AMD EPYC 7R32 48-Core testing with a Supermicro H11SSL-i v2.00 (2.1 BIOS) and llvmpipe 126GB on Ubuntu 19.10 via the Phoronix Test Suite.
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
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) .
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 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
Xeon 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 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 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 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 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) 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 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 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 Logarithmic Result Overview Phoronix Test Suite 10.4.0m1 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 PyBench Numpy Benchmark lzbench Zstd Compression Renaissance Scikit-Learn Himeno Benchmark Radiance Benchmark DaCapo Benchmark
Xeon Tests mkl-dnn: Convolution Batch conv_googlenet_v3 - u8s8f32 arrayfire: Conjugate Gradient CPU arrayfire: BLAS CPU mkl-dnn: Convolution Batch conv_alexnet - f32 mkl-dnn: Convolution Batch conv_all - u8s8f32 mkl-dnn: Convolution Batch conv_googlenet_v3 - f32 mkl-dnn: Convolution Batch conv_alexnet - u8s8f32 mkl-dnn: Deconvolution Batch deconv_3d - f32 mkl-dnn: Convolution Batch conv_all - f32 mkl-dnn: Convolution Batch conv_alexnet - bf16bf16bf16 mkl-dnn: Convolution Batch conv_all - bf16bf16bf16 mkl-dnn: Convolution Batch conv_googlenet_v3 - bf16bf16bf16 ospray: NASA Streamlines - Path Tracer ospray: XFrog Forest - SciVis ospray: XFrog Forest - Path Tracer mkl-dnn: Convolution Batch conv_3d - bf16bf16bf16 ospray: NASA Streamlines - SciVis mkl-dnn: IP Batch All - u8s8f32 mkl-dnn: Deconvolution Batch deconv_3d - bf16bf16bf16 ospray: San Miguel - SciVis embree: Pathtracer ISPC - Crown ospray: San Miguel - Path Tracer hpcg: embree: Pathtracer ISPC - Asian Dragon embree: Pathtracer ISPC - Asian Dragon Obj luxcorerender: Rainbow Colors and Prism blender: Classroom - CPU-Only mkl-dnn: Deconvolution Batch deconv_1d - f32 namd: ATPase Simulation - 327,506 Atoms luxcorerender: DLSC mkl-dnn: Deconvolution Batch deconv_1d - bf16bf16bf16 john-the-ripper: MD5 blender: Pabellon Barcelona - CPU-Only john-the-ripper: Blowfish mkl-dnn: Convolution Batch conv_3d - u8s8f32 intel-mpi: IMB-P2P PingPong mkl-dnn: Deconvolution Batch deconv_1d - u8s8f32 npb: EP.D ospray: Magnetic Reconnection - SciVis npb: EP.C mkl-dnn: Deconvolution Batch deconv_all - bf16bf16bf16 mkl-dnn: Deconvolution Batch deconv_3d - u8s8f32 blender: BMW27 - CPU-Only embree: Pathtracer - Crown stockfish: Total Time asmfish: 1024 Hash Memory, 26 Depth v-ray: CPU embree: Pathtracer - Asian Dragon embree: Pathtracer - Asian Dragon Obj blender: Fishy Cat - CPU-Only mkl-dnn: IP Batch 1D - bf16bf16bf16 npb: SP.B blender: Barbershop - CPU-Only lammps: Rhodopsin Protein mkl-dnn: IP Batch 1D - f32 appleseed: Disney Material mkl-dnn: Deconvolution Batch deconv_all - f32 tungsten: Hair basis: UASTC Level 3 npb: LU.C build-linux-kernel: Time To Compile npb: BT.C dav1d: Summer Nature 1080p pgbench: Buffer Test - Normal Load - Read Only mkl-dnn: IP Batch All - f32 dav1d: Chimera 1080p 10-bit oidn: Memorial build-llvm: Time To Compile npb: MG.C dav1d: Summer Nature 4K appleseed: Emily svt-av1: Enc Mode 8 - 1080p svt-av1: Enc Mode 4 - 1080p mrbayes: Primate Phylogeny Analysis mlpack: scikit_qda pgbench: Buffer Test - Normal Load - Read Write renaissance: Apache Spark Bayes mlpack: scikit_ica deepspeech: CPU build2: Time To Compile mlpack: scikit_linearridgeregression svt-vp9: Visual Quality Optimized - Bosphorus 1080p build-gcc: Time To Compile build-gdb: Time To Compile pyperformance: python_startup appleseed: Material Tester nettle: poly1305-aes nettle: chacha nettle: aes256 lzbench: Crush 0 - Decompression phpbench: PHP Benchmark Suite pyperformance: float pyperformance: django_template lzbench: Brotli 2 - Decompression basis: ETC1S lzbench: Zstd 1 - Compression pybench: Total For Average Test Times smhasher: wyhash smhasher: wyhash numpy: lzbench: Zstd 8 - Decompression compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 mlpack: scikit_svm lzbench: Brotli 2 - Compression lzbench: Zstd 1 - Decompression nettle: sha512 scikit-learn: himeno: Poisson Pressure Solver radiance: Serial radiance: SMP Parallel lzbench: Crush 0 - Compression renaissance: Apache Spark PageRank pyperformance: regex_compile dacapobench: Jython tungsten: Water Caustic lzbench: Zstd 8 - Compression renaissance: Scala Dotty cloverleaf: Lagrangian-Eulerian Hydrodynamics renaissance: Savina Reactors.IO 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 15.7542 9.898 2359.13 122.761 2479.28 54.8190 35.9778 2.69700 999.544 712.201 3917.52 187.168 10.42 7.19 3.98 15.2177 55.56 4.08605 9.42591 43.48 33.4469 3.95 25.6303 43.0983 37.1498 4.46 165.96 2.12680 0.60333 4.44 7.22975 4821000 208.30 51324 4896.41 19650424.333333 0.560890 3780.59 47.62 3768.66 3152.41 3112.36 60.67 29.5153 74235829 85501851 40270 35.8757 32.3301 98.24 5.72791 50932.88 260.56 17.378 2.23009 88.856634 1278.25 11.0726 27.981 108883.40 36.699 100761.29 321.84 598798.571324 10.6348 70.81 27.97 286.782 58984.18 177.89 180.645797 49.209 5.302 134.928 42.69 34227.724903 3662.767 77.41 125.11863 72.151 2.39 237.57 1060.578 146.439 11.2 189.459653 2797.22 1024.975 6159.21 419 631283 113 47.3 613 54.554 437 1100 18.806 300.73 1101 10.449 17.92 172 1147 489.15 10.458 3404.690861 746.918 230.561 93 24540.720 167 4877 23.3367 74 7414.619 1.06 26257.008 28.4532 6.409 1201.54 244.745 4826.71 108.161 66.7352 4.88966 1948.77 1433.47 7839.95 369.287 5.38 3.70 2.06 29.9173 28.57 4.61054 16.8253 23.26 17.6604 2.14 13.3529 23.6042 20.3418 2.48 328.81 3.36432 1.15745 2.32 13.1428 2506000 404.78 25547 9696.92 10276849.521739 0.843709 1966.61 27.03 1863.15 5695.58 6072.57 113.30 16.0514 38167326 43217939 21886 19.6105 17.7957 175.95 8.68590 23346.56 456.47 9.535 4.49985 158.77238 1920.74 18.9840 46.708 56744.87 59.012 50787.79 274.98 383120.690509 8.90795 58.05 18.41 430.426 31197.22 160.59 284.27974 33.088 4.285 134.483 34.24 45518.593515 3150.096 68.19 126.07801 91.641 2.25 224.01 1167.683 151.909 11.3 162.860353 2779.78 1020.093 6133.91 428 629690 114 47.1 651 56.018 444 1114 18.815 313.76 1194 10.355 17.82 176 1180 485.86 10.112 3398.397455 749.923 242.515 98 21704.485 168 4834 25.0080 76 7556.329 1.28 22776.295 11.2900 4.115 3432.16 94.1937 2846.12 42.0758 26.8391 1.96279 765.745 637.374 3497.47 166.984 9.49 6.25 3.46 14.0780 50 3.23121 7.69605 38.46 28.7730 3.52 14.9097 38.3100 33.0490 4.11 198.25 1.46232 0.70709 3.79 6.55374 4090000 246.31 42864 5919.94 16653864.768116 0.371036 3283.38 42.87 3194.18 2935.99 3716.98 69.80 26.2800 62891312 68762075 34710 32.2474 29.2061 110.67 4.83170 32682.14 287.80 15.314 2.39451 103.833099 1113.54 12.6863 30.689 74255.67 40.898 71842.34 323.20 560887.766696 6.79509 65.40 31.10 308.741 37089.05 199.08 197.649505 51.917 6.030 128.848 30.45 53139.057777 2674.175 67.36 118.09377 74.118 1.67 265.40 1063.705 144.643 11.2 123.979103 2867.48 1051.111 6313.16 440 649164 109 46.2 673 51.446 457 1076 22.678 330.33 1224 8.203 17.19 181 1212 501.98 9.127 3510.205159 728.361 235 101 20621.229 164 4547 22.0167 77 6664.254 0.96 21975.122 7.46050 7.481 3430.28 49.8437 1517.44 23.1772 19.8143 1.13608 496.816 320.060 1766.35 86.5391 18.18 12.05 6.67 7.92912 90.91 3.11002 4.35817 69.52 53.2304 6.53 28.8542 68.4241 58.6945 7.15 100.47 1.24029 0.36226 7.19 4.06847 7880000 129.01 84084 3005.48 31821690.550725 0.394455 6284.65 71.43 6104.94 1779.15 1893.72 38.79 45.6121 119715795 133839896 64331 57.4870 51.7853 66.39 3.65964 70893.41 187.33 24.788 1.63986 68.618272 881.783 7.82706 19.885 140090.32 27.309 136046.53 409.88 909916.490086 9.52466 85.14 34.49 221.515 69175.12 221.31 154.980752 56.982 7.033 129.986 38.35 24466.911227 3228.633 63.35 122.22468 62.776 1.82 233.17 1005.530 142.695 11.2 193.44241 2868.69 1051.936 6320.00 428 649693 109 45.9 623 52.694 449 1073 22.677 321.82 1124 9.137 17.19 176 1168 500.98 9.392 3514.604106 728.246 226.076 96 23588.397 164 4711 21.5896 75 6890.606 0.69 26764.941 34.6031 7.042 1002.09 298.300 5840.26 131.088 81.0705 5.80420 2363.00 1874.47 10255.2 484.594 4.37 3.01 1.68 39.9985 23.26 4.83875 21.4290 18.87 14.4163 1.75 13.0138 19.4321 16.7685 1.88 433.42 3.99488 1.51168 1.74 16.5484 1912667 531.98 21403 11821.3 9066471.0434783 0.976730 1635.78 22.22 1621.48 6721.02 7189.03 149.39 12.3882 32424332 36561817 16981 15.3104 13.8526 229.28 8.8271 22329.34 589.07 8.158 4.75696 182.557972 1699.69 22.4866 55.209 48143.49 67.156 48617.05 265.46 322051.631187 9.30959 55.88 15.80 501.218 30328.65 136.86 328.139133 27.193 3.339 147.734 37.41 40894.896756 3477.331 68.78 128.40692 101.716 2.46 172.82 1218.874 156.299 11.1 179.751505 2798.56 1024.493 6164.79 430 632455 114 47.2 655 58.473 446 1101 19.806 315.14 1195 11.122 17.98 176 1184 489.51 10.286 3405.035897 747.844 241.897 96 23703.029 167 5096 25.9635 74 8286.123 1.37 27198.080 45.0502 7.819 765.491 395.441 6241.16 171.428 105.826 7.63646 3129.93 1875.23 10258.0 484.895 3.41 2.34 1.31 40.0192 18.18 5.59275 21.4755 14.71 11.3827 1.40 11.8883 15.5911 13.4918 1.88 432.11 5.31087 1.51721 1.77 16.5516 1893333 531.39 20424 12300.3 8923779.5507246 1.27375 1571.49 17.94 1545.50 6721.54 7457.86 149.02 12.4316 31174576 35085496 17105 15.2796 13.8827 229.71 10.9014 21149.68 593.13 7.810 5.16658 194.401843 2201.04 23.6129 58.246 46723.01 71.770 46389.79 232.35 313376.779917 10.1930 50.10 12.85 531.152 28301.13 132.46 345.389961 26.460 3.309 193.466 40.75 40373.304894 3588.692 81.36 135.99744 109.699 2.97 173.18 1398.020 177.772 15.4 188.776756 2291.69 837.612 5024.39 353 515697 137 57.5 542 67.461 365 1342 22.131 22004.08 272.12 998 11.430 20.89 146 973 399.99 12.030 2823.595364 909.318 299.739 82 25271.433 204 5768 28.8979 64 8634.691 1.49 22798.382 17.9735 6.451 2137.03 155.368 4478.93 69.1431 42.2202 3.13006 1227.07 1042.34 5709.17 269.991 5.52 3.68 2.02 22.4243 29.41 4.53821 12.3271 22.69 16.8099 2.02 13.9581 22.4598 19.3228 2.51 321.53 2.23126 1.13586 2.35 9.90362 2583000 400.96 27126 9374.60 10620968.608695 0.528632 2094.53 25.48 2044.24 3966.73 5864.26 111.82 15.9943 39776292 44614925 22074 19.3472 17.4223 173.95 5.71439 23859.79 453.22 10.325 4.41366 155.228014 983.913 18.6129 44.943 58594.50 57.772 56576.12 307.75 376860.318615 8.84233 62.32 22.01 433.191 31633.6 170.07 276.768654 34.636 4.340 123.702 31.96 46503.283040 2856.850 61.82 119.78717 88.977 1.93 221.95 1092.587 139.120 11.0 156.605614 2795.49 1024.992 6161.42 429 632431 115 47.3 653 54.790 445 1103 25.134 19429.87 318.87 1193 10.330 17.92 176 1182 488.81 9.924 3401.157135 746.687 242.002 95 21743.019 168 4609 24.0874 74 6999.497 1.27 