum 8280 EPYC 2 7R32 2 x Xeon Platinum 8259CL 2 x Xeon Gold 5220R 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 6226R Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Gold 6226R Xeon Platinum 8259CL Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 30K 60K 90K 120K 150K SE +/- 78.84, N = 3 SE +/- 500.22, N = 3 SE +/- 107.83, N = 3 SE +/- 42.06, N = 3 SE +/- 64.74, N = 3 SE +/- 86.40, N = 3 SE +/- 52.95, N = 3 SE +/- 127.07, N = 3 SE +/- 124.40, N = 3 SE +/- 27.55, N = 3 SE +/- 15.49, N = 3 SE +/- 44.99, N = 3 SE +/- 54.74, N = 3 SE +/- 4.15, N = 3 136046.53 106415.53 104107.99 100761.29 84766.14 77470.67 71842.34 69347.58 65509.98 56576.12 51975.35 50787.79 48617.05 46389.79 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. 2 x Xeon Platinum 8280: Open MPI 4.0.3rc4 3. EPYC 2 7R32: Open MPI 3.1.3 4. 2 x Xeon Platinum 8259CL: Open MPI 3.1.3 5. 2 x Xeon Gold 5220R: Open MPI 4.0.3rc4 6. 2 x Xeon Platinum 8259CL NUMA off: Open MPI 3.1.3 7. 2 x Xeon Gold 6226R: Open MPI 4.0.3rc4 8. Xeon Platinum 8280: Open MPI 4.0.3rc4 9. Xeon W-3275M: Open MPI 3.1.3 10. 2 x Xeon Silver 4216: Open MPI 4.0.3rc4 11. Xeon Gold 6226R: Open MPI 4.0.3rc4 12. Xeon Platinum 8259CL: Open MPI 3.1.3 13. Xeon Gold 5220R: Open MPI 4.0.3rc4 14. Xeon Gold 5218: Open MPI 4.0.3rc4 15. Xeon Silver 4216: Open MPI 4.0.3rc4
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.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_3d - Data Type: bf16bf16bf16 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R Xeon Platinum 8280 2 x Xeon Gold 5220R Xeon W-3275M Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 9 18 27 36 45 SE +/- 0.00328, N = 3 SE +/- 0.00469, N = 3 SE +/- 0.00882, N = 3 SE +/- 0.00811, N = 3 SE +/- 0.00172, N = 3 SE +/- 0.00770, N = 3 SE +/- 0.00390, N = 3 SE +/- 0.00301, N = 3 SE +/- 0.24390, N = 4 SE +/- 0.00403, N = 3 SE +/- 0.00466, N = 3 SE +/- 0.00584, N = 3 SE +/- 0.01559, N = 3 SE +/- 0.00339, N = 3 SE +/- 0.00904, N = 3 7.92912 8.64707 8.71234 9.18751 9.20665 11.60760 14.07800 15.21770 16.59060 17.32170 20.51630 22.42430 29.91730 39.99850 40.01920 MIN: 8.43 MIN: 8.5 MIN: 9.03 MIN: 9.04 MIN: 11.46 MIN: 13.95 MIN: 15.05 MIN: 14.98 MIN: 17.21 MIN: 20.35 MIN: 22.32 MIN: 29.42 MIN: 39.89 MIN: 39.9 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
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.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer - Model: Asian Dragon Obj 2 x Xeon Platinum 8280 EPYC 2 7R32 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 5220R Xeon Gold 6226R Xeon Silver 4216 Xeon Gold 5218 12 24 36 48 60 SE +/- 0.11, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 SE +/- 0.34, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 51.79 47.58 42.76 42.49 40.85 35.67 32.33 31.31 29.21 27.20 25.50 23.72 17.80 17.42 13.88 13.85 MIN: 50.62 / MAX: 53.17 MIN: 46.92 / MAX: 48.74 MIN: 42.06 / MAX: 43.59 MIN: 41.76 / MAX: 43.28 MIN: 40.1 / MAX: 42.54 MIN: 34.25 / MAX: 38.16 MIN: 31.97 / MAX: 32.83 MIN: 31.07 / MAX: 31.76 MIN: 28.89 / MAX: 29.61 MIN: 26.82 / MAX: 27.54 MIN: 25.3 / MAX: 25.83 MIN: 23.57 / MAX: 23.92 MIN: 17.67 / MAX: 17.93 MIN: 17.34 / MAX: 17.59 MIN: 13.82 / MAX: 13.97 MIN: 13.79 / MAX: 13.97
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer ISPC - Model: Asian Dragon Obj 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off EPYC 2 7R32 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Gold 5220R 2 x Xeon Platinum 8275CL 2 x Xeon Gold 6226R Xeon Platinum 8280 Xeon W-3275M Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 5220R Xeon Gold 6226R Xeon Gold 5218 Xeon Silver 4216 13 26 39 52 65 SE +/- 0.05, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.63, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 58.69 50.98 50.86 45.43 44.72 37.15 36.67 34.80 33.05 30.35 28.29 25.07 20.34 19.32 16.77 13.49 MIN: 56.97 / MAX: 60.91 MIN: 49.91 / MAX: 52.27 MIN: 49.88 / MAX: 52.05 MIN: 44.82 / MAX: 46.53 MIN: 43.9 / MAX: 46.32 MIN: 36.74 / MAX: 37.69 MIN: 34.56 / MAX: 39.51 MIN: 34.51 / MAX: 35.32 MIN: 32.72 / MAX: 33.4 MIN: 29.95 / MAX: 30.77 MIN: 28.06 / MAX: 28.6 MIN: 24.86 / MAX: 25.34 MIN: 20.23 / MAX: 20.53 MIN: 19.25 / MAX: 19.46 MIN: 16.69 / MAX: 16.88 MIN: 13.43 / MAX: 13.59
PyPerformance PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: django_template 2 x Xeon Platinum 8280 Xeon Platinum 8280 Xeon Gold 5220R 2 x Xeon Gold 6226R Xeon Gold 5218 2 x Xeon Gold 5220R Xeon Gold 6226R Xeon W-3275M Xeon Silver 4216 2 x Xeon Silver 4216 2 x Xeon Platinum 8259CL NUMA off Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL EPYC 2 7R32 15 30 45 60 75 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.67, N = 3 SE +/- 0.00, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 45.9 46.2 47.1 47.1 47.2 47.3 47.3 49.9 57.5 57.5 64.1 64.1 64.2 66.4
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.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 3 EPYC 2 7R32 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon W-3275M Xeon Platinum 8280 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 13 26 39 52 65 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.18, N = 3 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 19.19 19.89 20.99 21.06 23.09 23.15 27.23 27.98 30.63 30.69 34.63 35.98 44.94 46.71 55.21 58.25 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
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.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch 1D - Data Type: f32 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8280 EPYC 2 7R32 2 x Xeon Platinum 8275CL 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon W-3275M Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 1.1625 2.325 3.4875 4.65 5.8125 SE +/- 0.01953, N = 3 SE +/- 0.01483, N = 15 SE +/- 0.00571, N = 3 SE +/- 0.01437, N = 15 SE +/- 0.00673, N = 3 SE +/- 0.02693, N = 15 SE +/- 0.01296, N = 3 SE +/- 0.02205, N = 15 SE +/- 0.01072, N = 3 SE +/- 0.01245, N = 3 SE +/- 0.00893, N = 3 SE +/- 0.00575, N = 3 SE +/- 0.00644, N = 3 SE +/- 0.01148, N = 3 SE +/- 0.02145, N = 3 SE +/- 0.01398, N = 3 1.53729 1.57687 1.63599 1.63986 1.67560 1.95992 2.18975 2.23009 2.39451 2.66699 2.69977 2.86715 4.41366 4.49985 4.75696 5.16658 MIN: 1.39 MIN: 1.29 MIN: 1.41 MIN: 1.39 MIN: 1.59 MIN: 1.37 MIN: 1.86 MIN: 1.82 MIN: 2.28 MIN: 2.31 MIN: 2.46 MIN: 2.53 MIN: 3.68 MIN: 4.19 MIN: 4.33 MIN: 4.71 1. (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.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: Blowfish 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL EPYC 2 7R32 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 2 x Xeon Silver 4216 Xeon W-3275M Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 20K 40K 60K 80K 100K SE +/- 700.53, N = 3 SE +/- 78.50, N = 3 SE +/- 465.66, N = 3 SE +/- 24.01, N = 3 SE +/- 107.83, N = 3 SE +/- 203.51, N = 3 SE +/- 111.31, N = 3 SE +/- 12.50, N = 3 SE +/- 99.39, N = 3 SE +/- 91.33, N = 3 SE +/- 149.28, N = 3 SE +/- 8.37, N = 3 SE +/- 60.93, N = 3 SE +/- 77.98, N = 3 SE +/- 6.03, N = 3 SE +/- 24.29, N = 3 84084 78327 77771 70955 70888 66475 53485 51324 42864 41021 40326 35599 27126 25547 21403 20424 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
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.org FPS, More Is Better OSPray 1.8.5 Demo: NASA Streamlines - Renderer: SciVis 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL EPYC 2 7R32 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 Xeon W-3275M Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 20 40 60 80 100 SE +/- 0.00, N = 13 SE +/- 0.00, N = 12 SE +/- 0.71, N = 9 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 15 SE +/- 0.00, N = 15 SE +/- 0.00, N = 3 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 90.91 83.33 82.62 76.92 76.92 76.92 55.56 55.56 50.00 45.45 43.48 34.48 29.41 28.57 23.26 18.18 MIN: 29.41 MIN: 71.43 / MAX: 90.91 MIN: 26.32 / MAX: 90.91 MIN: 71.43 / MAX: 83.33 MIN: 27.78 / MAX: 83.33 MIN: 71.43 / MAX: 83.33 MIN: 19.23 MIN: 24.39 MIN: 43.48 MIN: 43.48 / MAX: 47.62 MIN: 37.04 MIN: 18.87 / MAX: 35.71 MIN: 26.32 MIN: 26.32 / MAX: 29.41 MIN: 22.73 / MAX: 23.81 MIN: 17.86 / MAX: 18.52
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.org MB/s, More Is Better lzbench 1.8 Test: Crush 0 - Process: Decompression Xeon W-3275M Xeon Platinum 8280 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off Xeon Gold 5218 Xeon Gold 6226R 2 x Xeon Platinum 8280 Xeon Gold 5220R 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL EPYC 2 7R32 Xeon Silver 4216 2 x Xeon Silver 4216 110 220 330 440 550 SE +/- 0.33, N = 3 509 440 434 432 430 429 428 428 419 418 404 396 394 380 353 344 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Crush 0 - Process: Compression Xeon W-3275M Xeon Platinum 8280 Xeon Gold 5220R Xeon Gold 5218 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off Xeon Gold 6226R 2 x Xeon Platinum 8275CL 2 x Xeon Gold 5220R Xeon Platinum 8259CL 2 x Xeon Gold 6226R 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off Xeon Silver 4216 EPYC 2 7R32 2 x Xeon Silver 4216 20 40 60 80 100 SE +/- 1.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 109 101 98 96 96 95 95 94 93 91 91 88 86 82 81 80 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
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.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R EPYC 2 7R32 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Silver 4216 Xeon Platinum 8280 Xeon W-3275M Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 30K 60K 90K 120K 150K SE +/- 188.25, N = 3 SE +/- 55.32, N = 3 SE +/- 135.16, N = 3 SE +/- 50.65, N = 3 SE +/- 139.53, N = 3 SE +/- 32.58, N = 3 SE +/- 91.80, N = 3 SE +/- 82.95, N = 3 SE +/- 35.10, N = 3 SE +/- 7.82, N = 3 SE +/- 30.22, N = 3 SE +/- 45.25, N = 3 SE +/- 41.33, N = 3 SE +/- 38.08, N = 3 140090.32 120961.91 108883.40 106268.33 99821.89 94642.99 85606.53 74255.67 69606.84 65522.46 58594.50 56744.87 48143.49 46723.01 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. 2 x Xeon Platinum 8280: Open MPI 4.0.3rc4 3. 2 x Xeon Platinum 8259CL: Open MPI 3.1.3 4. 2 x Xeon Gold 5220R: Open MPI 4.0.3rc4 5. 2 x Xeon Gold 6226R: Open MPI 4.0.3rc4 6. EPYC 2 7R32: Open MPI 3.1.3 7. 2 x Xeon Platinum 8259CL NUMA off: Open MPI 3.1.3 8. 2 x Xeon Silver 4216: Open MPI 4.0.3rc4 9. Xeon Platinum 8280: Open MPI 4.0.3rc4 10. Xeon W-3275M: Open MPI 3.1.3 11. Xeon Platinum 8259CL: Open MPI 3.1.3 12. Xeon Gold 6226R: Open MPI 4.0.3rc4 13. Xeon Gold 5220R: Open MPI 4.0.3rc4 14. Xeon Gold 5218: Open MPI 4.0.3rc4 15. Xeon Silver 4216: Open MPI 4.0.3rc4
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.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Water Caustic Xeon W-3275M 2 x Xeon Platinum 8280 Xeon Platinum 8280 EPYC 2 7R32 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Gold 6226R 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off Xeon Gold 5220R Xeon Platinum 8259CL Xeon Gold 5218 2 x Xeon Silver 4216 Xeon Silver 4216 7 14 21 28 35 SE +/- 0.10, N = 3 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.12, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 SE +/- 0.17, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.12, N = 3 21.55 21.59 22.02 22.32 22.71 22.76 23.19 23.34 24.09 24.54 24.78 25.01 25.36 25.96 27.39 28.90 -mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a -ljpeg -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 -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 1. (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
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.org Average Msg/sec, More Is Better Intel MPI Benchmarks 2019.3 Test: IMB-P2P PingPong 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8280 2 x Xeon Gold 6226R EPYC 2 7R32 Xeon W-3275M 2 x Xeon Gold 5220R 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Platinum 8280 Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 8M 16M 24M 32M 40M SE +/- 12198.08, N = 3 SE +/- 131246.22, N = 3 SE +/- 105849.64, N = 3 SE +/- 80057.86, N = 3 SE +/- 66348.18, N = 3 SE +/- 41319.75, N = 3 SE +/- 40509.97, N = 3 SE +/- 59477.15, N = 3 SE +/- 12631.77, N = 3 SE +/- 20273.79, N = 3 SE +/- 30074.61, N = 3 SE +/- 33688.94, N = 3 SE +/- 19484.28, N = 3 SE +/- 20987.71, N = 3 SE +/- 10529.89, N = 3 SE +/- 7036.00, N = 3 35954425.36 35888907.99 32444647.43 31988149.25 31821690.55 20467429.52 20348261.03 20246604.62 19650424.33 17176230.54 16759832.26 16653864.77 10620968.61 10276849.52 9066471.04 8923779.55 MIN: 2889 / MAX: 93907202 MIN: 2551 / MAX: 94279351 MIN: 5770 / MAX: 85492119 MIN: 9163 / MAX: 84595469 MIN: 9950 / MAX: 90956260 MIN: 7824 / MAX: 55096192 MIN: 6272 / MAX: 47546902 MIN: 5167 / MAX: 52108336 MIN: 8143 / MAX: 56362584 MIN: 7391 / MAX: 46585428 MIN: 4962 / MAX: 43240261 MIN: 5455 / MAX: 45833330 1. (CXX) g++ options: -O0 -pedantic -fopenmp -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.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer ISPC - Model: Crown 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL EPYC 2 7R32 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R Xeon Platinum 8280 Xeon W-3275M Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 5220R Xeon Gold 6226R Xeon Gold 5218 Xeon Silver 4216 12 24 36 48 60 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.49, N = 12 SE +/- 0.05, N = 3 SE +/- 0.38, N = 3 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 53.23 49.96 49.05 46.42 46.18 45.19 33.45 31.73 28.77 26.40 24.73 21.75 17.66 16.81 14.42 11.38 MIN: 51.36 / MAX: 55.83 MIN: 48.68 / MAX: 51.86 MIN: 37.93 / MAX: 51.79 MIN: 45.24 / MAX: 47.89 MIN: 42.99 / MAX: 47.93 MIN: 44.15 / MAX: 46.52 MIN: 32.87 / MAX: 34.13 MIN: 31.27 / MAX: 32.36 MIN: 28.26 / MAX: 29.24 MIN: 25.71 / MAX: 26.95 MIN: 24.4 / MAX: 25.05 MIN: 21.43 / MAX: 22.13 MIN: 17.5 / MAX: 17.85 MIN: 16.67 / MAX: 17 MIN: 14.3 / MAX: 14.63 MIN: 11.32 / MAX: 11.49
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.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Xeon W-3275M 2 x Xeon Platinum 8280 Xeon Platinum 8280 2 x Xeon Gold 5220R Xeon Gold 5218 Xeon Gold 6226R 2 x Xeon Gold 6226R Xeon Gold 5220R 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL EPYC 2 7R32 Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off Xeon Silver 4216 2 x Xeon Silver 4216 300 600 900 1200 1500 SE +/- 1.45, N = 3 SE +/- 1.00, N = 3 SE +/- 1.15, N = 3 SE +/- 1.45, N = 3 SE +/- 3.06, N = 3 SE +/- 0.67, N = 3 SE +/- 12.17, N = 3 SE +/- 0.88, N = 3 SE +/- 4.73, N = 3 SE +/- 3.18, N = 3 SE +/- 0.67, N = 3 SE +/- 1.00, N = 3 SE +/- 1.33, N = 3 SE +/- 0.58, N = 3 SE +/- 0.67, N = 3 951 1073 1076 1100 1101 1103 1104 1114 1123 1133 1226 1250 1252 1253 1342 1343