27198.856 11.3282 7.155 3912.30 81.1400 2377.91 36.3716 26.5363 1.70749 694.324 527.017 2871.11 137.734 10.56 7.09 3.88 11.6076 55.56 4.11779 6.29647 42.27 31.7318 3.71 26.5910 40.4325 34.8030 4.32 163.32 1.49724 0.58237 4.5183 5.38402 4977667 207.41 53485 4821.24 20467429.521739 0.369060 3969.60 45.45 4005.26 2169.93 2987.08 59.45 28.9602 75203729 83894514 34749 34.6919 31.3117 96.41 3.21281 49232.24 257.01 18.150 2.18975 84.844108 711.389 10.6653 27.226 106268.33 36.595 77470.67 358.62 587882.232699 10.5239 73.95 33.06 279.682 58681.42 203.10 177.661148 51.710 5.431 124.258 44.53 37715.216271 3405.414 74.63 123.38702 70.608 2.08 256.91 996.904 133.444 10.9 185.357154 2797.43 1025.384 6157.49 418 632601 113 47.1 608 54.947 437 1104 25.129 19424.11 304.16 1100 10.206 17.77 172 1141 489.42 10.449 3410.383938 745.686 233.042 91 24522.220 167 4806 23.1916 72 7231.014 0.93 27972.998 23.7028 16.92 1497.75 197.914 3215.17 87.5434 55.3361 3.85512 1578.24 938.910 5156.69 246.446 6.62 4.57 2.55 20.5163 34.48 4.82603 10.9379 27.84 21.7468 2.63 23.1574 28.9732 25.0678 3.65 218.06 3.06590 0.76982 3.43 8.86913 3764000 272.72 41021 6329.94 17176230.536232 0.770300 3144.70 32.53 2984.02 3600.95 3849.13 78.72 23.2674 60569696 66895810 27592 28.2032 25.4971 125.35 5.56500 42220.94 333.40 14.161 2.66699 107.498089 1364.26 13.6031 34.632 85606.53 45.315 65509.98 272.55 501697.238231 11.4215 59.51 20.43 347.827 52832.47 159.60 222.968514 40.548 4.216 194.504 50.10 34916.030852 4199.411 94.45 133.01160 86.325 2.99 206.42 1268.815 169.704 15.4 197.740442 2294.74 841.649 5061.60 344 519964 137 57.5 509 65.644 359 1343 22.129 22011.20 262.78 930 10.978 21.09 142 943 401.13 12.549 2817.673053 907.757 281.251 80 28045.920 204 5802 27.3948 63 8583.014 1.00 28596.105 13.4504 4.423 3128.39 108.568 2967.92 49.8744 31.9893 2.27526 878.390 702.065 3880.44 188.611 8.69 5.72 3.17 16.5906 45.45 3.59218 8.46273 34.48 26.4010 3.25 14.1623 35.1495 30.3458 3.79 213.36 1.74515 0.81434 3.53 7.61595 3654000 265.41 40326 6183.11 20246604.623188 0.458422 3210.52 40 3025.11 3293.94 3852.37 74.96 24.5503 61170651 66225641 33014 30.1057 27.1952 118.09 5.56304 31426.53 304.79 14.562 2.86715 106.643392 1292.62 12.7104 30.634 69606.84 36.367 69347.58 537.84 567696.505912 7.54439 81.60 27.35 281.678 35376.11 256.60 196.929786 53.819 6.389 143.348 32.65 11704.231804 2743.623 54.91 123.85252 66.415 1.99 282.18 994.583 134.824 17.7 124.147301 3207.98 1172.153 7070.60 509 734339 94.5 49.9 721 47.653 508 951 18.508 26298.77 367.56 1298 8.380 15.78 196 1299 550.93 9.661 3866.090988 665.7 219.836 109 21015.543 157 4321 21.5517 84 6970.904 1.14 25186.666 17.7549 13.22 6259.01 79.1109 2023.47 33.6305 59.9040 1.17385 1206.22 348.243 1919.50 93.3596 17.02 11.36 6.25 8.71234 82.62 5.36708 4.37952 63.54 49.0461 5.82 8.41405 38.7658 36.6652 7.09 108.97 1.33109 6.73 3.96906 7388333 139.11 77771 3250.89 35954425.362319 0.355362 50.88 1730.80 2059.03 41.68 41.7899 109874307 119549901 58326 40.0787 35.6676 69.93 4.10369 189.55 22.301 1.95992 68.606542 981.058 8.29067 21.060 27.100 422.89 629984.514253 19.1030 90.28 15.06 218.050 218.14 152.902049 55.374 5.243 125.867 62.02 3890.770882 5185.621 53.50 113.14396 64.503 2.36 191.66 966.599 128.950 189.296166 2785.99 1025.603 6172.55 434 640173 592 52.608 439 1133 26.086 18770.15 338.44 1053 10.945 16.87 170 1099 487.55 11.065 3440.518277 753.635 232.695 94 24505.962 4685 22.7599 73 6733.160 26906.886 10.4841 9.654 6325.07 57.5111 1708.05 25.0533 30.6427 1.17278 650.981 348.326 1918.28 93.2842 16.95 11.36 6.24 8.64707 83.33 3.84746 4.36002 66.67 49.9559 5.87 6.32971 51.8741 44.7151 7.31 108.94 1.25116 6.75 3.96510 7350667 139.00 78327 3252.48 35888907.985507 0.354714 58.82 1705.35 2057.93 41.72 41.3944 108412514 103033955 58525 45.7674 40.8502 70.04 4.06041 190.01 20.984 1.63599 68.202167 910.142 8.19337 20.994 29.258 406.66 725740.723795 12.6820 90.78 19.55 244.910 216.86 152.093681 56.122 5.942 124.297 57.25 3197.742954 4510.830 53.66 138.25629 64.421 2.46 228.38 1032.978 145.510 194.846861 2803.55 1027.592 6184.20 432 639026 582 53.135 443 1123 26.129 18775.94 315.66 999 10.289 18.42 172 1090 490.26 11.490 3430.766164 753.433 227.159 95 24666.363 4759 22.7088 75 7042.354 27361.597 730.306 35.13 990.798 96.6881 11728.8 42.5413 1301.36 2.20471 710.140 16.60 11.03 5.85 76.92 149.339 58.82 45.1869 4.73 17.0608 52.3541 45.4330 8.12 101.34 2.22540 0.48614 7.28 3972000 132.04 66475 3076.76 20348261.028985 1131.13 3570.46 40 3485.99 1899.24 41.76 47.6464 116765028 113278977 62897 52.9532 47.5806 65.67 51225.18 177.79 20.821 1.67560 62.431047 1485.47 7.67455 19.193 99821.89 24.005 106415.53 676.16 891303.121943 8.88390 140.14 28.71 200.039 49330.15 321.17 147.685856 54.472 5.714 92.361 39.54 6105.728957 3057.059 49.47 72.81599 59.956 1.79 291.17 849.192 108.675 16.3 175.193708 2046.35 750.357 4665.33 380 500524 66.4 564 54.310 418 1226 323.58 1266 9.230 15.16 165 1148 478.09 10.419 3769.723664 730.7 219.652 81 21641.954 213 5246 22.3247 83 6577.343 0.36 19303.561 OpenBenchmarking.org
MKL-DNN DNNL This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page
Result
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_googlenet_v3 - Data Type: u8s8f32 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 160 320 480 640 800 SE +/- 0.00643, N = 3 SE +/- 0.02138, N = 3 SE +/- 0.01386, N = 3 SE +/- 0.03597, N = 3 SE +/- 0.01482, N = 3 SE +/- 0.02504, N = 3 SE +/- 0.01762, N = 3 SE +/- 0.01218, N = 3 SE +/- 0.01146, N = 3 SE +/- 0.01662, N = 3 SE +/- 0.29660, N = 3 SE +/- 0.02611, N = 3 SE +/- 7.24186, N = 3 15.75420 28.45320 11.29000 7.46050 34.60310 45.05020 17.97350 11.32820 23.70280 13.45040 17.75490 10.48410 730.30600 MIN: 698.32 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl Result Confidence
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_googlenet_v3 - Data Type: u8s8f32 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 130 260 390 520 650 Min: 15.75 / Avg: 15.75 / Max: 15.77 Min: 28.41 / Avg: 28.45 / Max: 28.48 Min: 11.27 / Avg: 11.29 / Max: 11.32 Min: 7.4 / Avg: 7.46 / Max: 7.52 Min: 34.58 / Avg: 34.6 / Max: 34.63 Min: 45.01 / Avg: 45.05 / Max: 45.1 Min: 17.95 / Avg: 17.97 / Max: 18.01 Min: 11.31 / Avg: 11.33 / Max: 11.35 Min: 23.68 / Avg: 23.7 / Max: 23.72 Min: 13.43 / Avg: 13.45 / Max: 13.48 Min: 17.22 / Avg: 17.75 / Max: 18.24 Min: 10.45 / Avg: 10.48 / Max: 10.54 Min: 717.38 / Avg: 730.31 / Max: 742.42 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
Result
OpenBenchmarking.org ms, Fewer Is Better ArrayFire 3.7 Test: Conjugate Gradient CPU 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 8 16 24 32 40 SE +/- 0.099, N = 15 SE +/- 0.094, N = 3 SE +/- 0.067, N = 3 SE +/- 0.086, N = 6 SE +/- 0.069, N = 9 SE +/- 0.047, N = 3 SE +/- 0.026, N = 3 SE +/- 0.072, N = 15 SE +/- 0.372, N = 15 SE +/- 0.075, N = 15 SE +/- 0.220, N = 3 SE +/- 0.272, N = 15 SE +/- 0.217, N = 3 9.898 6.409 4.115 7.481 7.042 7.819 6.451 7.155 16.920 4.423 13.220 9.654 35.130 1. (CXX) g++ options: -rdynamic Perf Per Core
OpenBenchmarking.org ms x Core, Fewer Is Better ArrayFire 3.7 Performance Per Core - Test: Conjugate Gradient CPU 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 400 800 1200 1600 2000 356.33 115.36 115.22 418.94 112.67 125.10 103.22 228.96 541.44 123.84 634.56 463.39 1686.24 1. 2 x Xeon Gold 5220R: Detected core count of 36 2. Xeon Gold 5220R: Detected core count of 18 3. Xeon Platinum 8280: Detected core count of 28 4. 2 x Xeon Platinum 8280: Detected core count of 56 5. Xeon Gold 5218: Detected core count of 16 6. Xeon Silver 4216: Detected core count of 16 7. Xeon Gold 6226R: Detected core count of 16 8. 2 x Xeon Gold 6226R: Detected core count of 32 9. 2 x Xeon Silver 4216: Detected core count of 32 10. Xeon W-3275M: Detected core count of 28 11. 2 x Xeon Platinum 8275CL: Detected core count of 48 12. 2 x Xeon Platinum 8275CL NUMA off: Detected core count of 48 13. EPYC 2 7R32: Detected core count of 48 Perf Per Thread
OpenBenchmarking.org ms x Thread, Fewer Is Better ArrayFire 3.7 Performance Per Thread - Test: Conjugate Gradient CPU 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 700 1400 2100 2800 3500 712.66 230.72 230.44 837.87 225.34 250.21 206.43 457.92 1082.88 247.69 1269.12 926.78 3372.48 1. 2 x Xeon Gold 5220R: Detected thread count of 72 2. Xeon Gold 5220R: Detected thread count of 36 3. Xeon Platinum 8280: Detected thread count of 56 4. 2 x Xeon Platinum 8280: Detected thread count of 112 5. Xeon Gold 5218: Detected thread count of 32 6. Xeon Silver 4216: Detected thread count of 32 7. Xeon Gold 6226R: Detected thread count of 32 8. 2 x Xeon Gold 6226R: Detected thread count of 64 9. 2 x Xeon Silver 4216: Detected thread count of 64 10. Xeon W-3275M: Detected thread count of 56 11. 2 x Xeon Platinum 8275CL: Detected thread count of 96 12. 2 x Xeon Platinum 8275CL NUMA off: Detected thread count of 96 13. EPYC 2 7R32: Detected thread count of 96 Perf Per Clock
OpenBenchmarking.org ms x GHz, Fewer Is Better ArrayFire 3.7 Performance Per Clock - Test: Conjugate Gradient CPU 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 20 40 60 80 100 38.60 25.00 16.46 29.92 27.46 25.02 25.16 27.91 54.14 20.35 51.56 37.65 98.36 1. 2 x Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 2. Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 3. Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 4. 2 x Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 5. Xeon Gold 5218: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 6. Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 7. Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 8. 2 x Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 9. 2 x Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 10. Xeon W-3275M: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.60 11. 2 x Xeon Platinum 8275CL: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 12. 2 x Xeon Platinum 8275CL NUMA off: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 13. EPYC 2 7R32: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 2.80 Perf Per RAM Channel
OpenBenchmarking.org ms x Channel, Fewer Is Better ArrayFire 3.7 Performance Per Memory Channel - Test: Conjugate Gradient CPU 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 EPYC 2 7R32 60 120 180 240 300 59.39 38.45 24.69 44.89 42.25 46.91 38.71 42.93 101.52 281.04 1. 2 x Xeon Gold 5220R: Detected channel count of 6 2. Xeon Gold 5220R: Detected channel count of 6 3. Xeon Platinum 8280: Detected channel count of 6 4. 2 x Xeon Platinum 8280: Detected channel count of 6 5. Xeon Gold 5218: Detected channel count of 6 6. Xeon Silver 4216: Detected channel count of 6 7. Xeon Gold 6226R: Detected channel count of 6 8. 2 x Xeon Gold 6226R: Detected channel count of 6 9. 2 x Xeon Silver 4216: Detected channel count of 6 10. EPYC 2 7R32: Detected channel count of 8 Result Confidence