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.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer - Model: Crown EPYC 2 7R32 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 5220R Xeon Gold 6226R Xeon Silver 4216 Xeon Gold 5218 11 22 33 44 55 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 SE +/- 0.12, N = 3 SE +/- 0.17, N = 3 SE +/- 0.17, N = 3 SE +/- 0.15, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 47.65 45.61 41.79 41.39 38.12 38.10 29.52 28.96 26.28 24.55 23.27 21.38 16.05 15.99 12.43 12.39 MIN: 46.77 / MAX: 49.17 MIN: 44.2 / MAX: 47.35 MIN: 40.7 / MAX: 42.99 MIN: 40.34 / MAX: 42.73 MIN: 37.03 / MAX: 39.42 MIN: 37.24 / MAX: 39.22 MIN: 29.05 / MAX: 30.15 MIN: 28.49 / MAX: 29.56 MIN: 25.64 / MAX: 26.64 MIN: 24.09 / MAX: 24.98 MIN: 23 / MAX: 23.64 MIN: 21.05 / MAX: 21.63 MIN: 15.89 / MAX: 16.22 MIN: 15.9 / MAX: 16.17 MIN: 12.35 / MAX: 12.55 MIN: 12.32 / MAX: 12.5
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.org MB/s, More Is Better lzbench 1.8 Test: Zstd 8 - Process: Decompression Xeon W-3275M EPYC 2 7R32 Xeon Platinum 8280 Xeon Gold 5218 Xeon Gold 5220R Xeon Gold 6226R 2 x Xeon Platinum 8280 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL NUMA off Xeon Silver 4216 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Silver 4216 300 600 900 1200 1500 SE +/- 1.45, N = 3 SE +/- 0.58, N = 3 SE +/- 1.33, N = 3 SE +/- 0.33, N = 3 SE +/- 1.53, N = 3 SE +/- 1.53, N = 3 SE +/- 0.67, N = 3 SE +/- 1.53, N = 3 SE +/- 0.67, N = 3 SE +/- 1.53, N = 3 SE +/- 11.50, N = 3 SE +/- 1.86, N = 3 1298 1266 1224 1195 1194 1193 1124 1101 1100 1089 1053 1011 999 998 966 930 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Zstd 8 - Process: Compression Xeon W-3275M EPYC 2 7R32 Xeon Platinum 8280 Xeon Gold 5220R 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8280 Xeon Gold 6226R Xeon Gold 5218 2 x Xeon Gold 5220R 2 x Xeon Platinum 8275CL 2 x Xeon Gold 6226R Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL Xeon Silver 4216 2 x Xeon Silver 4216 20 40 60 80 100 84 83 77 76 75 75 74 74 74 73 72 71 71 69 64 63 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Brotli 2 - Process: Decompression Xeon W-3275M Xeon Platinum 8280 Xeon Gold 5218 Xeon Gold 6226R Xeon Gold 5220R 2 x Xeon Platinum 8280 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R 2 x Xeon Platinum 8275CL Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL NUMA off EPYC 2 7R32 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off Xeon Silver 4216 2 x Xeon Silver 4216 160 320 480 640 800 SE +/- 1.45, N = 3 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 SE +/- 0.88, N = 3 SE +/- 5.03, N = 3 SE +/- 1.33, N = 3 SE +/- 1.20, N = 3 SE +/- 1.00, N = 3 SE +/- 0.88, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 721 673 655 653 651 623 613 608 592 587 582 564 551 543 542 509 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Brotli 2 - Process: Compression Xeon W-3275M Xeon Platinum 8280 Xeon Gold 6226R Xeon Gold 5218 2 x Xeon Platinum 8280 Xeon Gold 5220R 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R 2 x Xeon Platinum 8275CL EPYC 2 7R32 Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL Xeon Silver 4216 2 x Xeon Silver 4216 40 80 120 160 200 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 0.33, N = 3 SE +/- 1.33, N = 3 SE +/- 0.58, N = 3 196 181 176 176 176 176 172 172 172 170 165 160 159 157 146 142 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Zstd 1 - Process: Decompression Xeon W-3275M Xeon Platinum 8280 Xeon Gold 5218 Xeon Gold 6226R Xeon Gold 5220R 2 x Xeon Platinum 8280 EPYC 2 7R32 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL Xeon Silver 4216 2 x Xeon Silver 4216 300 600 900 1200 1500 SE +/- 2.65, N = 3 SE +/- 0.33, N = 3 SE +/- 2.00, N = 3 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 SE +/- 1.33, N = 3 1299 1212 1184 1182 1180 1168 1148 1147 1141 1099 1090 1061 1032 1027 973 943 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Zstd 1 - Process: Compression Xeon W-3275M Xeon Platinum 8280 2 x Xeon Platinum 8280 Xeon Gold 5218 Xeon Gold 6226R Xeon Gold 5220R 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R EPYC 2 7R32 Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL Xeon Silver 4216 2 x Xeon Silver 4216 110 220 330 440 550 SE +/- 1.00, N = 3 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 2.33, N = 3 SE +/- 2.33, N = 3 508 457 449 446 445 444 443 439 437 437 418 410 407 399 365 359 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
Mlpack Benchmark Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_svm EPYC 2 7R32 Xeon W-3275M 2 x Xeon Platinum 8275CL Xeon Platinum 8280 2 x Xeon Platinum 8280 2 x Xeon Gold 6226R Xeon Gold 5220R 2 x Xeon Gold 5220R Xeon Gold 6226R Xeon Gold 5218 2 x Xeon Platinum 8275CL NUMA off Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off Xeon Silver 4216 2 x Xeon Silver 4216 5 10 15 20 25 SE +/- 0.09, N = 3 SE +/- 0.19, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 SE +/- 0.13, N = 3 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 15.16 15.78 16.87 17.19 17.19 17.77 17.82 17.92 17.92 17.98 18.42 18.67 18.76 19.62 20.89 21.09
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.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 2 x Xeon Platinum 8280 EPYC 2 7R32 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 2 x Xeon Silver 4216 Xeon W-3275M Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 1600 3200 4800 6400 8000 SE +/- 5.70, N = 3 SE +/- 3.22, N = 3 SE +/- 2.13, N = 3 SE +/- 0.43, N = 3 SE +/- 3.00, N = 3 SE +/- 22.00, N = 3 SE +/- 2.41, N = 3 SE +/- 3.26, N = 3 SE +/- 2.14, N = 3 SE +/- 2.28, N = 3 SE +/- 48.27, N = 3 SE +/- 0.90, N = 3 SE +/- 5.07, N = 3 SE +/- 5.71, N = 3 SE +/- 2.58, N = 3 SE +/- 0.67, N = 3 1893.72 1899.24 2057.93 2059.03 2238.05 2252.67 2987.08 3112.36 3716.98 3849.13 3852.37 4426.06 5864.26 6072.57 7189.03 7457.86 MIN: 1871.79 MIN: 1888.24 MIN: 2050.62 MIN: 2054.86 MIN: 2230.65 MIN: 2229.49 MIN: 2977.12 MIN: 3107.3 MIN: 3705.72 MIN: 3842.7 MIN: 3728.62 MIN: 4423.17 MIN: 5830.88 MIN: 6048.56 MIN: 7180.23 MIN: 7454.84 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
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.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer - Model: Asian Dragon 2 x Xeon Platinum 8280 EPYC 2 7R32 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 5220R Xeon Gold 6226R Xeon Gold 5218 Xeon Silver 4216 13 26 39 52 65 SE +/- 0.16, N = 3 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 SE +/- 0.38, N = 3 SE +/- 0.19, N = 3 SE +/- 0.32, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 57.49 52.95 46.91 46.79 45.77 40.08 35.88 34.69 32.25 30.11 28.20 26.06 19.61 19.35 15.31 15.28 MIN: 55.98 / MAX: 58.87 MIN: 52.3 / MAX: 53.84 MIN: 46.17 / MAX: 47.87 MIN: 44.43 / MAX: 47.97 MIN: 44.89 / MAX: 47.26 MIN: 37.64 / MAX: 43.58 MIN: 35.51 / MAX: 36.33 MIN: 34.44 / MAX: 35.19 MIN: 32 / MAX: 32.54 MIN: 29.8 / MAX: 30.54 MIN: 27.97 / MAX: 28.53 MIN: 25.85 / MAX: 26.28 MIN: 19.5 / MAX: 19.79 MIN: 19.28 / MAX: 19.48 MIN: 15.25 / MAX: 15.4 MIN: 15.18 / MAX: 15.39
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.org Frames Per Second, More Is Better SVT-AV1 0.8 Encoder Mode: Enc Mode 4 - Input: 1080p 2 x Xeon Platinum 8280 Xeon W-3275M Xeon Platinum 8280 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL NUMA off EPYC 2 7R32 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R 2 x Xeon Platinum 8275CL Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R 2 x Xeon Silver 4216 Xeon Gold 5218 Xeon Silver 4216 2 4 6 8 10 SE +/- 0.064, N = 3 SE +/- 0.023, N = 3 SE +/- 0.032, N = 3 SE +/- 0.075, N = 4 SE +/- 0.002, N = 3 SE +/- 0.046, N = 3 SE +/- 0.072, N = 5 SE +/- 0.009, N = 3 SE +/- 0.019, N = 3 SE +/- 0.041, N = 3 SE +/- 0.052, N = 3 SE +/- 0.018, N = 3 SE +/- 0.014, N = 3 SE +/- 0.010, N = 3 SE +/- 0.003, N = 3 SE +/- 0.021, N = 3 7.033 6.389 6.030 5.996 5.955 5.942 5.714 5.431 5.302 5.243 5.112 4.340 4.285 4.216 3.339 3.309 1. (CXX) g++ options: -fPIE -fPIC -pie
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.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_alexnet - Data Type: bf16bf16bf16 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 6226R Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Gold 5220R Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 400 800 1200 1600 2000 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 SE +/- 0.33, N = 3 SE +/- 0.23, N = 3 SE +/- 0.11, N = 3 SE +/- 4.23, N = 3 SE +/- 0.07, N = 3 SE +/- 1.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.41, N = 3 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 SE +/- 1.48, N = 3 SE +/- 0.15, N = 3 SE +/- 0.03, N = 3 320.06 348.24 348.33 399.30 399.31 527.02 637.37 702.07 712.20 796.75 938.91 1042.34 1433.47 1874.47 1875.23 MIN: 319.23 MIN: 346.92 MIN: 347.28 MIN: 398.05 MIN: 398.47 MIN: 521.14 MIN: 636.97 MIN: 687.86 MIN: 710.93 MIN: 795.52 MIN: 937.57 MIN: 1041.43 MIN: 1421.77 MIN: 1873.87 MIN: 1873.9 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 6226R Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8280 Xeon Platinum 8259CL Xeon W-3275M Xeon Gold 6226R 2 x Xeon Gold 5220R 2 x Xeon Silver 4216 Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 EPYC 2 7R32 200 400 600 800 1000 SE +/- 0.001652, N = 3 SE +/- 0.001152, N = 3 SE +/- 0.001016, N = 3 SE +/- 0.001915, N = 3 SE +/- 0.000361, N = 3 SE +/- 0.000864, N = 3 SE +/- 0.006813, N = 3 SE +/- 0.000985, N = 3 SE +/- 0.001267, N = 3 SE +/- 0.000358, N = 3 SE +/- 0.002792, N = 3 SE +/- 0.003675, N = 3 SE +/- 0.001194, N = 3 SE +/- 0.001460, N = 3 SE +/- 0.001246, N = 3 SE +/- 4.136428, N = 3 0.354714 0.355362 0.361414 0.369060 0.371036 0.376222 0.394455 0.415614 0.458422 0.528632 0.560890 0.770300 0.843709 0.976730 1.273750 1131.130000 MIN: 1118.79 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_1d - Data Type: bf16bf16bf16 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R Xeon Platinum 8280 2 x Xeon Gold 5220R Xeon W-3275M Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 4 8 12 16 20 SE +/- 0.00401, N = 3 SE +/- 0.01030, N = 3 SE +/- 0.00661, N = 3 SE +/- 0.00151, N = 3 SE +/- 0.00489, N = 3 SE +/- 0.00747, N = 3 SE +/- 0.00167, N = 3 SE +/- 0.00772, N = 3 SE +/- 0.03740, N = 3 SE +/- 0.02376, N = 3 SE +/- 0.01001, N = 3 SE +/- 0.00392, N = 3 SE +/- 0.04579, N = 3 SE +/- 0.00105, N = 3 SE +/- 0.00867, N = 3 3.96510 3.96906 4.06847 4.46523 4.49039 5.38402 6.55374 7.22975 7.61595 7.98292 8.86913 9.90362 13.14280 16.54840 16.55160 MIN: 3.88 MIN: 3.86 MIN: 3.93 MIN: 4.38 MIN: 4.4 MIN: 5.3 MIN: 6.5 MIN: 7.13 MIN: 6.95 MIN: 7.92 MIN: 8.78 MIN: 9.85 MIN: 12.96 MIN: 16.51 MIN: 16.51 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
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.org Seconds, Fewer Is Better Zstd Compression 1.3.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Platinum 8280 EPYC 2 7R32 Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8259CL NUMA off Xeon Gold 6226R Xeon Gold 5220R 2 x Xeon Gold 5220R 2 x Xeon Platinum 8275CL 2 x Xeon Silver 4216 Xeon Gold 5218 Xeon Silver 4216 3 6 9 12 15 SE +/- 0.016, N = 3 SE +/- 0.023, N = 3 SE +/- 0.148, N = 3 SE +/- 0.062, N = 15 SE +/- 0.128, N = 3 SE +/- 0.094, N = 15 SE +/- 0.096, N = 3 SE +/- 0.138, N = 5 SE +/- 0.128, N = 5 SE +/- 0.056, N = 3 SE +/- 0.021, N = 3 SE +/- 0.117, N = 3 SE +/- 0.114, N = 15 SE +/- 0.104, N = 15 SE +/- 0.029, N = 3 SE +/- 0.075, N = 3 8.203 8.380 9.137 9.230 9.672 9.949 10.206 10.289 10.294 10.330 10.355 10.449 10.945 10.978 11.122 11.430 -llzma 1. (CC) gcc options: -O3 -pthread -lz
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.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_1d - Data Type: f32 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL Xeon Platinum 8280 2 x Xeon Gold 6226R Xeon Platinum 8259CL Xeon W-3275M 2 x Xeon Gold 5220R EPYC 2 7R32 Xeon Gold 6226R 2 x Xeon Silver 4216 Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 1.1949 2.3898 3.5847 4.7796 5.9745 SE +/- 0.00066, N = 3 SE +/- 0.00318, N = 3 SE +/- 0.00024, N = 3 SE +/- 0.00693, N = 3 SE +/- 0.00979, N = 3 SE +/- 0.00157, N = 3 SE +/- 0.00475, N = 3 SE +/- 0.00097, N = 3 SE +/- 0.01273, N = 3 SE +/- 0.00174, N = 3 SE +/- 0.01972, N = 3 SE +/- 0.00272, N = 3 SE +/- 0.00576, N = 3 SE +/- 0.00527, N = 3 SE +/- 0.00570, N = 3 SE +/- 0.01140, N = 3 1.22589 1.24029 1.25116 1.25795 1.33109 1.46232 1.49724 1.63928 1.74515 2.12680 2.22540 2.23126 3.06590 3.36432 3.99488 5.31087 MIN: 1.18 MIN: 1.17 MIN: 1.19 MIN: 1.2 MIN: 1.26 MIN: 1.44 MIN: 1.43 MIN: 1.61 MIN: 1.55 MIN: 2.06 MIN: 2.11 MIN: 2.17 MIN: 2.99 MIN: 3.3 MIN: 3.95 MIN: 5.16 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
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.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer ISPC - Model: Asian Dragon 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off EPYC 2 7R32 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R 2 x Xeon Platinum 8275CL Xeon Platinum 8280 Xeon W-3275M Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 5220R Xeon Gold 6226R Xeon Gold 5218 Xeon Silver 4216 15 30 45 60 75 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.53, N = 4 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 68.42 59.06 59.05 52.35 51.87 43.10 40.43 38.77 38.31 35.15 32.91 28.97 23.60 22.46 19.43 15.59 MIN: 66.22 / MAX: 70.39 MIN: 57.51 / MAX: 60.42 MIN: 57.78 / MAX: 60.29 MIN: 51.67 / MAX: 53.48 MIN: 50.96 / MAX: 54.15 MIN: 42.68 / MAX: 43.7 MIN: 40.04 / MAX: 41.18 MIN: 35.85 / MAX: 45.98 MIN: 37.87 / MAX: 38.72 MIN: 33.95 / MAX: 35.72 MIN: 32.68 / MAX: 33.18 MIN: 28.72 / MAX: 29.29 MIN: 23.45 / MAX: 23.8 MIN: 22.38 / MAX: 22.62 MIN: 19.37 / MAX: 19.6 MIN: 15.54 / MAX: 15.7
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.org FPS, More Is Better dav1d 0.6.0 Video Input: Summer Nature 4K EPYC 2 7R32 Xeon W-3275M 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off Xeon Platinum 8259CL 2 x Xeon Gold 6226R Xeon Platinum 8280 2 x Xeon Gold 5220R Xeon Gold 6226R Xeon Gold 5220R 2 x Xeon Silver 4216 Xeon Gold 5218 Xeon Silver 4216 70 140 210 280 350 SE +/- 0.98, N = 3 SE +/- 1.20, N = 3 SE +/- 3.68, N = 3 SE +/- 1.14, N = 3 SE +/- 0.62, N = 3 SE +/- 1.73, N = 3 SE +/- 1.78, N = 3 SE +/- 1.31, N = 3 SE +/- 1.66, N = 3 SE +/- 1.15, N = 3 SE +/- 0.84, N = 3 SE +/- 1.20, N = 3 SE +/- 0.78, N = 3 SE +/- 1.81, N = 3 SE +/- 0.30, N = 3 SE +/- 0.15, N = 3 321.17 256.60 221.31 218.14 216.86 215.64 212.99 205.63 203.10 199.08 177.89 170.07 160.59 159.60 136.86 132.46 MIN: 150.11 / MAX: 347.95 MIN: 164.1 / MAX: 284.35 MIN: 81.4 / MAX: 247.6 MIN: 105.24 / MAX: 238.99 MIN: 97.39 / MAX: 239.16 MIN: 93.88 / MAX: 236.99 MIN: 89.5 / MAX: 233.99 MIN: 134.32 / MAX: 229.88 MIN: 119.16 / MAX: 222.17 MIN: 121.12 / MAX: 214.69 MIN: 103.41 / MAX: 190.93 MIN: 115.59 / MAX: 193.75 MIN: 110.85 / MAX: 181 MIN: 100.88 / MAX: 178.21 MIN: 107.86 / MAX: 153.94 MIN: 104.21 / MAX: 150.6 1. (CC) gcc options: -pthread