OpenBenchmarking.org ms, Fewer Is Better ArrayFire 3.7 Test: Conjugate Gradient CPU 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 8 16 24 32 40 Min: 9.29 / Avg: 9.9 / Max: 10.81 Min: 6.29 / Avg: 6.41 / Max: 6.59 Min: 4 / Avg: 4.12 / Max: 4.23 Min: 7.21 / Avg: 7.48 / Max: 7.81 Min: 6.91 / Avg: 7.04 / Max: 7.56 Min: 7.73 / Avg: 7.82 / Max: 7.87 Min: 6.42 / Avg: 6.45 / Max: 6.5 Min: 6.54 / Avg: 7.16 / Max: 7.52 Min: 13.72 / Avg: 16.92 / Max: 18.32 Min: 4.12 / Avg: 4.42 / Max: 5.06 Min: 12.78 / Avg: 13.22 / Max: 13.45 Min: 7.39 / Avg: 9.65 / Max: 11.48 Min: 34.75 / Avg: 35.13 / Max: 35.5 1. (CXX) g++ options: -rdynamic
Result
OpenBenchmarking.org GFLOPS, More Is Better ArrayFire 3.7 Test: BLAS CPU 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 1400 2800 4200 5600 7000 SE +/- 3.91, N = 3 SE +/- 0.37, N = 3 SE +/- 25.11, N = 3 SE +/- 20.06, N = 3 SE +/- 0.62, N = 3 SE +/- 1.52, N = 3 SE +/- 4.16, N = 3 SE +/- 31.78, N = 3 SE +/- 0.79, N = 3 SE +/- 30.40, N = 3 SE +/- 61.47, N = 3 SE +/- 4.90, N = 3 SE +/- 6.50, N = 3 2359.13 1201.54 3432.16 3430.28 1002.09 765.49 2137.03 3912.30 1497.75 3128.39 6259.01 6325.07 990.80 1. (CXX) g++ options: -rdynamic Perf Per Core
OpenBenchmarking.org GFLOPS Per Core, More Is Better ArrayFire 3.7 Performance Per Core - Test: BLAS CPU 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 30 60 90 120 150 65.53 66.75 122.58 61.26 62.63 47.84 133.56 122.26 46.80 111.73 130.40 131.77 20.64 1. 2 x Xeon Gold 5220R: Detected core count of 36 2. Xeon Gold 5220R: Detected core count of 18 3. Xeon Platinum 8280: Detected core count of 28 4. 2 x Xeon Platinum 8280: Detected core count of 56 5. Xeon Gold 5218: Detected core count of 16 6. Xeon Silver 4216: Detected core count of 16 7. Xeon Gold 6226R: Detected core count of 16 8. 2 x Xeon Gold 6226R: Detected core count of 32 9. 2 x Xeon Silver 4216: Detected core count of 32 10. Xeon W-3275M: Detected core count of 28 11. 2 x Xeon Platinum 8275CL: Detected core count of 48 12. 2 x Xeon Platinum 8275CL NUMA off: Detected core count of 48 13. EPYC 2 7R32: Detected core count of 48 Perf Per Thread
OpenBenchmarking.org GFLOPS Per Thread, More Is Better ArrayFire 3.7 Performance Per Thread - Test: BLAS CPU 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 15 30 45 60 75 32.77 33.38 61.29 30.63 31.32 23.92 66.78 61.13 23.40 55.86 65.20 65.89 10.32 1. 2 x Xeon Gold 5220R: Detected thread count of 72 2. Xeon Gold 5220R: Detected thread count of 36 3. Xeon Platinum 8280: Detected thread count of 56 4. 2 x Xeon Platinum 8280: Detected thread count of 112 5. Xeon Gold 5218: Detected thread count of 32 6. Xeon Silver 4216: Detected thread count of 32 7. Xeon Gold 6226R: Detected thread count of 32 8. 2 x Xeon Gold 6226R: Detected thread count of 64 9. 2 x Xeon Silver 4216: Detected thread count of 64 10. Xeon W-3275M: Detected thread count of 56 11. 2 x Xeon Platinum 8275CL: Detected thread count of 96 12. 2 x Xeon Platinum 8275CL NUMA off: Detected thread count of 96 13. EPYC 2 7R32: Detected thread count of 96 Perf Per Clock
OpenBenchmarking.org GFLOPS Per GHz, More Is Better ArrayFire 3.7 Performance Per Clock - Test: BLAS CPU 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 300 600 900 1200 1500 604.91 308.09 858.04 857.57 256.95 239.22 547.96 1003.15 468.05 680.08 1604.87 1621.81 353.86 1. 2 x Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 2. Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 3. Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 4. 2 x Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 5. Xeon Gold 5218: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 6. Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 7. Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 8. 2 x Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 9. 2 x Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 10. Xeon W-3275M: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.60 11. 2 x Xeon Platinum 8275CL: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 12. 2 x Xeon Platinum 8275CL NUMA off: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 13. EPYC 2 7R32: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 2.80 Perf Per RAM Channel
OpenBenchmarking.org GFLOPS Per Channel, More Is Better ArrayFire 3.7 Performance Per Memory Channel - Test: BLAS CPU 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 EPYC 2 7R32 140 280 420 560 700 393.19 200.26 572.03 571.71 167.02 127.58 356.17 652.05 249.63 123.85 1. 2 x Xeon Gold 5220R: Detected channel count of 6 2. Xeon Gold 5220R: Detected channel count of 6 3. Xeon Platinum 8280: Detected channel count of 6 4. 2 x Xeon Platinum 8280: Detected channel count of 6 5. Xeon Gold 5218: Detected channel count of 6 6. Xeon Silver 4216: Detected channel count of 6 7. Xeon Gold 6226R: Detected channel count of 6 8. 2 x Xeon Gold 6226R: Detected channel count of 6 9. 2 x Xeon Silver 4216: Detected channel count of 6 10. EPYC 2 7R32: Detected channel count of 8 Result Confidence
OpenBenchmarking.org GFLOPS, More Is Better ArrayFire 3.7 Test: BLAS CPU 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 1100 2200 3300 4400 5500 Min: 2351.37 / Avg: 2359.13 / Max: 2363.88 Min: 1200.98 / Avg: 1201.54 / Max: 1202.24 Min: 3385.97 / Avg: 3432.16 / Max: 3472.32 Min: 3391.32 / Avg: 3430.28 / Max: 3458.08 Min: 1001.43 / Avg: 1002.09 / Max: 1003.32 Min: 763.23 / Avg: 765.49 / Max: 768.38 Min: 2129.01 / Avg: 2137.03 / Max: 2142.94 Min: 3849.99 / Avg: 3912.3 / Max: 3954.29 Min: 1496.17 / Avg: 1497.75 / Max: 1498.69 Min: 3086.09 / Avg: 3128.39 / Max: 3187.37 Min: 6136.22 / Avg: 6259.01 / Max: 6325.81 Min: 6318.16 / Avg: 6325.07 / Max: 6334.54 Min: 983.21 / Avg: 990.8 / Max: 1003.73 1. (CXX) g++ options: -rdynamic
MKL-DNN DNNL This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page
Result
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_alexnet - Data Type: f32 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 90 180 270 360 450 SE +/- 0.04, N = 3 SE +/- 0.16, N = 3 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 SE +/- 0.11, N = 3 SE +/- 0.95, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.11, N = 3 SE +/- 0.88, N = 3 SE +/- 0.79, N = 3 SE +/- 1.13, N = 3 122.76 244.75 94.19 49.84 298.30 395.44 155.37 81.14 197.91 108.57 79.11 57.51 96.69 MIN: 121.68 MIN: 242.31 MIN: 93.73 MIN: 297.84 MIN: 390.56 MIN: 154.79 MIN: 79.72 MIN: 195.97 MIN: 102.46 MIN: 74.84 MIN: 93.63 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl Result Confidence
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_alexnet - Data Type: f32 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 70 140 210 280 350 Min: 122.69 / Avg: 122.76 / Max: 122.81 Min: 244.44 / Avg: 244.75 / Max: 244.98 Min: 94.07 / Avg: 94.19 / Max: 94.27 Min: 49.69 / Avg: 49.84 / Max: 49.95 Min: 298.15 / Avg: 298.3 / Max: 298.51 Min: 393.64 / Avg: 395.44 / Max: 396.87 Min: 155.26 / Avg: 155.37 / Max: 155.43 Min: 81.1 / Avg: 81.14 / Max: 81.2 Min: 197.83 / Avg: 197.91 / Max: 197.98 Min: 108.37 / Avg: 108.57 / Max: 108.74 Min: 77.71 / Avg: 79.11 / Max: 80.74 Min: 56.48 / Avg: 57.51 / Max: 59.07 Min: 94.45 / Avg: 96.69 / Max: 98.06 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Result
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_all - Data Type: u8s8f32 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 3K 6K 9K 12K 15K SE +/- 2.07, N = 3 SE +/- 4.48, N = 3 SE +/- 1.24, N = 3 SE +/- 3.12, N = 3 SE +/- 1.57, N = 3 SE +/- 4.87, N = 3 SE +/- 7.74, N = 3 SE +/- 10.67, N = 3 SE +/- 23.72, N = 3 SE +/- 15.10, N = 3 SE +/- 3.97, N = 3 SE +/- 0.40, N = 3 SE +/- 19.01, N = 3 2479.28 4826.71 2846.12 1517.44 5840.26 6241.16 4478.93 2377.91 3215.17 2967.92 2023.47 1708.05 11728.80 MIN: 4806.63 MIN: 2813.78 MIN: 5831.48 MIN: 6214.68 MIN: 4461.44 MIN: 3181.24 MIN: 2893.12 MIN: 11565.1 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl Result Confidence
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_all - Data Type: u8s8f32 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 2K 4K 6K 8K 10K Min: 2475.39 / Avg: 2479.28 / Max: 2482.46 Min: 4817.98 / Avg: 4826.71 / Max: 4832.8 Min: 2843.64 / Avg: 2846.12 / Max: 2847.53 Min: 1513.64 / Avg: 1517.44 / Max: 1523.62 Min: 5838.56 / Avg: 5840.26 / Max: 5843.39 Min: 6234.77 / Avg: 6241.16 / Max: 6250.73 Min: 4466.85 / Avg: 4478.93 / Max: 4493.36 Min: 2366.63 / Avg: 2377.91 / Max: 2399.24 Min: 3191.41 / Avg: 3215.17 / Max: 3262.6 Min: 2951.08 / Avg: 2967.92 / Max: 2998.05 Min: 2015.56 / Avg: 2023.47 / Max: 2028.08 Min: 1707.25 / Avg: 1708.05 / Max: 1708.54 Min: 11690.8 / Avg: 11728.8 / Max: 11749.1 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Result
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32 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 40 80 120 160 200 SE +/- 0.06, N = 3 SE +/- 0.24, N = 3 SE +/- 0.02, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.17, N = 3 SE +/- 0.01, N = 3 SE +/- 0.19, N = 3 54.82 108.16 42.08 23.18 131.09 171.43 69.14 36.37 87.54 49.87 33.63 25.05 42.54 MIN: 54.08 MIN: 106.43 MIN: 41.31 MIN: 130.56 MIN: 170.75 MIN: 68.48 MIN: 34.65 MIN: 86.64 MIN: 44.78 MIN: 32.49 MIN: 40.72 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl Result Confidence
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32 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 30 60 90 120 150 Min: 54.7 / Avg: 54.82 / Max: 54.9 Min: 107.84 / Avg: 108.16 / Max: 108.62 Min: 42.04 / Avg: 42.08 / Max: 42.1 Min: 23.03 / Avg: 23.18 / Max: 23.35 Min: 131.05 / Avg: 131.09 / Max: 131.15 Min: 171.33 / Avg: 171.43 / Max: 171.54 Min: 69.03 / Avg: 69.14 / Max: 69.27 Min: 36.35 / Avg: 36.37 / Max: 36.39 Min: 87.46 / Avg: 87.54 / Max: 87.61 Min: 49.75 / Avg: 49.87 / Max: 49.99 Min: 33.37 / Avg: 33.63 / Max: 33.95 Min: 25.04 / Avg: 25.05 / Max: 25.08 Min: 42.21 / Avg: 42.54 / Max: 42.87 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Result
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_alexnet - Data Type: u8s8f32 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 300 600 900 1200 1500 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.25, N = 3 SE +/- 0.14, N = 3 SE +/- 0.04, N = 3 SE +/- 0.73, N = 3 SE +/- 0.03, N = 3 SE +/- 2.69, N = 3 35.98 66.74 26.84 19.81 81.07 105.83 42.22 26.54 55.34 31.99 59.90 30.64 1301.36 MIN: 1286.29 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl Result Confidence
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_alexnet - Data Type: u8s8f32 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 200 400 600 800 1000 Min: 35.92 / Avg: 35.98 / Max: 36.02 Min: 66.57 / Avg: 66.74 / Max: 66.89 Min: 26.8 / Avg: 26.84 / Max: 26.88 Min: 19.76 / Avg: 19.81 / Max: 19.86 Min: 81 / Avg: 81.07 / Max: 81.13 Min: 105.74 / Avg: 105.83 / Max: 105.95 Min: 42.21 / Avg: 42.22 / Max: 42.24 Min: 26.05 / Avg: 26.54 / Max: 26.86 Min: 55.17 / Avg: 55.34 / Max: 55.61 Min: 31.94 / Avg: 31.99 / Max: 32.06 Min: 58.62 / Avg: 59.9 / Max: 61.17 Min: 30.58 / Avg: 30.64 / Max: 30.68 Min: 1295.98 / Avg: 1301.36 / Max: 1304.14 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Result
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_3d - Data Type: f32 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 4 6 8 10 SE +/- 0.00092, N = 3 SE +/- 0.01927, N = 3 SE +/- 0.00032, N = 3 SE +/- 0.00373, N = 3 SE +/- 0.01731, N = 3 SE +/- 0.01443, N = 3 SE +/- 0.00634, N = 3 SE +/- 0.00200, N = 3 SE +/- 0.00590, N = 3 SE +/- 0.01801, N = 3 SE +/- 0.00161, N = 3 SE +/- 0.00132, N = 3 SE +/- 0.00603, N = 3 2.69700 4.88966 1.96279 1.13608 5.80420 7.63646 3.13006 1.70749 3.85512 2.27526 1.17385 1.17278 2.20471 MIN: 2.66 MIN: 4.84 MIN: 1.95 MIN: 5.77 MIN: 7.57 MIN: 3.1 MIN: 3.82 MIN: 2.12 MIN: 2.14 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl Result Confidence
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_3d - Data Type: f32 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 3 6 9 12 15 Min: 2.7 / Avg: 2.7 / Max: 2.7 Min: 4.87 / Avg: 4.89 / Max: 4.93 Min: 1.96 / Avg: 1.96 / Max: 1.96 Min: 1.13 / Avg: 1.14 / Max: 1.14 Min: 5.78 / Avg: 5.8 / Max: 5.84 Min: 7.61 / Avg: 7.64 / Max: 7.66 Min: 3.12 / Avg: 3.13 / Max: 3.14 Min: 1.7 / Avg: 1.71 / Max: 1.71 Min: 3.84 / Avg: 3.86 / Max: 3.86 Min: 2.25 / Avg: 2.28 / Max: 2.31 Min: 1.17 / Avg: 1.17 / Max: 1.18 Min: 1.17 / Avg: 1.17 / Max: 1.18 Min: 2.2 / Avg: 2.2 / Max: 2.22 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Result
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_all - Data Type: f32 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 700 1400 2100 2800 3500 SE +/- 0.29, N = 3 SE +/- 1.16, N = 3 SE +/- 0.39, N = 3 SE +/- 0.78, N = 3 SE +/- 0.47, N = 3 SE +/- 1.30, N = 3 SE +/- 0.59, N = 3 SE +/- 0.79, N = 3 SE +/- 1.69, N = 3 SE +/- 0.68, N = 3 SE +/- 7.07, N = 3 SE +/- 5.95, N = 3 SE +/- 2.05, N = 3 999.54 1948.77 765.75 496.82 2363.00 3129.93 1227.07 694.32 1578.24 878.39 1206.22 650.98 710.14 MIN: 995.71 MIN: 1927.2 MIN: 755.35 MIN: 2357.87 MIN: 3085.85 MIN: 1218.34 MIN: 686.24 MIN: 1571.3 MIN: 819.94 MIN: 1181.19 MIN: 639.1 MIN: 700.52 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl Result Confidence
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_all - Data Type: f32 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 500 1000 1500 2000 2500 Min: 999.25 / Avg: 999.54 / Max: 1000.12 Min: 1946.47 / Avg: 1948.77 / Max: 1950.16 Min: 765.14 / Avg: 765.75 / Max: 766.49 Min: 495.3 / Avg: 496.82 / Max: 497.87 Min: 2362.17 / Avg: 2363 / Max: 2363.81 Min: 3127.45 / Avg: 3129.93 / Max: 3131.87 Min: 1226.38 / Avg: 1227.07 / Max: 1228.24 Min: 692.88 / Avg: 694.32 / Max: 695.62 Min: 1575.89 / Avg: 1578.24 / Max: 1581.52 Min: 877.4 / Avg: 878.39 / Max: 879.69 Min: 1192.1 / Avg: 1206.22 / Max: 1214.06 Min: 644.85 / Avg: 650.98 / Max: 662.89 Min: 706.04 / Avg: 710.14 / Max: 712.25 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Result
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_alexnet - Data Type: bf16bf16bf16 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 400 800 1200 1600 2000 SE +/- 0.06, N = 3 SE +/- 1.48, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.15, N = 3 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 SE +/- 4.23, N = 3 SE +/- 0.08, N = 3 SE +/- 1.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.33, N = 3 712.20 1433.47 637.37 320.06 1874.47 1875.23 1042.34 527.02 938.91 702.07 348.24 348.33 MIN: 710.93 MIN: 1421.77 MIN: 636.97 MIN: 319.23 MIN: 1873.87 MIN: 1873.9 MIN: 1041.43 MIN: 521.14 MIN: 937.57 MIN: 687.86 MIN: 346.92 MIN: 347.28 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl Result Confidence
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_alexnet - Data Type: bf16bf16bf16 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 300 600 900 1200 1500 Min: 712.08 / Avg: 712.2 / Max: 712.3 Min: 1430.58 / Avg: 1433.47 / Max: 1435.46 Min: 637.27 / Avg: 637.37 / Max: 637.49 Min: 319.97 / Avg: 320.06 / Max: 320.18 Min: 1874.2 / Avg: 1874.47 / Max: 1874.72 Min: 1875.18 / Avg: 1875.23 / Max: 1875.27 Min: 1042.2 / Avg: 1042.34 / Max: 1042.5 Min: 522.71 / Avg: 527.02 / Max: 535.48 Min: 938.8 / Avg: 938.91 / Max: 939.07 Min: 700.45 / Avg: 702.07 / Max: 704.02 Min: 348.13 / Avg: 348.24 / Max: 348.38 Min: 347.69 / Avg: 348.33 / Max: 348.81 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Result
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_all - Data Type: bf16bf16bf16 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 2K 4K 6K 8K 10K SE +/- 3.93, N = 3 SE +/- 4.68, N = 3 SE +/- 0.26, N = 3 SE +/- 1.13, N = 3 SE +/- 0.34, N = 3 SE +/- 0.35, N = 3 SE +/- 0.12, N = 3 SE +/- 2.73, N = 3 SE +/- 6.81, N = 3 SE +/- 0.11, N = 3 SE +/- 0.16, N = 3 SE +/- 0.26, N = 3 3917.52 7839.95 3497.47 1766.35 10255.20 10258.00 5709.17 2871.11 5156.69 3880.44 1919.50 1918.28 MIN: 3906.67 MIN: 7795.37 MIN: 3490.41 MIN: 10250.1 MIN: 10250.4 MIN: 5699.77 MIN: 2860.81 MIN: 5142.07 MIN: 3767 MIN: 1911.94 MIN: 1911.42 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl Result Confidence
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_all - Data Type: bf16bf16bf16 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 2K 4K 6K 8K 10K Min: 3912.84 / Avg: 3917.52 / Max: 3925.33 Min: 7834.19 / Avg: 7839.95 / Max: 7849.22 Min: 3497.1 / Avg: 3497.47 / Max: 3497.97 Min: 1765.16 / Avg: 1766.35 / Max: 1768.6 Min: 10254.5 / Avg: 10255.17 / Max: 10255.6 Min: 10257.3 / Avg: 10257.97 / Max: 10258.5 Min: 5708.98 / Avg: 5709.17 / Max: 5709.4 Min: 2867.97 / Avg: 2871.11 / Max: 2876.54 Min: 5149.22 / Avg: 5156.69 / Max: 5170.3 Min: 3880.24 / Avg: 3880.44 / Max: 3880.6 Min: 1919.22 / Avg: 1919.5 / Max: 1919.79 Min: 1918.01 / Avg: 1918.28 / Max: 1918.81 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Result
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_googlenet_v3 - Data Type: bf16bf16bf16 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 100 200 300 400 500 SE +/- 0.02, N = 3 SE +/- 0.42, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.10, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.20, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 187.17 369.29 166.98 86.54 484.59 484.90 269.99 137.73 246.45 188.61 93.36 93.28 MIN: 186.33 MIN: 365.68 MIN: 166.21 MIN: 85.56 MIN: 484.13 MIN: 484.15 MIN: 268.99 MIN: 136.67 MIN: 245.49 MIN: 178.56 MIN: 92.35 MIN: 92.44 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl Result Confidence
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_googlenet_v3 - Data Type: bf16bf16bf16 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 90 180 270 360 450 Min: 187.14 / Avg: 187.17 / Max: 187.21 Min: 368.87 / Avg: 369.29 / Max: 370.12 Min: 166.94 / Avg: 166.98 / Max: 167.04 Min: 86.53 / Avg: 86.54 / Max: 86.55 Min: 484.56 / Avg: 484.59 / Max: 484.62 Min: 484.78 / Avg: 484.9 / Max: 485.04 Min: 269.85 / Avg: 269.99 / Max: 270.19 Min: 137.7 / Avg: 137.73 / Max: 137.77 Min: 246.4 / Avg: 246.45 / Max: 246.54 Min: 188.22 / Avg: 188.61 / Max: 188.81 Min: 93.34 / Avg: 93.36 / Max: 93.38 Min: 93.23 / Avg: 93.28 / Max: 93.32 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
Result
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: NASA Streamlines - Renderer: Path Tracer 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 4 8 12 16 20 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.03, N = 3 SE +/- 0.00, N = 12 SE +/- 0.01, N = 3 SE +/- 0.00, N = 15 SE +/- 0.01, N = 4 SE +/- 0.04, N = 3 SE +/- 0.00, N = 12 SE +/- 0.01, N = 12 SE +/- 0.07, N = 4 SE +/- 0.00, N = 12 SE +/- 0.07, N = 4 10.42 5.38 9.49 18.18 4.37 3.41 5.52 10.56 6.62 8.69 17.02 16.95 16.60 MIN: 8.47 / MAX: 10.53 MIN: 5.29 / MAX: 5.46 MIN: 9.26 / MAX: 9.62 MIN: 12.2 / MAX: 18.52 MIN: 4.29 / MAX: 4.44 MIN: 3.33 / MAX: 3.45 MIN: 5.43 / MAX: 5.62 MIN: 8.77 / MAX: 10.75 MIN: 5.52 / MAX: 6.76 MIN: 8.33 / MAX: 9.01 MIN: 11.76 / MAX: 17.54 MIN: 16.13 / MAX: 17.54 MIN: 15.87 / MAX: 16.95 Perf Per Core
OpenBenchmarking.org FPS Per Core, More Is Better OSPray 1.8.5 Performance Per Core - Demo: NASA Streamlines - Renderer: Path Tracer 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 0.0798 0.1596 0.2394 0.3192 0.399 0.2894 0.2989 0.3389 0.3246 0.2731 0.2131 0.3450 0.3300 0.2069 0.3104 0.3546 0.3531 0.3458 1. 2 x Xeon Gold 5220R: Detected core count of 36 2. Xeon Gold 5220R: Detected core count of 18 3. Xeon Platinum 8280: Detected core count of 28 4. 2 x Xeon Platinum 8280: Detected core count of 56 5. Xeon Gold 5218: Detected core count of 16 6. Xeon Silver 4216: Detected core count of 16 7. Xeon Gold 6226R: Detected core count of 16 8. 2 x Xeon Gold 6226R: Detected core count of 32 9. 2 x Xeon Silver 4216: Detected core count of 32 10. Xeon W-3275M: Detected core count of 28 11. 2 x Xeon Platinum 8275CL: Detected core count of 48 12. 2 x Xeon Platinum 8275CL NUMA off: Detected core count of 48 13. EPYC 2 7R32: Detected core count of 48 Perf Per Thread
OpenBenchmarking.org FPS Per Thread, More Is Better OSPray 1.8.5 Performance Per Thread - Demo: NASA Streamlines - Renderer: Path Tracer 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 0.0399 0.0798 0.1197 0.1596 0.1995 0.1447 0.1494 0.1695 0.1623 0.1366 0.1066 0.1725 0.1650 0.1034 0.1552 0.1773 0.1766 0.1729 1. 2 x Xeon Gold 5220R: Detected thread count of 72 2. Xeon Gold 5220R: Detected thread count of 36 3. Xeon Platinum 8280: Detected thread count of 56 4. 2 x Xeon Platinum 8280: Detected thread count of 112 5. Xeon Gold 5218: Detected thread count of 32 6. Xeon Silver 4216: Detected thread count of 32 7. Xeon Gold 6226R: Detected thread count of 32 8. 2 x Xeon Gold 6226R: Detected thread count of 64 9. 2 x Xeon Silver 4216: Detected thread count of 64 10. Xeon W-3275M: Detected thread count of 56 11. 2 x Xeon Platinum 8275CL: Detected thread count of 96 12. 2 x Xeon Platinum 8275CL NUMA off: Detected thread count of 96 13. EPYC 2 7R32: Detected thread count of 96 Perf Per Clock
OpenBenchmarking.org FPS Per GHz, More Is Better OSPray 1.8.5 Performance Per Clock - Demo: NASA Streamlines - Renderer: Path Tracer 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 1.3343 2.6686 4.0029 5.3372 6.6715 2.67 1.38 2.37 4.55 1.12 1.07 1.42 2.71 2.07 1.89 4.36 4.35 5.93 1. 2 x Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 2. Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 3. Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 4. 2 x Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 5. Xeon Gold 5218: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 6. Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 7. Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 8. 2 x Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 9. 2 x Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 10. Xeon W-3275M: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.60 11. 2 x Xeon Platinum 8275CL: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 12. 2 x Xeon Platinum 8275CL NUMA off: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 13. EPYC 2 7R32: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 2.80 Perf Per RAM Channel