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.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_alexnet - Data Type: u8s8f32 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off Xeon Platinum 8259CL Xeon W-3275M 2 x Xeon Gold 5220R Xeon Gold 6226R 2 x Xeon Silver 4216 2 x Xeon Platinum 8275CL Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 EPYC 2 7R32 300 600 900 1200 1500 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.24, N = 3 SE +/- 0.25, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.14, N = 3 SE +/- 0.73, N = 3 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 2.69, N = 3 19.37 19.81 22.38 26.54 26.84 30.64 30.88 31.99 35.98 42.22 55.34 59.90 66.74 81.07 105.83 1301.36 MIN: 1286.29 1. (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.org GFLOPS, More Is Better ArrayFire 3.7 Test: BLAS CPU 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R Xeon Platinum 8280 2 x Xeon Platinum 8280 Xeon W-3275M Xeon Platinum 8259CL 2 x Xeon Gold 5220R Xeon Gold 6226R 2 x Xeon Silver 4216 Xeon Gold 5220R Xeon Gold 5218 EPYC 2 7R32 Xeon Silver 4216 1400 2800 4200 5600 7000 SE +/- 4.90, N = 3 SE +/- 61.47, N = 3 SE +/- 14.66, N = 3 SE +/- 122.72, N = 12 SE +/- 31.78, N = 3 SE +/- 25.11, N = 3 SE +/- 20.06, N = 3 SE +/- 30.40, N = 3 SE +/- 1.09, N = 3 SE +/- 3.91, N = 3 SE +/- 4.16, N = 3 SE +/- 0.79, N = 3 SE +/- 0.37, N = 3 SE +/- 0.62, N = 3 SE +/- 6.50, N = 3 SE +/- 1.52, N = 3 6325.07 6259.01 5650.71 5319.58 3912.30 3432.16 3430.28 3128.39 2950.16 2359.13 2137.03 1497.75 1201.54 1002.09 990.80 765.49 1. (CXX) g++ options: -rdynamic
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.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Xeon W-3275M 2 x Xeon Platinum 8280 Xeon Platinum 8280 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Gold 6226R Xeon Gold 5218 Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Gold 5220R 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Silver 4216 EPYC 2 7R32 160K 320K 480K 640K 800K SE +/- 1014.34, N = 3 SE +/- 884.68, N = 3 SE +/- 425.09, N = 3 SE +/- 144.16, N = 3 SE +/- 312.21, N = 3 SE +/- 164.78, N = 3 SE +/- 786.96, N = 3 SE +/- 752.01, N = 3 SE +/- 914.97, N = 3 SE +/- 862.18, N = 3 SE +/- 377.70, N = 3 SE +/- 961.65, N = 3 SE +/- 778.31, N = 3 SE +/- 200.00, N = 3 SE +/- 1865.15, N = 3 SE +/- 1283.26, N = 3 734339 649693 649164 640173 639026 632601 632455 632431 631283 629690 574348 573483 569793 519964 515697 500524
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.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_alexnet - Data Type: f32 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Gold 6226R Xeon Platinum 8280 EPYC 2 7R32 Xeon Platinum 8259CL Xeon W-3275M 2 x Xeon Gold 5220R Xeon Gold 6226R 2 x Xeon Silver 4216 Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 90 180 270 360 450 SE +/- 0.08, N = 3 SE +/- 0.20, N = 3 SE +/- 0.23, N = 3 SE +/- 0.79, N = 3 SE +/- 0.88, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 1.13, N = 3 SE +/- 0.12, N = 3 SE +/- 0.11, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.16, N = 3 SE +/- 0.11, N = 3 SE +/- 0.95, N = 3 49.84 55.36 56.65 57.51 79.11 81.14 94.19 96.69 107.80 108.57 122.76 155.37 197.91 244.75 298.30 395.44 MIN: 74.84 MIN: 79.72 MIN: 93.73 MIN: 93.63 MIN: 106.14 MIN: 102.46 MIN: 121.68 MIN: 154.79 MIN: 195.97 MIN: 242.31 MIN: 297.84 MIN: 390.56 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
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.org ms, Fewer Is Better Renaissance 0.10.0 Test: Scala Dotty EPYC 2 7R32 Xeon Platinum 8280 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8280 Xeon W-3275M Xeon Gold 6226R 2 x Xeon Platinum 8275CL NUMA off Xeon Platinum 8259CL 2 x Xeon Gold 6226R 2 x Xeon Platinum 8259CL 2 x Xeon Gold 5220R Xeon Gold 5220R 2 x Xeon Platinum 8259CL NUMA off Xeon Gold 5218 2 x Xeon Silver 4216 Xeon Silver 4216 2K 4K 6K 8K 10K SE +/- 29.54, N = 5 SE +/- 19.31, N = 5 SE +/- 21.19, N = 5 SE +/- 56.89, N = 13 SE +/- 31.93, N = 5 SE +/- 46.73, N = 5 SE +/- 19.51, N = 5 SE +/- 35.89, N = 5 SE +/- 78.90, N = 5 SE +/- 20.56, N = 5 SE +/- 62.31, N = 5 SE +/- 50.08, N = 5 SE +/- 54.97, N = 5 SE +/- 41.65, N = 5 SE +/- 82.66, N = 9 SE +/- 17.62, N = 5 6577.34 6664.25 6733.16 6890.61 6970.90 6999.50 7042.35 7200.75 7231.01 7256.92 7414.62 7556.33 7566.34 8286.12 8583.01 8634.69
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.org FPS, More Is Better OSPray 1.8.5 Demo: Magnetic Reconnection - Renderer: SciVis 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R Xeon Platinum 8280 EPYC 2 7R32 Xeon W-3275M Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 5220R Xeon Gold 6226R Xeon Gold 5218 Xeon Silver 4216 16 32 48 64 80 SE +/- 0.00, N = 12 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 12 SE +/- 0.88, N = 3 SE +/- 0.00, N = 12 SE +/- 0.00, N = 3 SE +/- 0.60, N = 3 SE +/- 0.00, N = 12 SE +/- 0.27, N = 4 SE +/- 0.00, N = 12 SE +/- 0.16, N = 4 SE +/- 0.00, N = 15 SE +/- 0.08, N = 4 71.43 62.50 62.50 58.82 50.88 47.62 45.45 42.87 40.00 40.00 37.04 32.53 27.03 25.48 22.22 17.94 MIN: 15.87 / MAX: 76.92 MIN: 58.82 / MAX: 66.67 MIN: 18.52 / MAX: 66.67 MIN: 52.63 MIN: 16.95 / MAX: 55.56 MIN: 16.67 / MAX: 50 MIN: 20 MIN: 38.46 / MAX: 43.48 MIN: 38.46 / MAX: 41.67 MIN: 37.04 MIN: 33.33 MIN: 14.93 / MAX: 33.33 MIN: 24.39 MIN: 24.39 / MAX: 25.64 MIN: 21.28 MIN: 16.95 / MAX: 18.18
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.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch 1D - Data Type: bf16bf16bf16 2 x Xeon Gold 6226R 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 3 6 9 12 15 SE +/- 0.00482, N = 3 SE +/- 0.01183, N = 3 SE +/- 0.00386, N = 3 SE +/- 0.00988, N = 3 SE +/- 0.00913, N = 3 SE +/- 0.00431, N = 3 SE +/- 0.00377, N = 3 SE +/- 0.02664, N = 3 SE +/- 0.01534, N = 3 SE +/- 0.00262, N = 3 SE +/- 0.00265, N = 3 SE +/- 0.02081, N = 3 SE +/- 0.02077, N = 3 SE +/- 0.00212, N = 3 SE +/- 0.02765, N = 3 3.21281 3.65964 4.06041 4.10369 4.46440 4.48918 4.83170 5.56304 5.56500 5.69900 5.71439 5.72791 8.68590 8.82710 10.90140 MIN: 2.99 MIN: 3.47 MIN: 3.85 MIN: 3.91 MIN: 4.28 MIN: 4.31 MIN: 4.76 MIN: 5.04 MIN: 5.18 MIN: 5.57 MIN: 5.6 MIN: 5.56 MIN: 8.38 MIN: 8.65 MIN: 10.12 1. (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.org FPS, More Is Better dav1d 0.6.0 Video Input: Summer Nature 1080p EPYC 2 7R32 Xeon W-3275M 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 6226R Xeon Platinum 8259CL Xeon Platinum 8280 2 x Xeon Gold 5220R Xeon Gold 6226R Xeon Gold 5220R 2 x Xeon Silver 4216 Xeon Gold 5218 Xeon Silver 4216 150 300 450 600 750 SE +/- 2.19, N = 3 SE +/- 2.32, N = 3 SE +/- 3.67, N = 3 SE +/- 4.96, N = 3 SE +/- 3.74, N = 15 SE +/- 3.42, N = 3 SE +/- 3.77, N = 15 SE +/- 1.84, N = 3 SE +/- 1.73, N = 3 SE +/- 0.52, N = 3 SE +/- 3.79, N = 6 SE +/- 0.97, N = 3 SE +/- 2.31, N = 3 SE +/- 4.57, N = 3 SE +/- 1.26, N = 3 SE +/- 1.97, N = 3 676.16 537.84 431.76 422.89 409.88 406.66 400.24 358.62 353.78 323.20 321.84 307.75 274.98 272.55 265.46 232.35 MIN: 302.17 / MAX: 751.14 MIN: 317.28 / MAX: 605.87 MIN: 205.51 / MAX: 479.42 MIN: 175.85 / MAX: 474 MIN: 126.27 / MAX: 481.12 MIN: 144.68 / MAX: 463.23 MIN: 106.81 / MAX: 466.09 MIN: 196.53 / MAX: 395.24 MIN: 207.11 / MAX: 387.94 MIN: 200.79 / MAX: 358.32 MIN: 175.96 / MAX: 365.43 MIN: 179.63 / MAX: 337.24 MIN: 160.24 / MAX: 299.46 MIN: 156.69 / MAX: 307.87 MIN: 166.24 / MAX: 288.23 MIN: 133.23 / MAX: 255.75 1. (CC) gcc options: -pthread