OpenBenchmarking.org FPS Per Channel, More Is Better OSPray 1.8.5 Performance Per Memory Channel - Demo: NASA Streamlines - Renderer: Path Tracer 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 EPYC 2 7R32 0.6818 1.3636 2.0454 2.7272 3.409 1.7400 0.8967 1.5800 3.0300 0.7283 0.5683 0.9200 1.7600 1.1000 2.0800 1. 2 x Xeon Gold 5220R: Detected channel count of 6 2. Xeon Gold 5220R: Detected channel count of 6 3. Xeon Platinum 8280: Detected channel count of 6 4. 2 x Xeon Platinum 8280: Detected channel count of 6 5. Xeon Gold 5218: Detected channel count of 6 6. Xeon Silver 4216: Detected channel count of 6 7. Xeon Gold 6226R: Detected channel count of 6 8. 2 x Xeon Gold 6226R: Detected channel count of 6 9. 2 x Xeon Silver 4216: Detected channel count of 6 10. EPYC 2 7R32: Detected channel count of 8 Result Confidence
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: NASA Streamlines - Renderer: Path Tracer 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 5 10 15 20 25 Min: 10.42 / Avg: 10.42 / Max: 10.42 Min: 5.38 / Avg: 5.38 / Max: 5.38 Min: 9.43 / Avg: 9.49 / Max: 9.52 Min: 18.18 / Avg: 18.18 / Max: 18.18 Min: 4.37 / Avg: 4.37 / Max: 4.39 Min: 3.41 / Avg: 3.41 / Max: 3.41 Min: 5.49 / Avg: 5.52 / Max: 5.52 Min: 10.53 / Avg: 10.56 / Max: 10.64 Min: 6.62 / Avg: 6.62 / Max: 6.62 Min: 8.62 / Avg: 8.69 / Max: 8.7 Min: 16.95 / Avg: 17.02 / Max: 17.24 Min: 16.95 / Avg: 16.95 / Max: 16.95 Min: 16.39 / Avg: 16.6 / Max: 16.67
Result
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: XFrog Forest - Renderer: SciVis 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 3 6 9 12 15 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 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 SE +/- 0.00, N = 8 SE +/- 0.00, N = 13 SE +/- 0.00, N = 13 SE +/- 0.04, N = 3 7.19 3.70 6.25 12.05 3.01 2.34 3.68 7.09 4.57 5.72 11.36 11.36 11.03 MIN: 6.45 / MAX: 7.25 MIN: 3.66 / MAX: 3.73 MIN: 6.13 / MAX: 6.29 MIN: 9.71 / MAX: 12.2 MIN: 2.98 / MAX: 3.05 MIN: 2.3 / MAX: 2.36 MIN: 3.64 / MAX: 3.7 MIN: 6.37 / MAX: 7.14 MIN: 4.08 / MAX: 4.61 MIN: 5.56 / MAX: 5.78 MIN: 9.8 / MAX: 11.49 MIN: 10.99 / MAX: 11.49 MIN: 10.75 / MAX: 11.24 Perf Per Core
OpenBenchmarking.org FPS Per Core, More Is Better OSPray 1.8.5 Performance Per Core - Demo: XFrog Forest - Renderer: SciVis 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 0.0533 0.1066 0.1599 0.2132 0.2665 0.1997 0.2056 0.2232 0.2152 0.1881 0.1463 0.2300 0.2216 0.1428 0.2043 0.2367 0.2367 0.2298 1. 2 x Xeon Gold 5220R: Detected core count of 36 2. Xeon Gold 5220R: Detected core count of 18 3. Xeon Platinum 8280: Detected core count of 28 4. 2 x Xeon Platinum 8280: Detected core count of 56 5. Xeon Gold 5218: Detected core count of 16 6. Xeon Silver 4216: Detected core count of 16 7. Xeon Gold 6226R: Detected core count of 16 8. 2 x Xeon Gold 6226R: Detected core count of 32 9. 2 x Xeon Silver 4216: Detected core count of 32 10. Xeon W-3275M: Detected core count of 28 11. 2 x Xeon Platinum 8275CL: Detected core count of 48 12. 2 x Xeon Platinum 8275CL NUMA off: Detected core count of 48 13. EPYC 2 7R32: Detected core count of 48 Perf Per Thread
OpenBenchmarking.org FPS Per Thread, More Is Better OSPray 1.8.5 Performance Per Thread - Demo: XFrog Forest - Renderer: SciVis 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 0.0266 0.0532 0.0798 0.1064 0.133 0.0999 0.1028 0.1116 0.1076 0.0941 0.0731 0.1150 0.1108 0.0714 0.1021 0.1183 0.1183 0.1149 1. 2 x Xeon Gold 5220R: Detected thread count of 72 2. Xeon Gold 5220R: Detected thread count of 36 3. Xeon Platinum 8280: Detected thread count of 56 4. 2 x Xeon Platinum 8280: Detected thread count of 112 5. Xeon Gold 5218: Detected thread count of 32 6. Xeon Silver 4216: Detected thread count of 32 7. Xeon Gold 6226R: Detected thread count of 32 8. 2 x Xeon Gold 6226R: Detected thread count of 64 9. 2 x Xeon Silver 4216: Detected thread count of 64 10. Xeon W-3275M: Detected thread count of 56 11. 2 x Xeon Platinum 8275CL: Detected thread count of 96 12. 2 x Xeon Platinum 8275CL NUMA off: Detected thread count of 96 13. EPYC 2 7R32: Detected thread count of 96 Perf Per Clock
OpenBenchmarking.org FPS Per GHz, More Is Better OSPray 1.8.5 Performance Per Clock - Demo: XFrog Forest - Renderer: SciVis 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 0.8865 1.773 2.6595 3.546 4.4325 1.8400 0.9487 1.5600 3.0100 0.7718 0.7313 0.9436 1.8200 1.4300 1.2400 2.9100 2.9100 3.9400 1. 2 x Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 2. Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 3. Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 4. 2 x Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 5. Xeon Gold 5218: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 6. Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 7. Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 8. 2 x Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 9. 2 x Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 10. Xeon W-3275M: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.60 11. 2 x Xeon Platinum 8275CL: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 12. 2 x Xeon Platinum 8275CL NUMA off: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 13. EPYC 2 7R32: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 2.80 Perf Per RAM Channel
OpenBenchmarking.org FPS Per Channel, More Is Better OSPray 1.8.5 Performance Per Memory Channel - Demo: XFrog Forest - Renderer: SciVis 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 EPYC 2 7R32 0.4523 0.9046 1.3569 1.8092 2.2615 1.2000 0.6167 1.0400 2.0100 0.5017 0.3900 0.6133 1.1800 0.7617 1.3800 1. 2 x Xeon Gold 5220R: Detected channel count of 6 2. Xeon Gold 5220R: Detected channel count of 6 3. Xeon Platinum 8280: Detected channel count of 6 4. 2 x Xeon Platinum 8280: Detected channel count of 6 5. Xeon Gold 5218: Detected channel count of 6 6. Xeon Silver 4216: Detected channel count of 6 7. Xeon Gold 6226R: Detected channel count of 6 8. 2 x Xeon Gold 6226R: Detected channel count of 6 9. 2 x Xeon Silver 4216: Detected channel count of 6 10. EPYC 2 7R32: Detected channel count of 8 Result Confidence
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: XFrog Forest - Renderer: SciVis 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 4 8 12 16 20 Min: 7.19 / Avg: 7.19 / Max: 7.19 Min: 3.69 / Avg: 3.7 / Max: 3.7 Min: 6.25 / Avg: 6.25 / Max: 6.25 Min: 12.05 / Avg: 12.05 / Max: 12.05 Min: 3.01 / Avg: 3.01 / Max: 3.01 Min: 2.34 / Avg: 2.34 / Max: 2.34 Min: 3.68 / Avg: 3.68 / Max: 3.68 Min: 7.09 / Avg: 7.09 / Max: 7.09 Min: 4.57 / Avg: 4.57 / Max: 4.57 Min: 5.71 / Avg: 5.72 / Max: 5.75 Min: 11.36 / Avg: 11.36 / Max: 11.36 Min: 11.36 / Avg: 11.36 / Max: 11.36 Min: 10.99 / Avg: 11.03 / Max: 11.11
Result
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: XFrog Forest - Renderer: Path Tracer 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 4 6 8 10 SE +/- 0.00, N = 12 SE +/- 0.00, N = 6 SE +/- 0.00, N = 4 SE +/- 0.00, N = 12 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 12 SE +/- 0.00, N = 5 SE +/- 0.00, N = 7 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 3.98 2.06 3.46 6.67 1.68 1.31 2.02 3.88 2.55 3.17 6.25 6.24 5.85 MIN: 3.64 / MAX: 4.02 MIN: 2.04 / MAX: 2.07 MIN: 3.41 / MAX: 3.47 MIN: 5.85 / MAX: 6.76 MIN: 1.67 MIN: 1.3 / MAX: 1.32 MIN: 2 / MAX: 2.04 MIN: 3.57 / MAX: 3.92 MIN: 2.28 / MAX: 2.57 MIN: 3.09 / MAX: 3.19 MIN: 5.68 / MAX: 6.29 MIN: 6.1 / MAX: 6.29 MIN: 5.65 / MAX: 5.99 Perf Per Core
OpenBenchmarking.org FPS Per Core, More Is Better OSPray 1.8.5 Performance Per Core - Demo: XFrog Forest - Renderer: Path Tracer 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 0.0293 0.0586 0.0879 0.1172 0.1465 0.1106 0.1144 0.1236 0.1191 0.1050 0.0819 0.1263 0.1213 0.0797 0.1132 0.1302 0.1300 0.1219 1. 2 x Xeon Gold 5220R: Detected core count of 36 2. Xeon Gold 5220R: Detected core count of 18 3. Xeon Platinum 8280: Detected core count of 28 4. 2 x Xeon Platinum 8280: Detected core count of 56 5. Xeon Gold 5218: Detected core count of 16 6. Xeon Silver 4216: Detected core count of 16 7. Xeon Gold 6226R: Detected core count of 16 8. 2 x Xeon Gold 6226R: Detected core count of 32 9. 2 x Xeon Silver 4216: Detected core count of 32 10. Xeon W-3275M: Detected core count of 28 11. 2 x Xeon Platinum 8275CL: Detected core count of 48 12. 2 x Xeon Platinum 8275CL NUMA off: Detected core count of 48 13. EPYC 2 7R32: Detected core count of 48 Perf Per Thread
OpenBenchmarking.org FPS Per Thread, More Is Better OSPray 1.8.5 Performance Per Thread - Demo: XFrog Forest - Renderer: Path Tracer 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 0.0146 0.0292 0.0438 0.0584 0.073 0.0553 0.0572 0.0618 0.0596 0.0525 0.0409 0.0631 0.0606 0.0398 0.0566 0.0651 0.0650 0.0609 1. 2 x Xeon Gold 5220R: Detected thread count of 72 2. Xeon Gold 5220R: Detected thread count of 36 3. Xeon Platinum 8280: Detected thread count of 56 4. 2 x Xeon Platinum 8280: Detected thread count of 112 5. Xeon Gold 5218: Detected thread count of 32 6. Xeon Silver 4216: Detected thread count of 32 7. Xeon Gold 6226R: Detected thread count of 32 8. 2 x Xeon Gold 6226R: Detected thread count of 64 9. 2 x Xeon Silver 4216: Detected thread count of 64 10. Xeon W-3275M: Detected thread count of 56 11. 2 x Xeon Platinum 8275CL: Detected thread count of 96 12. 2 x Xeon Platinum 8275CL NUMA off: Detected thread count of 96 13. EPYC 2 7R32: Detected thread count of 96 Perf Per Clock
OpenBenchmarking.org FPS Per GHz, More Is Better OSPray 1.8.5 Performance Per Clock - Demo: XFrog Forest - Renderer: Path Tracer 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 0.4703 0.9406 1.4109 1.8812 2.3515 1.0200 0.5282 0.8650 1.6700 0.4308 0.4094 0.5179 0.9949 0.7969 0.6891 1.6000 1.6000 2.0900 1. 2 x Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 2. Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 3. Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 4. 2 x Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 5. Xeon Gold 5218: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 6. Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 7. Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 8. 2 x Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 9. 2 x Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 10. Xeon W-3275M: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.60 11. 2 x Xeon Platinum 8275CL: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 12. 2 x Xeon Platinum 8275CL NUMA off: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 13. EPYC 2 7R32: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 2.80 Perf Per RAM Channel
OpenBenchmarking.org FPS Per Channel, More Is Better OSPray 1.8.5 Performance Per Memory Channel - Demo: XFrog Forest - Renderer: Path Tracer 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 EPYC 2 7R32 0.2498 0.4996 0.7494 0.9992 1.249 0.6633 0.3433 0.5767 1.1100 0.2800 0.2183 0.3367 0.6467 0.4250 0.7313 1. 2 x Xeon Gold 5220R: Detected channel count of 6 2. Xeon Gold 5220R: Detected channel count of 6 3. Xeon Platinum 8280: Detected channel count of 6 4. 2 x Xeon Platinum 8280: Detected channel count of 6 5. Xeon Gold 5218: Detected channel count of 6 6. Xeon Silver 4216: Detected channel count of 6 7. Xeon Gold 6226R: Detected channel count of 6 8. 2 x Xeon Gold 6226R: Detected channel count of 6 9. 2 x Xeon Silver 4216: Detected channel count of 6 10. EPYC 2 7R32: Detected channel count of 8 Result Confidence
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: XFrog Forest - Renderer: Path Tracer 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 3 6 9 12 15 Min: 3.98 / Avg: 3.98 / Max: 3.98 Min: 2.05 / Avg: 2.06 / Max: 2.06 Min: 3.45 / Avg: 3.46 / Max: 3.46 Min: 6.67 / Avg: 6.67 / Max: 6.67 Min: 1.68 / Avg: 1.68 / Max: 1.68 Min: 1.31 / Avg: 1.31 / Max: 1.31 Min: 2.02 / Avg: 2.02 / Max: 2.02 Min: 3.88 / Avg: 3.88 / Max: 3.88 Min: 2.55 / Avg: 2.55 / Max: 2.56 Min: 3.16 / Avg: 3.17 / Max: 3.17 Min: 6.25 / Avg: 6.25 / Max: 6.25 Min: 6.21 / Avg: 6.24 / Max: 6.25 Min: 5.81 / Avg: 5.85 / Max: 5.88
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
Result
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_3d - Data Type: bf16bf16bf16 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 9 18 27 36 45 SE +/- 0.00301, N = 3 SE +/- 0.01559, N = 3 SE +/- 0.00390, N = 3 SE +/- 0.00328, N = 3 SE +/- 0.00339, N = 3 SE +/- 0.00904, N = 3 SE +/- 0.00584, N = 3 SE +/- 0.00770, N = 3 SE +/- 0.00466, N = 3 SE +/- 0.24390, N = 4 SE +/- 0.00882, N = 3 SE +/- 0.00469, N = 3 15.21770 29.91730 14.07800 7.92912 39.99850 40.01920 22.42430 11.60760 20.51630 16.59060 8.71234 8.64707 MIN: 15.05 MIN: 29.42 MIN: 13.95 MIN: 39.89 MIN: 39.9 MIN: 22.32 MIN: 11.46 MIN: 20.35 MIN: 14.98 MIN: 8.5 MIN: 8.43 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl Result Confidence
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_3d - Data Type: bf16bf16bf16 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 8 16 24 32 40 Min: 15.21 / Avg: 15.22 / Max: 15.22 Min: 29.89 / Avg: 29.92 / Max: 29.94 Min: 14.07 / Avg: 14.08 / Max: 14.08 Min: 7.92 / Avg: 7.93 / Max: 7.93 Min: 39.99 / Avg: 40 / Max: 40.01 Min: 40.01 / Avg: 40.02 / Max: 40.04 Min: 22.41 / Avg: 22.42 / Max: 22.43 Min: 11.59 / Avg: 11.61 / Max: 11.62 Min: 20.51 / Avg: 20.52 / Max: 20.52 Min: 16.33 / Avg: 16.59 / Max: 17.32 Min: 8.7 / Avg: 8.71 / Max: 8.73 Min: 8.64 / Avg: 8.65 / Max: 8.66 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
Result
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: NASA Streamlines - Renderer: SciVis 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 20 40 60 80 100 SE +/- 0.00, N = 15 SE +/- 0.00, N = 12 SE +/- 0.00, N = 13 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 15 SE +/- 0.00, N = 12 SE +/- 0.00, N = 3 SE +/- 0.71, N = 9 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 55.56 28.57 50.00 90.91 23.26 18.18 29.41 55.56 34.48 45.45 82.62 83.33 76.92 MIN: 24.39 MIN: 26.32 / MAX: 29.41 MIN: 43.48 MIN: 29.41 MIN: 22.73 / MAX: 23.81 MIN: 17.86 / MAX: 18.52 MIN: 26.32 MIN: 19.23 MIN: 18.87 / MAX: 35.71 MIN: 43.48 / MAX: 47.62 MIN: 26.32 / MAX: 90.91 MIN: 71.43 / MAX: 90.91 MIN: 71.43 / MAX: 83.33 Perf Per Core
OpenBenchmarking.org FPS Per Core, More Is Better OSPray 1.8.5 Performance Per Core - Demo: NASA Streamlines - Renderer: SciVis 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 0.414 0.828 1.242 1.656 2.07 1.54 1.59 1.79 1.62 1.45 1.14 1.84 1.74 1.08 1.62 1.72 1.74 1.60 1. 2 x Xeon Gold 5220R: Detected core count of 36 2. Xeon Gold 5220R: Detected core count of 18 3. Xeon Platinum 8280: Detected core count of 28 4. 2 x Xeon Platinum 8280: Detected core count of 56 5. Xeon Gold 5218: Detected core count of 16 6. Xeon Silver 4216: Detected core count of 16 7. Xeon Gold 6226R: Detected core count of 16 8. 2 x Xeon Gold 6226R: Detected core count of 32 9. 2 x Xeon Silver 4216: Detected core count of 32 10. Xeon W-3275M: Detected core count of 28 11. 2 x Xeon Platinum 8275CL: Detected core count of 48 12. 2 x Xeon Platinum 8275CL NUMA off: Detected core count of 48 13. EPYC 2 7R32: Detected core count of 48 Perf Per Thread
OpenBenchmarking.org FPS Per Thread, More Is Better OSPray 1.8.5 Performance Per Thread - Demo: NASA Streamlines - Renderer: SciVis 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 0.2068 0.4136 0.6204 0.8272 1.034 0.7717 0.7936 0.8929 0.8117 0.7269 0.5681 0.9191 0.8681 0.5388 0.8116 0.8606 0.8680 0.8013 1. 2 x Xeon Gold 5220R: Detected thread count of 72 2. Xeon Gold 5220R: Detected thread count of 36 3. Xeon Platinum 8280: Detected thread count of 56 4. 2 x Xeon Platinum 8280: Detected thread count of 112 5. Xeon Gold 5218: Detected thread count of 32 6. Xeon Silver 4216: Detected thread count of 32 7. Xeon Gold 6226R: Detected thread count of 32 8. 2 x Xeon Gold 6226R: Detected thread count of 64 9. 2 x Xeon Silver 4216: Detected thread count of 64 10. Xeon W-3275M: Detected thread count of 56 11. 2 x Xeon Platinum 8275CL: Detected thread count of 96 12. 2 x Xeon Platinum 8275CL NUMA off: Detected thread count of 96 13. EPYC 2 7R32: Detected thread count of 96 Perf Per Clock
OpenBenchmarking.org FPS Per GHz, More Is Better OSPray 1.8.5 Performance Per Clock - Demo: NASA Streamlines - Renderer: SciVis 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 6 12 18 24 30 14.25 7.33 12.50 22.73 5.96 5.68 7.54 14.25 10.78 9.88 21.18 21.37 27.47 1. 2 x Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 2. Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 3. Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 4. 2 x Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 5. Xeon Gold 5218: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 6. Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 7. Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 8. 2 x Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 9. 2 x Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 10. Xeon W-3275M: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.60 11. 2 x Xeon Platinum 8275CL: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 12. 2 x Xeon Platinum 8275CL NUMA off: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 13. EPYC 2 7R32: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 2.80 Perf Per RAM Channel
OpenBenchmarking.org FPS Per Channel, More Is Better OSPray 1.8.5 Performance Per Memory Channel - Demo: NASA Streamlines - Renderer: SciVis 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 EPYC 2 7R32 4 8 12 16 20 9.26 4.76 8.33 15.15 3.88 3.03 4.90 9.26 5.75 9.62 1. 2 x Xeon Gold 5220R: Detected channel count of 6 2. Xeon Gold 5220R: Detected channel count of 6 3. Xeon Platinum 8280: Detected channel count of 6 4. 2 x Xeon Platinum 8280: Detected channel count of 6 5. Xeon Gold 5218: Detected channel count of 6 6. Xeon Silver 4216: Detected channel count of 6 7. Xeon Gold 6226R: Detected channel count of 6 8. 2 x Xeon Gold 6226R: Detected channel count of 6 9. 2 x Xeon Silver 4216: Detected channel count of 6 10. EPYC 2 7R32: Detected channel count of 8 Result Confidence
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: NASA Streamlines - Renderer: SciVis 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 20 40 60 80 100 Min: 55.56 / Avg: 55.56 / Max: 55.56 Min: 28.57 / Avg: 28.57 / Max: 28.57 Min: 90.91 / Avg: 90.91 / Max: 90.91 Min: 23.26 / Avg: 23.26 / Max: 23.26 Min: 18.18 / Avg: 18.18 / Max: 18.18 Min: 29.41 / Avg: 29.41 / Max: 29.41 Min: 55.56 / Avg: 55.56 / Max: 55.56 Min: 34.48 / Avg: 34.48 / Max: 34.48 Min: 45.45 / Avg: 45.45 / Max: 45.45 Min: 76.92 / Avg: 82.62 / Max: 83.33 Min: 83.33 / Avg: 83.33 / Max: 83.33 Min: 76.92 / Avg: 76.92 / Max: 76.92
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
Result
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch All - Data Type: u8s8f32 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 30 60 90 120 150 SE +/- 0.03777, N = 3 SE +/- 0.02448, N = 3 SE +/- 0.00398, N = 3 SE +/- 0.04146, N = 4 SE +/- 0.00870, N = 3 SE +/- 0.03131, N = 3 SE +/- 0.01160, N = 3 SE +/- 0.03959, N = 3 SE +/- 0.04012, N = 3 SE +/- 0.03226, N = 3 SE +/- 0.06319, N = 3 SE +/- 0.01731, N = 3 SE +/- 0.23997, N = 3 4.08605 4.61054 3.23121 3.11002 4.83875 5.59275 4.53821 4.11779 4.82603 3.59218 5.36708 3.84746 149.33900 MIN: 144.74 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl Result Confidence
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch All - Data Type: u8s8f32 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 30 60 90 120 150 Min: 4.01 / Avg: 4.09 / Max: 4.14 Min: 4.56 / Avg: 4.61 / Max: 4.64 Min: 3.23 / Avg: 3.23 / Max: 3.24 Min: 3 / Avg: 3.11 / Max: 3.2 Min: 4.82 / Avg: 4.84 / Max: 4.85 Min: 5.53 / Avg: 5.59 / Max: 5.64 Min: 4.52 / Avg: 4.54 / Max: 4.56 Min: 4.06 / Avg: 4.12 / Max: 4.19 Min: 4.76 / Avg: 4.83 / Max: 4.89 Min: 3.53 / Avg: 3.59 / Max: 3.63 Min: 5.3 / Avg: 5.37 / Max: 5.49 Min: 3.81 / Avg: 3.85 / Max: 3.87 Min: 148.88 / Avg: 149.34 / Max: 149.7 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Result
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_3d - Data Type: bf16bf16bf16 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 5 10 15 20 25 SE +/- 0.01392, N = 3 SE +/- 0.00134, N = 3 SE +/- 0.00251, N = 3 SE +/- 0.00369, N = 3 SE +/- 0.05476, N = 3 SE +/- 0.02388, N = 3 SE +/- 0.00297, N = 3 SE +/- 0.00159, N = 3 SE +/- 0.00821, N = 3 SE +/- 0.03985, N = 3 SE +/- 0.01549, N = 3 SE +/- 0.00222, N = 3 9.42591 16.82530 7.69605 4.35817 21.42900 21.47550 12.32710 6.29647 10.93790 8.46273 4.37952 4.36002 MIN: 9.32 MIN: 16.72 MIN: 7.67 MIN: 21.29 MIN: 21.24 MIN: 12.27 MIN: 6.25 MIN: 10.86 MIN: 8.21 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl Result Confidence
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_3d - Data Type: bf16bf16bf16 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 5 10 15 20 25 Min: 9.4 / Avg: 9.43 / Max: 9.45 Min: 16.82 / Avg: 16.83 / Max: 16.83 Min: 7.69 / Avg: 7.7 / Max: 7.7 Min: 4.35 / Avg: 4.36 / Max: 4.36 Min: 21.37 / Avg: 21.43 / Max: 21.54 Min: 21.44 / Avg: 21.48 / Max: 21.52 Min: 12.32 / Avg: 12.33 / Max: 12.33 Min: 6.29 / Avg: 6.3 / Max: 6.3 Min: 10.92 / Avg: 10.94 / Max: 10.95 Min: 8.39 / Avg: 8.46 / Max: 8.53 Min: 4.36 / Avg: 4.38 / Max: 4.41 Min: 4.36 / Avg: 4.36 / Max: 4.36 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
Result