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.org ms, Fewer Is Better ArrayFire 3.7 Test: Conjugate Gradient CPU Xeon Platinum 8280 Xeon W-3275M Xeon Platinum 8259CL Xeon Gold 5220R Xeon Gold 6226R Xeon Gold 5218 2 x Xeon Gold 6226R 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL NUMA off Xeon Silver 4216 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Gold 5220R 2 x Xeon Platinum 8275CL 2 x Xeon Silver 4216 EPYC 2 7R32 8 16 24 32 40 SE +/- 0.067, N = 3 SE +/- 0.075, N = 15 SE +/- 0.022, N = 3 SE +/- 0.094, N = 3 SE +/- 0.026, N = 3 SE +/- 0.069, N = 9 SE +/- 0.072, N = 15 SE +/- 0.086, N = 6 SE +/- 0.243, N = 15 SE +/- 0.047, N = 3 SE +/- 0.091, N = 15 SE +/- 0.272, N = 15 SE +/- 0.099, N = 15 SE +/- 0.220, N = 3 SE +/- 0.372, N = 15 SE +/- 0.217, N = 3 4.115 4.423 4.677 6.409 6.451 7.042 7.155 7.481 7.604 7.819 8.430 9.654 9.898 13.220 16.920 35.130 1. (CXX) g++ options: -rdynamic
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.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Hair EPYC 2 7R32 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 6 12 18 24 30 SE +/- 0.05445, N = 3 SE +/- 0.11249, N = 3 SE +/- 0.03939, N = 3 SE +/- 0.03608, N = 3 SE +/- 0.05235, N = 3 SE +/- 0.05659, N = 3 SE +/- 0.05690, N = 3 SE +/- 0.03810, N = 3 SE +/- 0.03914, N = 3 SE +/- 0.05256, N = 3 SE +/- 0.06619, N = 3 SE +/- 0.03318, N = 3 SE +/- 0.06005, N = 3 SE +/- 0.03525, N = 3 SE +/- 0.02235, N = 3 SE +/- 0.12220, N = 3 7.67455 7.82706 8.19337 8.29067 9.09073 9.26217 10.66530 11.07260 12.68630 12.71040 13.60310 14.80460 18.61290 18.98400 22.48660 23.61290 -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 -mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a -mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a -ljpeg -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 1. (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
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.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL EPYC 2 7R32 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R 2 x Xeon Silver 4216 2 x Xeon Platinum 8259CL NUMA off Xeon Platinum 8280 Xeon W-3275M Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 15K 30K 45K 60K 75K SE +/- 115.61, N = 3 SE +/- 77.17, N = 3 SE +/- 520.84, N = 15 SE +/- 31.12, N = 3 SE +/- 190.70, N = 3 SE +/- 157.62, N = 3 SE +/- 42.29, N = 3 SE +/- 151.80, N = 3 SE +/- 146.25, N = 3 SE +/- 28.87, N = 3 SE +/- 23.98, N = 3 SE +/- 54.67, N = 3 SE +/- 13.76, N = 3 SE +/- 57.24, N = 3 70893.41 53978.90 51225.18 50932.88 49232.24 42220.94 38493.57 32682.14 31426.53 24288.34 23859.79 23346.56 22329.34 21149.68 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. 2 x Xeon Platinum 8280: Open MPI 4.0.3rc4 3. 2 x Xeon Platinum 8259CL: Open MPI 3.1.3 4. EPYC 2 7R32: Open MPI 3.1.3 5. 2 x Xeon Gold 5220R: Open MPI 4.0.3rc4 6. 2 x Xeon Gold 6226R: Open MPI 4.0.3rc4 7. 2 x Xeon Silver 4216: Open MPI 4.0.3rc4 8. 2 x Xeon Platinum 8259CL NUMA off: Open MPI 3.1.3 9. Xeon Platinum 8280: Open MPI 4.0.3rc4 10. Xeon W-3275M: Open MPI 3.1.3 11. Xeon Platinum 8259CL: Open MPI 3.1.3 12. Xeon Gold 6226R: Open MPI 4.0.3rc4 13. Xeon Gold 5220R: Open MPI 4.0.3rc4 14. Xeon Gold 5218: Open MPI 4.0.3rc4 15. Xeon Silver 4216: Open MPI 4.0.3rc4
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.org Frames Per Second, More Is Better SVT-AV1 0.8 Encoder Mode: Enc Mode 8 - Input: 1080p 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL EPYC 2 7R32 Xeon W-3275M 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off Xeon Platinum 8280 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 13 26 39 52 65 SE +/- 0.67, N = 3 SE +/- 0.48, N = 3 SE +/- 0.17, N = 3 SE +/- 0.77, N = 3 SE +/- 0.46, N = 3 SE +/- 0.13, N = 3 SE +/- 0.29, N = 3 SE +/- 0.07, N = 3 SE +/- 0.25, N = 3 SE +/- 0.18, N = 3 SE +/- 0.35, N = 3 SE +/- 0.11, N = 3 SE +/- 0.09, N = 3 SE +/- 0.13, N = 3 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 56.98 56.12 55.37 54.47 53.82 53.04 52.31 51.92 51.71 49.21 46.87 40.55 34.64 33.09 27.19 26.46 1. (CXX) g++ options: -fPIE -fPIC -pie
SMHasher SMHasher is a hash function tester. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/sec, More Is Better SMHasher 2020-02-29 Hash: wyhash Xeon W-3275M 2 x Xeon Silver 4216 Xeon Silver 4216 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL Xeon Platinum 8259CL Xeon Gold 6226R 2 x Xeon Gold 6226R 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 6K 12K 18K 24K 30K SE +/- 105.54, N = 3 SE +/- 4.76, N = 3 SE +/- 0.31, N = 3 SE +/- 0.70, N = 3 SE +/- 6.86, N = 3 SE +/- 8.73, N = 3 SE +/- 5.65, N = 3 SE +/- 4.48, N = 3 SE +/- 4.81, N = 3 SE +/- 4.38, N = 3 26298.77 22011.20 22004.08 20231.58 20225.18 20221.25 19429.87 19424.11 18775.94 18770.15 1. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.org cycles/hash, Fewer Is Better SMHasher 2020-02-29 Hash: wyhash Xeon W-3275M 2 x Xeon Gold 5220R Xeon Gold 5220R Xeon Gold 5218 2 x Xeon Silver 4216 Xeon Silver 4216 2 x Xeon Platinum 8280 Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off Xeon Platinum 8259CL 2 x Xeon Gold 6226R Xeon Gold 6226R 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 18.51 18.81 18.82 19.81 22.13 22.13 22.68 22.68 24.15 24.15 24.19 25.13 25.13 26.09 26.13 1. (CXX) g++ options: -march=native -O3 -lpthread
Scikit-Learn Scikit-learn is a Python module for machine learning Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 0.22.1 Xeon Platinum 8280 2 x Xeon Platinum 8280 Xeon W-3275M Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 EPYC 2 7R32 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8275CL NUMA off Xeon Silver 4216 Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL 2 x Xeon Silver 4216 2 x Xeon Platinum 8259CL NUMA off 3 6 9 12 15 SE +/- 0.042, N = 3 SE +/- 0.122, N = 3 SE +/- 0.035, N = 3 SE +/- 0.029, N = 3 SE +/- 0.034, N = 3 SE +/- 0.041, N = 3 SE +/- 0.037, N = 3 SE +/- 0.055, N = 3 SE +/- 0.024, N = 3 SE +/- 0.052, N = 3 SE +/- 0.032, N = 3 SE +/- 0.028, N = 3 SE +/- 0.056, N = 3 SE +/- 0.039, N = 3 SE +/- 0.035, N = 3 SE +/- 0.043, N = 3 9.127 9.392 9.661 9.924 10.112 10.286 10.419 10.449 10.458 11.065 11.490 12.030 12.088 12.459 12.549 12.954
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.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Jython Xeon W-3275M Xeon Platinum 8280 Xeon Gold 6226R 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Gold 6226R Xeon Gold 5220R 2 x Xeon Gold 5220R Xeon Platinum 8259CL Xeon Gold 5218 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL EPYC 2 7R32 Xeon Silver 4216 2 x Xeon Silver 4216 1200 2400 3600 4800 6000 SE +/- 10.08, N = 4 SE +/- 15.39, N = 4 SE +/- 11.58, N = 4 SE +/- 21.20, N = 4 SE +/- 19.30, N = 4 SE +/- 14.64, N = 4 SE +/- 35.02, N = 4 SE +/- 23.48, N = 4 SE +/- 22.03, N = 4 SE +/- 26.49, N = 4 SE +/- 11.32, N = 4 SE +/- 56.00, N = 4 SE +/- 10.59, N = 4 SE +/- 10.79, N = 4 SE +/- 36.99, N = 4 4321 4547 4609 4685 4711 4759 4806 4834 4877 5012 5096 5161 5172 5246 5768 5802
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.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p EPYC 2 7R32 Xeon W-3275M Xeon Platinum 8280 2 x Xeon Gold 6226R Xeon Platinum 8259CL 2 x Xeon Gold 5220R 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8275CL NUMA off Xeon Gold 5220R Xeon Gold 6226R 2 x Xeon Silver 4216 2 x Xeon Platinum 8275CL Xeon Silver 4216 Xeon Gold 5218 60 120 180 240 300 SE +/- 2.49, N = 3 SE +/- 0.97, N = 3 SE +/- 3.65, N = 4 SE +/- 3.77, N = 4 SE +/- 1.36, N = 3 SE +/- 2.14, N = 3 SE +/- 2.89, N = 4 SE +/- 8.04, N = 12 SE +/- 8.15, N = 12 SE +/- 8.25, N = 12 SE +/- 1.23, N = 3 SE +/- 3.10, N = 3 SE +/- 1.51, N = 3 SE +/- 5.20, N = 12 SE +/- 2.39, N = 3 SE +/- 1.79, N = 3 291.17 282.18 265.40 256.91 256.24 237.57 233.17 229.91 229.53 228.38 224.01 221.95 206.42 191.66 173.18 172.82 1. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -lm
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.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R 2 x Xeon Silver 4216 EPYC 2 7R32 2 x Xeon Platinum 8259CL NUMA off Xeon Platinum 8280 Xeon W-3275M Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 15K 30K 45K 60K 75K SE +/- 860.82, N = 5 SE +/- 304.73, N = 3 SE +/- 464.43, N = 3 SE +/- 193.70, N = 3 SE +/- 151.51, N = 3 SE +/- 796.48, N = 3 SE +/- 420.94, N = 3 SE +/- 129.93, N = 3 SE +/- 40.04, N = 3 SE +/- 114.90, N = 3 SE +/- 27.89, N = 3 SE +/- 114.95, N = 3 SE +/- 36.97, N = 3 SE +/- 69.19, N = 3 69175.12 63393.35 58984.18 58681.42 52832.47 49330.15 43490.15 37089.05 35376.11 33490.03 31633.60 31197.22 30328.65 28301.13 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. 2 x Xeon Platinum 8280: Open MPI 4.0.3rc4 3. 2 x Xeon Platinum 8259CL: Open MPI 3.1.3 4. 2 x Xeon Gold 5220R: Open MPI 4.0.3rc4 5. 2 x Xeon Gold 6226R: Open MPI 4.0.3rc4 6. 2 x Xeon Silver 4216: Open MPI 4.0.3rc4 7. EPYC 2 7R32: Open MPI 3.1.3 8. 2 x Xeon Platinum 8259CL NUMA off: Open MPI 3.1.3 9. Xeon Platinum 8280: Open MPI 4.0.3rc4 10. Xeon W-3275M: Open MPI 3.1.3 11. Xeon Platinum 8259CL: Open MPI 3.1.3 12. Xeon Gold 6226R: Open MPI 4.0.3rc4 13. Xeon Gold 5220R: Open MPI 4.0.3rc4 14. Xeon Gold 5218: Open MPI 4.0.3rc4 15. Xeon Silver 4216: Open MPI 4.0.3rc4
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.org Images / Sec, More Is Better Intel Open Image Denoise 1.0.0 Scene: Memorial 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Gold 6226R Xeon Platinum 8280 EPYC 2 7R32 Xeon Platinum 8259CL 2 x Xeon Gold 5220R Xeon W-3275M Xeon Gold 6226R 2 x Xeon Silver 4216 2 x Xeon Platinum 8275CL NUMA off Xeon Gold 5220R Xeon Gold 5218 2 x Xeon Platinum 8275CL Xeon Silver 4216 8 16 24 32 40 SE +/- 0.17, N = 3 SE +/- 0.12, N = 3 SE +/- 0.21, N = 3 SE +/- 0.36, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.30, N = 3 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.13, N = 3 SE +/- 0.02, N = 3 34.49 33.89 33.10 33.06 31.10 28.71 27.99 27.97 27.35 22.01 20.43 19.55 18.41 15.80 15.06 12.85
Nettle GNU Nettle is a low-level cryptographic library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mbyte/s, More Is Better Nettle 3.5.1 Test: aes256 Xeon W-3275M 2 x Xeon Platinum 8280 Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL Xeon Gold 5218 Xeon Gold 6226R 2 x Xeon Gold 5220R 2 x Xeon Gold 6226R Xeon Gold 5220R 2 x Xeon Platinum 8259CL NUMA off Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Silver 4216 EPYC 2 7R32 1500 3000 4500 6000 7500 SE +/- 39.45, N = 3 SE +/- 3.29, N = 3 SE +/- 7.98, N = 3 SE +/- 1.10, N = 3 SE +/- 4.53, N = 3 SE +/- 1.48, N = 3 SE +/- 6.01, N = 3 SE +/- 2.26, N = 3 SE +/- 8.42, N = 3 SE +/- 2.03, N = 3 SE +/- 5.89, N = 3 SE +/- 20.53, N = 3 SE +/- 24.71, N = 3 SE +/- 1.63, N = 3 SE +/- 11.26, N = 3 SE +/- 0.67, N = 3 7070.60 6320.00 6313.16 6184.20 6172.55 6164.79 6161.42 6159.21 6157.49 6133.91 5523.31 5517.02 5513.08 5061.60 5024.39 4665.33 MIN: 4721.3 / MAX: 11806.11 MIN: 4254.97 / MAX: 10469.4 MIN: 4256.89 / MAX: 10467.36 MIN: 4170.96 / MAX: 10241.48 MIN: 4118.12 / MAX: 10228.73 MIN: 4152.92 / MAX: 10208.98 MIN: 4158.08 / MAX: 10213.08 MIN: 4154.94 / MAX: 10200.04 MIN: 4104.14 / MAX: 10212.45 MIN: 4136.23 / MAX: 10160.8 MIN: 3739.77 / MAX: 9132.41 MIN: 3740.26 / MAX: 9153.64 MIN: 3744.15 / MAX: 9173.02 MIN: 3412.46 / MAX: 8379.01 MIN: 3388.65 / MAX: 8334.48 MIN: 3372.31 / MAX: 7239.74 1. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto
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.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.C 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R EPYC 2 7R32 Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 1300 2600 3900 5200 6500 SE +/- 88.25, N = 3 SE +/- 34.33, N = 3 SE +/- 77.32, N = 3 SE +/- 38.41, N = 3 SE +/- 32.92, N = 3 SE +/- 31.12, N = 3 SE +/- 44.67, N = 3 SE +/- 40.50, N = 3 SE +/- 38.56, N = 4 SE +/- 14.22, N = 3 SE +/- 34.91, N = 3 SE +/- 2.92, N = 3 SE +/- 2.61, N = 3 SE +/- 19.04, N = 5 6104.94 5059.02 5052.63 4005.26 3768.66 3485.99 3194.18 3025.11 2984.02 2641.32 2044.24 1863.15 1621.48 1545.50 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. 2 x Xeon Platinum 8280: Open MPI 4.0.3rc4 3. 2 x Xeon Platinum 8259CL NUMA off: Open MPI 3.1.3 4. 2 x Xeon Platinum 8259CL: Open MPI 3.1.3 5. 2 x Xeon Gold 6226R: Open MPI 4.0.3rc4 6. 2 x Xeon Gold 5220R: Open MPI 4.0.3rc4 7. EPYC 2 7R32: Open MPI 3.1.3 8. Xeon Platinum 8280: Open MPI 4.0.3rc4 9. Xeon W-3275M: Open MPI 3.1.3 10. 2 x Xeon Silver 4216: Open MPI 4.0.3rc4 11. Xeon Platinum 8259CL: Open MPI 3.1.3 12. Xeon Gold 6226R: Open MPI 4.0.3rc4 13. Xeon Gold 5220R: Open MPI 4.0.3rc4 14. Xeon Gold 5218: Open MPI 4.0.3rc4 15. Xeon Silver 4216: Open MPI 4.0.3rc4
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.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 9Jan2020 Model: Rhodopsin Protein 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8275CL NUMA off EPYC 2 7R32 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Platinum 8280 Xeon W-3275M 2 x Xeon Silver 4216 Xeon Platinum 8259CL Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 6 12 18 24 30 SE +/- 0.251, N = 14 SE +/- 0.332, N = 3 SE +/- 0.155, N = 3 SE +/- 0.324, N = 3 SE +/- 0.178, N = 3 SE +/- 0.372, N = 15 SE +/- 0.055, N = 3 SE +/- 0.046, N = 3 SE +/- 0.192, N = 3 SE +/- 0.127, N = 15 SE +/- 0.014, N = 3 SE +/- 0.083, N = 3 SE +/- 0.024, N = 3 SE +/- 0.018, N = 3 SE +/- 0.006, N = 3 SE +/- 0.021, N = 3 24.788 22.535 22.301 21.887 20.984 20.821 18.150 17.378 15.314 14.562 14.161 13.040 10.325 9.535 8.158 7.810 -lpng -lz -lpng -lz -lpng -lz -lpng -lz -ljpeg -lpng -lz -lpng -lz -lpng -lz -lpng -lz -lpng -lz -lpng -lz 1. (CXX) g++ options: -O3 -rdynamic -lfftw3 -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.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_3d - Data Type: bf16bf16bf16 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R Xeon Platinum 8280 Xeon W-3275M Xeon Platinum 8259CL 2 x Xeon Gold 5220R 2 x Xeon Silver 4216 Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 5 10 15 20 25 SE +/- 0.00369, N = 3 SE +/- 0.00222, N = 3 SE +/- 0.01549, N = 3 SE +/- 0.00526, N = 3 SE +/- 0.00712, N = 3 SE +/- 0.00159, N = 3 SE +/- 0.00251, N = 3 SE +/- 0.03985, N = 3 SE +/- 0.00210, N = 3 SE +/- 0.01392, N = 3 SE +/- 0.00821, N = 3 SE +/- 0.00297, N = 3 SE +/- 0.00134, N = 3 SE +/- 0.05476, N = 3 SE +/- 0.02388, N = 3 4.35817 4.36002 4.37952 4.85689 4.87194 6.29647 7.69605 8.46273 9.37107 9.42591 10.93790 12.32710 16.82530 21.42900 21.47550 MIN: 4.82 MIN: 4.83 MIN: 6.25 MIN: 7.67 MIN: 8.21 MIN: 9.33 MIN: 9.32 MIN: 10.86 MIN: 12.27 MIN: 16.72 MIN: 21.29 MIN: 21.24 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_3d - Data Type: f32 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R Xeon Platinum 8280 Xeon Platinum 8259CL EPYC 2 7R32 Xeon W-3275M 2 x Xeon Gold 5220R Xeon Gold 6226R 2 x Xeon Silver 4216 Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 2 4 6 8 10 SE +/- 0.00373, N = 3 SE +/- 0.00132, N = 3 SE +/- 0.00161, N = 3 SE +/- 0.00388, N = 3 SE +/- 0.00118, N = 3 SE +/- 0.00200, N = 3 SE +/- 0.00032, N = 3 SE +/- 0.00571, N = 3 SE +/- 0.00603, N = 3 SE +/- 0.01801, N = 3 SE +/- 0.00092, N = 3 SE +/- 0.00634, N = 3 SE +/- 0.00590, N = 3 SE +/- 0.01927, N = 3 SE +/- 0.01731, N = 3 SE +/- 0.01443, N = 3 1.13608 1.17278 1.17385 1.26395 1.26649 1.70749 1.96279 2.20053 2.20471 2.27526 2.69700 3.13006 3.85512 4.88966 5.80420 7.63646 MIN: 1.95 MIN: 2.17 MIN: 2.14 MIN: 2.12 MIN: 2.66 MIN: 3.1 MIN: 3.82 MIN: 4.84 MIN: 5.77 MIN: 7.57 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