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: SciVis 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 15 30 45 60 75 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.62, N = 15 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.04, N = 12 SE +/- 0.60, N = 3 SE +/- 0.07, N = 12 SE +/- 0.00, N = 12 SE +/- 0.54, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 43.48 23.26 38.46 69.52 18.87 14.71 22.69 42.27 27.84 34.48 63.54 66.67 58.82 MIN: 28.57 / MAX: 45.45 MIN: 21.74 / MAX: 23.81 MIN: 37.04 MIN: 37.04 / MAX: 71.43 MIN: 18.52 / MAX: 19.23 MIN: 14.29 / MAX: 14.93 MIN: 21.74 / MAX: 22.73 MIN: 28.57 / MAX: 43.48 MIN: 17.86 / MAX: 28.57 MIN: 30.3 / MAX: 35.71 MIN: 35.71 / MAX: 66.67 MIN: 55.56 MIN: 52.63 / MAX: 62.5 Perf Per Core
OpenBenchmarking.org FPS Per Core, More Is Better OSPray 1.8.5 Performance Per Core - Demo: San Miguel - Renderer: SciVis 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 0.3195 0.639 0.9585 1.278 1.5975 1.2100 1.2900 1.3700 1.2400 1.1800 0.9194 1.4200 1.3200 0.8700 1.2300 1.3200 1.3900 1.2300 1. 2 x Xeon Gold 5220R: Detected core count of 36 2. Xeon Gold 5220R: Detected core count of 18 3. Xeon Platinum 8280: Detected core count of 28 4. 2 x Xeon Platinum 8280: Detected core count of 56 5. Xeon Gold 5218: Detected core count of 16 6. Xeon Silver 4216: Detected core count of 16 7. Xeon Gold 6226R: Detected core count of 16 8. 2 x Xeon Gold 6226R: Detected core count of 32 9. 2 x Xeon Silver 4216: Detected core count of 32 10. Xeon W-3275M: Detected core count of 28 11. 2 x Xeon Platinum 8275CL: Detected core count of 48 12. 2 x Xeon Platinum 8275CL NUMA off: Detected core count of 48 13. EPYC 2 7R32: Detected core count of 48 Perf Per Thread
OpenBenchmarking.org FPS Per Thread, More Is Better OSPray 1.8.5 Performance Per Thread - Demo: San Miguel - Renderer: SciVis 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 0.1595 0.319 0.4785 0.638 0.7975 0.6039 0.6461 0.6868 0.6207 0.5897 0.4597 0.7091 0.6605 0.4350 0.6157 0.6619 0.6945 0.6127 1. 2 x Xeon Gold 5220R: Detected thread count of 72 2. Xeon Gold 5220R: Detected thread count of 36 3. Xeon Platinum 8280: Detected thread count of 56 4. 2 x Xeon Platinum 8280: Detected thread count of 112 5. Xeon Gold 5218: Detected thread count of 32 6. Xeon Silver 4216: Detected thread count of 32 7. Xeon Gold 6226R: Detected thread count of 32 8. 2 x Xeon Gold 6226R: Detected thread count of 64 9. 2 x Xeon Silver 4216: Detected thread count of 64 10. Xeon W-3275M: Detected thread count of 56 11. 2 x Xeon Platinum 8275CL: Detected thread count of 96 12. 2 x Xeon Platinum 8275CL NUMA off: Detected thread count of 96 13. EPYC 2 7R32: Detected thread count of 96 Perf Per Clock
OpenBenchmarking.org FPS Per GHz, More Is Better OSPray 1.8.5 Performance Per Clock - Demo: San Miguel - Renderer: SciVis 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 5 10 15 20 25 11.15 5.96 9.62 17.38 4.84 4.60 5.82 10.84 8.70 7.50 16.29 17.09 21.01 1. 2 x Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 2. Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 3. Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 4. 2 x Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 5. Xeon Gold 5218: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 6. Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 7. Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 8. 2 x Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 9. 2 x Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 10. Xeon W-3275M: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.60 11. 2 x Xeon Platinum 8275CL: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 12. 2 x Xeon Platinum 8275CL NUMA off: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 13. EPYC 2 7R32: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 2.80 Perf Per RAM Channel
OpenBenchmarking.org FPS Per Channel, More Is Better OSPray 1.8.5 Performance Per Memory Channel - Demo: San Miguel - Renderer: SciVis 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 EPYC 2 7R32 3 6 9 12 15 7.25 3.88 6.41 11.59 3.15 2.45 3.78 7.05 4.64 7.35 1. 2 x Xeon Gold 5220R: Detected channel count of 6 2. Xeon Gold 5220R: Detected channel count of 6 3. Xeon Platinum 8280: Detected channel count of 6 4. 2 x Xeon Platinum 8280: Detected channel count of 6 5. Xeon Gold 5218: Detected channel count of 6 6. Xeon Silver 4216: Detected channel count of 6 7. Xeon Gold 6226R: Detected channel count of 6 8. 2 x Xeon Gold 6226R: Detected channel count of 6 9. 2 x Xeon Silver 4216: Detected channel count of 6 10. EPYC 2 7R32: Detected channel count of 8 Result Confidence
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: SciVis 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 13 26 39 52 65 Min: 43.48 / Avg: 43.48 / Max: 43.48 Min: 23.26 / Avg: 23.26 / Max: 23.26 Min: 38.46 / Avg: 38.46 / Max: 38.46 Min: 66.67 / Avg: 69.52 / Max: 71.43 Min: 18.87 / Avg: 18.87 / Max: 18.87 Min: 14.71 / Avg: 14.71 / Max: 14.71 Min: 22.22 / Avg: 22.69 / Max: 22.73 Min: 41.67 / Avg: 42.27 / Max: 43.48 Min: 27.78 / Avg: 27.84 / Max: 28.57 Min: 34.48 / Avg: 34.48 / Max: 34.48 Min: 62.5 / Avg: 63.54 / Max: 66.67 Min: 66.67 / Avg: 66.67 / Max: 66.67 Min: 58.82 / Avg: 58.82 / Max: 58.82
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page
Result
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer ISPC - Model: Crown 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 12 24 36 48 60 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.49, N = 12 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 33.45 17.66 28.77 53.23 14.42 11.38 16.81 31.73 21.75 26.40 49.05 49.96 45.19 MIN: 32.87 / MAX: 34.13 MIN: 17.5 / MAX: 17.85 MIN: 28.26 / MAX: 29.24 MIN: 51.36 / MAX: 55.83 MIN: 14.3 / MAX: 14.63 MIN: 11.32 / MAX: 11.49 MIN: 16.67 / MAX: 17 MIN: 31.27 / MAX: 32.36 MIN: 21.43 / MAX: 22.13 MIN: 25.71 / MAX: 26.95 MIN: 37.93 / MAX: 51.79 MIN: 48.68 / MAX: 51.86 MIN: 44.15 / MAX: 46.52 Result Confidence
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer ISPC - Model: Crown 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 11 22 33 44 55 Min: 33.41 / Avg: 33.45 / Max: 33.48 Min: 17.65 / Avg: 17.66 / Max: 17.67 Min: 28.75 / Avg: 28.77 / Max: 28.8 Min: 53.18 / Avg: 53.23 / Max: 53.32 Min: 14.4 / Avg: 14.42 / Max: 14.43 Min: 11.38 / Avg: 11.38 / Max: 11.39 Min: 16.78 / Avg: 16.81 / Max: 16.84 Min: 31.68 / Avg: 31.73 / Max: 31.78 Min: 21.73 / Avg: 21.75 / Max: 21.76 Min: 26.36 / Avg: 26.4 / Max: 26.48 Min: 43.85 / Avg: 49.05 / Max: 49.92 Min: 49.93 / Avg: 49.96 / Max: 50.01 Min: 45.07 / Avg: 45.19 / Max: 45.32
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
Result
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: Path Tracer 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 4 6 8 10 SE +/- 0.00, N = 7 SE +/- 0.00, N = 4 SE +/- 0.00, N = 3 SE +/- 0.01, N = 5 SE +/- 0.00, N = 6 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 8 SE +/- 0.00, N = 4 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.01, N = 4 SE +/- 0.01, N = 3 3.95 2.14 3.52 6.53 1.75 1.40 2.02 3.71 2.63 3.25 5.82 5.87 4.73 MIN: 3.41 / MAX: 3.98 MIN: 2.13 / MAX: 2.15 MIN: 3.48 / MAX: 3.53 MIN: 5.18 / MAX: 6.58 MIN: 1.74 / MAX: 1.76 MAX: 1.41 MAX: 2.03 MIN: 2.99 / MAX: 3.73 MIN: 2.35 / MAX: 2.64 MIN: 3.16 / MAX: 3.28 MIN: 4.69 / MAX: 5.88 MIN: 5.75 / MAX: 5.92 MIN: 4.69 / MAX: 4.78 Perf Per Core
OpenBenchmarking.org FPS Per Core, More Is Better OSPray 1.8.5 Performance Per Core - Demo: San Miguel - Renderer: Path Tracer 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 0.0284 0.0568 0.0852 0.1136 0.142 0.1097 0.1189 0.1257 0.1166 0.1094 0.0875 0.1263 0.1159 0.0822 0.1161 0.1213 0.1223 0.0985 1. 2 x Xeon Gold 5220R: Detected core count of 36 2. Xeon Gold 5220R: Detected core count of 18 3. Xeon Platinum 8280: Detected core count of 28 4. 2 x Xeon Platinum 8280: Detected core count of 56 5. Xeon Gold 5218: Detected core count of 16 6. Xeon Silver 4216: Detected core count of 16 7. Xeon Gold 6226R: Detected core count of 16 8. 2 x Xeon Gold 6226R: Detected core count of 32 9. 2 x Xeon Silver 4216: Detected core count of 32 10. Xeon W-3275M: Detected core count of 28 11. 2 x Xeon Platinum 8275CL: Detected core count of 48 12. 2 x Xeon Platinum 8275CL NUMA off: Detected core count of 48 13. EPYC 2 7R32: Detected core count of 48 Perf Per Thread
OpenBenchmarking.org FPS Per Thread, More Is Better OSPray 1.8.5 Performance Per Thread - Demo: San Miguel - Renderer: Path Tracer 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 0.0142 0.0284 0.0426 0.0568 0.071 0.0549 0.0594 0.0629 0.0583 0.0547 0.0438 0.0631 0.0580 0.0411 0.0580 0.0606 0.0611 0.0493 1. 2 x Xeon Gold 5220R: Detected thread count of 72 2. Xeon Gold 5220R: Detected thread count of 36 3. Xeon Platinum 8280: Detected thread count of 56 4. 2 x Xeon Platinum 8280: Detected thread count of 112 5. Xeon Gold 5218: Detected thread count of 32 6. Xeon Silver 4216: Detected thread count of 32 7. Xeon Gold 6226R: Detected thread count of 32 8. 2 x Xeon Gold 6226R: Detected thread count of 64 9. 2 x Xeon Silver 4216: Detected thread count of 64 10. Xeon W-3275M: Detected thread count of 56 11. 2 x Xeon Platinum 8275CL: Detected thread count of 96 12. 2 x Xeon Platinum 8275CL NUMA off: Detected thread count of 96 13. EPYC 2 7R32: Detected thread count of 96 Perf Per Clock
OpenBenchmarking.org FPS Per GHz, More Is Better OSPray 1.8.5 Performance Per Clock - Demo: San Miguel - Renderer: Path Tracer 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 0.3803 0.7606 1.1409 1.5212 1.9015 1.0100 0.5487 0.8800 1.6300 0.4487 0.4375 0.5179 0.9513 0.8219 0.7065 1.4900 1.5100 1.6900 1. 2 x Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 2. Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 3. Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 4. 2 x Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 5. Xeon Gold 5218: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 6. Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 7. Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 8. 2 x Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 9. 2 x Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 10. Xeon W-3275M: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.60 11. 2 x Xeon Platinum 8275CL: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 12. 2 x Xeon Platinum 8275CL NUMA off: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 13. EPYC 2 7R32: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 2.80 Perf Per RAM Channel