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.org Seconds, Fewer Is Better CloverLeaf Lagrangian-Eulerian Hydrodynamics EPYC 2 7R32 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8280 2 x Xeon Platinum 8259CL 2 x Xeon Gold 6226R Xeon Platinum 8280 2 x Xeon Silver 4216 2 x Xeon Gold 5220R Xeon Platinum 8259CL Xeon W-3275M Xeon Gold 6226R Xeon Gold 5220R Xeon Gold 5218 Xeon Silver 4216 0.3353 0.6706 1.0059 1.3412 1.6765 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 15 SE +/- 0.03, N = 15 SE +/- 0.04, N = 15 SE +/- 0.00, N = 3 SE +/- 0.04, N = 15 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 15 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 0.36 0.63 0.69 0.78 0.93 0.96 1.00 1.06 1.11 1.14 1.27 1.28 1.37 1.49 1. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
Nettle GNU Nettle is a low-level cryptographic library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mbyte/s, More Is Better Nettle 3.5.1 Test: sha512 Xeon W-3275M Xeon Platinum 8280 2 x Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off Xeon Gold 5218 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Gold 6226R 2 x Xeon Platinum 8275CL Xeon Gold 5220R EPYC 2 7R32 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Silver 4216 120 240 360 480 600 SE +/- 2.72, N = 3 SE +/- 0.15, N = 3 SE +/- 0.97, N = 3 SE +/- 0.61, N = 3 SE +/- 0.19, N = 3 SE +/- 0.11, N = 3 SE +/- 0.19, N = 3 SE +/- 0.77, N = 3 SE +/- 2.94, N = 3 SE +/- 1.03, N = 3 SE +/- 0.28, N = 3 SE +/- 1.80, N = 3 SE +/- 2.61, N = 3 SE +/- 2.12, N = 3 SE +/- 0.28, N = 3 SE +/- 0.56, N = 3 550.93 501.98 500.98 490.26 489.51 489.42 489.15 488.81 487.55 485.86 478.09 438.23 437.62 436.73 401.13 399.99 1. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto
OpenBenchmarking.org Mbyte/s, More Is Better Nettle 3.5.1 Test: chacha Xeon W-3275M 2 x Xeon Platinum 8280 Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off 2 x Xeon Platinum 8275CL 2 x Xeon Gold 6226R Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Gold 5218 Xeon Gold 5220R Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Silver 4216 Xeon Silver 4216 EPYC 2 7R32 300 600 900 1200 1500 SE +/- 5.99, N = 3 SE +/- 0.37, N = 3 SE +/- 0.86, N = 3 SE +/- 0.48, N = 3 SE +/- 1.27, N = 3 SE +/- 0.61, N = 3 SE +/- 0.49, N = 3 SE +/- 0.41, N = 3 SE +/- 0.76, N = 3 SE +/- 1.02, N = 3 SE +/- 1.52, N = 3 SE +/- 4.50, N = 3 SE +/- 4.18, N = 3 SE +/- 0.18, N = 3 SE +/- 0.91, N = 3 SE +/- 0.08, N = 3 1172.15 1051.94 1051.11 1027.59 1025.60 1025.38 1024.99 1024.98 1024.49 1020.09 920.51 917.75 917.51 841.65 837.61 750.36 MIN: 567.45 / MAX: 3234.29 MIN: 535.04 / MAX: 2870.94 MIN: 532.77 / MAX: 2871.25 MIN: 523.28 / MAX: 2803.78 MIN: 515.88 / MAX: 2805.16 MIN: 522.31 / MAX: 2798.89 MIN: 521.91 / MAX: 2799.45 MIN: 518.14 / MAX: 2797.53 MIN: 507.67 / MAX: 2797.4 MIN: 519.31 / MAX: 2788.96 MIN: 461.1 / MAX: 2517.2 MIN: 461.99 / MAX: 2517.41 MIN: 463.47 / MAX: 2517.16 MIN: 428.69 / MAX: 2296.48 MIN: 423.28 / MAX: 2294.55 MIN: 382.32 / MAX: 2047.21 1. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto
OpenBenchmarking.org Mbyte/s, More Is Better Nettle 3.5.1 Test: poly1305-aes Xeon W-3275M 2 x Xeon Platinum 8280 Xeon Platinum 8280 2 x Xeon Platinum 8275CL NUMA off Xeon Gold 5218 2 x Xeon Gold 6226R 2 x Xeon Gold 5220R Xeon Gold 6226R 2 x Xeon Platinum 8275CL Xeon Gold 5220R 2 x Xeon Platinum 8259CL NUMA off 2 x Xeon Platinum 8259CL Xeon Platinum 8259CL 2 x Xeon Silver 4216 Xeon Silver 4216 EPYC 2 7R32 700 1400 2100 2800 3500 SE +/- 24.77, N = 3 SE +/- 1.10, N = 3 SE +/- 0.87, N = 3 SE +/- 1.01, N = 3 SE +/- 0.60, N = 3 SE +/- 0.50, N = 3 SE +/- 0.92, N = 3 SE +/- 2.79, N = 3 SE +/- 17.33, N = 3 SE +/- 5.86, N = 3 SE +/- 0.36, N = 3 SE +/- 15.23, N = 3 SE +/- 12.50, N = 3 SE +/- 1.74, N = 3 SE +/- 3.38, N = 3 SE +/- 0.71, N = 3 3207.98 2868.69 2867.48 2803.55 2798.56 2797.43 2797.22 2795.49 2785.99 2779.78 2516.87 2497.86 2492.48 2294.74 2291.69 2046.35 1. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto
2 x Xeon Gold 5220R Processor: 2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 12 x 32 GB DDR4-2933MT/s HMA84GR7CJR4N-WM, Disk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE
OS: Ubuntu 20.04, Kernel: 5.4.0-18-generic (x86_64), Desktop: GNOME Shell 3.36.0, Display Server: X Server 1.20.7, Display Driver: modesetting 1.20.7, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080
Compiler Notes: --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 -vProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002cJava Notes: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-2ubuntu2)Python Notes: + Python 3.8.2Security Notes: 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
Testing initiated at 26 March 2020 16:33 by user root.
Xeon Gold 5220R Processor: Intel Xeon Gold 5220R @ 3.90GHz (18 Cores / 36 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 6 x 32 GB DDR4-2933MT/s HMA84GR7CJR4N-WM, Disk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE
OS: Ubuntu 20.04, Kernel: 5.4.0-18-generic (x86_64), Desktop: GNOME Shell 3.36.0, Display Server: X Server 1.20.7, Display Driver: modesetting 1.20.7, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1024x768
Compiler Notes: --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 -vProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002cJava Notes: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-2ubuntu2)Python Notes: + Python 3.8.2Security Notes: 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
Testing initiated at 27 March 2020 07:29 by user root.
Xeon Platinum 8280 Processor: Intel Xeon Platinum 8280 @ 4.00GHz (28 Cores / 56 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 6 x 32 GB DDR4-2933MT/s HMA84GR7CJR4N-WM, Disk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE
OS: Ubuntu 20.04, Kernel: 5.4.0-18-generic (x86_64), Desktop: GNOME Shell 3.36.0, Display Server: X Server 1.20.7, Display Driver: modesetting 1.20.7, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1024x768
Compiler Notes: --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 -vProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002cJava Notes: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-2ubuntu2)Python Notes: + Python 3.8.2Security Notes: 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
Testing initiated at 28 March 2020 06:10 by user root.
2 x Xeon Platinum 8280 Processor: 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 12 x 32 GB DDR4-2933MT/s HMA84GR7CJR4N-WM, Disk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE
OS: Ubuntu 20.04, Kernel: 5.4.0-18-generic (x86_64), Desktop: GNOME Shell 3.36.0, Display Server: X Server 1.20.7, Display Driver: modesetting 1.20.7, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1024x768
Compiler Notes: --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 -vProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002cJava Notes: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-2ubuntu2)Python Notes: + Python 3.8.2Security Notes: 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
Testing initiated at 28 March 2020 18:49 by user root.
Xeon Gold 5218 Processor: Intel Xeon Gold 5218 @ 3.90GHz (16 Cores / 32 Threads), Motherboard: GIGA