OpenBenchmarking.org FPS Per Channel, More Is Better OSPray 1.8.5 Performance Per Memory Channel - Demo: San Miguel - Renderer: Path Tracer 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 EPYC 2 7R32 0.2453 0.4906 0.7359 0.9812 1.2265 0.6583 0.3567 0.5867 1.0900 0.2917 0.2333 0.3367 0.6183 0.4383 0.5913 1. 2 x Xeon Gold 5220R: Detected channel count of 6 2. Xeon Gold 5220R: Detected channel count of 6 3. Xeon Platinum 8280: Detected channel count of 6 4. 2 x Xeon Platinum 8280: Detected channel count of 6 5. Xeon Gold 5218: Detected channel count of 6 6. Xeon Silver 4216: Detected channel count of 6 7. Xeon Gold 6226R: Detected channel count of 6 8. 2 x Xeon Gold 6226R: Detected channel count of 6 9. 2 x Xeon Silver 4216: Detected channel count of 6 10. EPYC 2 7R32: Detected channel count of 8 Result Confidence
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: Path Tracer 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 3 6 9 12 15 Min: 3.95 / Avg: 3.95 / Max: 3.97 Min: 2.14 / Avg: 2.14 / Max: 2.14 Min: 3.51 / Avg: 3.52 / Max: 3.52 Min: 6.49 / Avg: 6.53 / Max: 6.54 Min: 1.75 / Avg: 1.75 / Max: 1.75 Min: 1.4 / Avg: 1.4 / Max: 1.4 Min: 2.02 / Avg: 2.02 / Max: 2.02 Min: 3.7 / Avg: 3.71 / Max: 3.72 Min: 2.62 / Avg: 2.63 / Max: 2.63 Min: 3.25 / Avg: 3.25 / Max: 3.26 Min: 5.81 / Avg: 5.82 / Max: 5.85 Min: 5.85 / Avg: 5.87 / Max: 5.88 Min: 4.72 / Avg: 4.73 / Max: 4.74
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
Result
OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 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 7 14 21 28 35 SE +/- 0.15366, N = 3 SE +/- 0.08231, N = 3 SE +/- 0.04073, N = 3 SE +/- 0.24605, N = 3 SE +/- 0.01417, N = 3 SE +/- 0.03282, N = 3 SE +/- 0.02780, N = 3 SE +/- 0.12533, N = 3 SE +/- 0.00847, N = 3 SE +/- 0.15186, N = 3 SE +/- 0.60187, N = 9 SE +/- 0.06827, N = 7 SE +/- 0.00395, N = 3 25.63030 13.35290 14.90970 28.85420 13.01380 11.88830 13.95810 26.59100 23.15740 14.16230 8.41405 6.32971 17.06080 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi Perf Per Core
OpenBenchmarking.org GFLOP/s Per Core, More Is Better High Performance Conjugate Gradient 3.1 Performance Per Core 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 0.1963 0.3926 0.5889 0.7852 0.9815 0.7120 0.7418 0.5325 0.5153 0.8134 0.7430 0.8724 0.8310 0.7237 0.5058 0.1753 0.1319 0.3554 1. 2 x Xeon Gold 5220R: Detected core count of 36 2. Xeon Gold 5220R: Detected core count of 18 3. Xeon Platinum 8280: Detected core count of 28 4. 2 x Xeon Platinum 8280: Detected core count of 56 5. Xeon Gold 5218: Detected core count of 16 6. Xeon Silver 4216: Detected core count of 16 7. Xeon Gold 6226R: Detected core count of 16 8. 2 x Xeon Gold 6226R: Detected core count of 32 9. 2 x Xeon Silver 4216: Detected core count of 32 10. Xeon W-3275M: Detected core count of 28 11. 2 x Xeon Platinum 8275CL: Detected core count of 48 12. 2 x Xeon Platinum 8275CL NUMA off: Detected core count of 48 13. EPYC 2 7R32: Detected core count of 48 Perf Per Thread
OpenBenchmarking.org GFLOP/s Per Thread, More Is Better High Performance Conjugate Gradient 3.1 Performance Per Thread 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 0.0981 0.1962 0.2943 0.3924 0.4905 0.3560 0.3709 0.2662 0.2576 0.4067 0.3715 0.4362 0.4155 0.3618 0.2529 0.0876 0.0659 0.1777 1. 2 x Xeon Gold 5220R: Detected thread count of 72 2. Xeon Gold 5220R: Detected thread count of 36 3. Xeon Platinum 8280: Detected thread count of 56 4. 2 x Xeon Platinum 8280: Detected thread count of 112 5. Xeon Gold 5218: Detected thread count of 32 6. Xeon Silver 4216: Detected thread count of 32 7. Xeon Gold 6226R: Detected thread count of 32 8. 2 x Xeon Gold 6226R: Detected thread count of 64 9. 2 x Xeon Silver 4216: Detected thread count of 64 10. Xeon W-3275M: Detected thread count of 56 11. 2 x Xeon Platinum 8275CL: Detected thread count of 96 12. 2 x Xeon Platinum 8275CL NUMA off: Detected thread count of 96 13. EPYC 2 7R32: Detected thread count of 96 Perf Per Clock
OpenBenchmarking.org GFLOP/s Per GHz, More Is Better High Performance Conjugate Gradient 3.1 Performance Per Clock 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 4 6 8 10 6.57 3.42 3.73 7.21 3.34 3.72 3.58 6.82 7.24 3.08 2.16 1.62 6.09 1. 2 x Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 2. Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 3. Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 4. 2 x Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 5. Xeon Gold 5218: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 6. Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 7. Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 8. 2 x Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 9. 2 x Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 10. Xeon W-3275M: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.60 11. 2 x Xeon Platinum 8275CL: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 12. 2 x Xeon Platinum 8275CL NUMA off: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 13. EPYC 2 7R32: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 2.80 Perf Per RAM Channel
OpenBenchmarking.org GFLOP/s Per Channel, More Is Better High Performance Conjugate Gradient 3.1 Performance Per Memory Channel 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 EPYC 2 7R32 1.0823 2.1646 3.2469 4.3292 5.4115 4.27 2.23 2.48 4.81 2.17 1.98 2.33 4.43 3.86 2.13 1. 2 x Xeon Gold 5220R: Detected channel count of 6 2. Xeon Gold 5220R: Detected channel count of 6 3. Xeon Platinum 8280: Detected channel count of 6 4. 2 x Xeon Platinum 8280: Detected channel count of 6 5. Xeon Gold 5218: Detected channel count of 6 6. Xeon Silver 4216: Detected channel count of 6 7. Xeon Gold 6226R: Detected channel count of 6 8. 2 x Xeon Gold 6226R: Detected channel count of 6 9. 2 x Xeon Silver 4216: Detected channel count of 6 10. EPYC 2 7R32: Detected channel count of 8 Result Confidence
OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 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 6 12 18 24 30 Min: 25.33 / Avg: 25.63 / Max: 25.84 Min: 13.19 / Avg: 13.35 / Max: 13.44 Min: 14.87 / Avg: 14.91 / Max: 14.99 Min: 28.36 / Avg: 28.85 / Max: 29.14 Min: 13 / Avg: 13.01 / Max: 13.04 Min: 11.82 / Avg: 11.89 / Max: 11.93 Min: 13.92 / Avg: 13.96 / Max: 14.01 Min: 26.34 / Avg: 26.59 / Max: 26.74 Min: 23.15 / Avg: 23.16 / Max: 23.17 Min: 13.94 / Avg: 14.16 / Max: 14.45 Min: 6.44 / Avg: 8.41 / Max: 10.67 Min: 6 / Avg: 6.33 / Max: 6.51 Min: 17.05 / Avg: 17.06 / Max: 17.07 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page
Result
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer ISPC - Model: Asian Dragon 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 15 30 45 60 75 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.53, N = 4 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 43.10 23.60 38.31 68.42 19.43 15.59 22.46 40.43 28.97 35.15 38.77 51.87 52.35 MIN: 42.68 / MAX: 43.7 MIN: 23.45 / MAX: 23.8 MIN: 37.87 / MAX: 38.72 MIN: 66.22 / MAX: 70.39 MIN: 19.37 / MAX: 19.6 MIN: 15.54 / MAX: 15.7 MIN: 22.38 / MAX: 22.62 MIN: 40.04 / MAX: 41.18 MIN: 28.72 / MAX: 29.29 MIN: 33.95 / MAX: 35.72 MIN: 35.85 / MAX: 45.98 MIN: 50.96 / MAX: 54.15 MIN: 51.67 / MAX: 53.48 Result Confidence
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer ISPC - Model: Asian Dragon 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 13 26 39 52 65 Min: 43.07 / Avg: 43.1 / Max: 43.14 Min: 23.56 / Avg: 23.6 / Max: 23.64 Min: 38.21 / Avg: 38.31 / Max: 38.41 Min: 68.36 / Avg: 68.42 / Max: 68.47 Min: 19.42 / Avg: 19.43 / Max: 19.45 Min: 15.58 / Avg: 15.59 / Max: 15.62 Min: 22.45 / Avg: 22.46 / Max: 22.48 Min: 40.29 / Avg: 40.43 / Max: 40.52 Min: 28.93 / Avg: 28.97 / Max: 29 Min: 35.01 / Avg: 35.15 / Max: 35.27 Min: 37.26 / Avg: 38.77 / Max: 39.72 Min: 51.84 / Avg: 51.87 / Max: 51.92 Min: 52.31 / Avg: 52.35 / Max: 52.41
Result
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer ISPC - Model: Asian Dragon Obj 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 13 26 39 52 65 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.63, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 37.15 20.34 33.05 58.69 16.77 13.49 19.32 34.80 25.07 30.35 36.67 44.72 45.43 MIN: 36.74 / MAX: 37.69 MIN: 20.23 / MAX: 20.53 MIN: 32.72 / MAX: 33.4 MIN: 56.97 / MAX: 60.91 MIN: 16.69 / MAX: 16.88 MIN: 13.43 / MAX: 13.59 MIN: 19.25 / MAX: 19.46 MIN: 34.51 / MAX: 35.32 MIN: 24.86 / MAX: 25.34 MIN: 29.95 / MAX: 30.77 MIN: 34.56 / MAX: 39.51 MIN: 43.9 / MAX: 46.32 MIN: 44.82 / MAX: 46.53 Result Confidence
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer ISPC - Model: Asian Dragon Obj 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 12 24 36 48 60 Min: 37.08 / Avg: 37.15 / Max: 37.2 Min: 20.33 / Avg: 20.34 / Max: 20.35 Min: 33.01 / Avg: 33.05 / Max: 33.08 Min: 58.6 / Avg: 58.69 / Max: 58.78 Min: 16.75 / Avg: 16.77 / Max: 16.78 Min: 13.47 / Avg: 13.49 / Max: 13.52 Min: 19.31 / Avg: 19.32 / Max: 19.34 Min: 34.77 / Avg: 34.8 / Max: 34.84 Min: 25.04 / Avg: 25.07 / Max: 25.09 Min: 30.31 / Avg: 30.35 / Max: 30.38 Min: 35.6 / Avg: 36.67 / Max: 37.78 Min: 44.7 / Avg: 44.72 / Max: 44.73 Min: 45.4 / Avg: 45.43 / Max: 45.5
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
Result
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.3 Scene: Rainbow Colors and Prism 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 4 6 8 10 SE +/- 0.30, N = 12 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.40, N = 15 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.13, N = 15 SE +/- 0.00, N = 3 SE +/- 0.03, N = 15 SE +/- 0.11, N = 15 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 4.46 2.48 4.11 7.15 1.88 1.88 2.51 4.32 3.65 3.79 7.09 7.31 8.12 MIN: 1.23 / MAX: 4.91 MIN: 2.4 / MAX: 2.53 MIN: 3.96 / MAX: 4.16 MIN: 2.92 / MAX: 8.11 MIN: 1.85 / MAX: 1.92 MIN: 1.84 / MAX: 1.92 MIN: 2.44 / MAX: 2.56 MIN: 2.71 / MAX: 4.87 MIN: 3.56 / MAX: 3.67 MIN: 3.45 / MAX: 3.89 MIN: 5.64 / MAX: 7.47 MIN: 6.62 / MAX: 7.52 MIN: 7.87 / MAX: 8.3 Result Confidence
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.3 Scene: Rainbow Colors and Prism 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 3 6 9 12 15 Min: 1.25 / Avg: 4.46 / Max: 4.88 Min: 2.45 / Avg: 2.48 / Max: 2.5 Min: 4.03 / Avg: 4.11 / Max: 4.16 Min: 2.98 / Avg: 7.15 / Max: 7.98 Min: 1.88 / Avg: 1.88 / Max: 1.88 Min: 1.88 / Avg: 1.88 / Max: 1.89 Min: 2.49 / Avg: 2.51 / Max: 2.53 Min: 2.88 / Avg: 4.32 / Max: 4.83 Min: 3.64 / Avg: 3.65 / Max: 3.65 Min: 3.48 / Avg: 3.79 / Max: 3.88 Min: 5.76 / Avg: 7.09 / Max: 7.37 Min: 7.22 / Avg: 7.31 / Max: 7.41 Min: 8 / Avg: 8.12 / Max: 8.18
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
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.82 Blend File: Classroom - Compute: CPU-Only 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 90 180 270 360 450 SE +/- 0.18, N = 3 SE +/- 0.39, N = 3 SE +/- 0.36, N = 3 SE +/- 0.26, N = 3 SE +/- 0.29, N = 3 SE +/- 0.20, N = 3 SE +/- 0.16, N = 3 SE +/- 0.52, N = 3 SE +/- 0.19, N = 3 SE +/- 0.32, N = 3 SE +/- 0.11, N = 3 SE +/- 0.29, N = 3 SE +/- 0.40, N = 3 165.96 328.81 198.25 100.47 433.42 432.11 321.53 163.32 218.06 213.36 108.97 108.94 101.34 Result Confidence
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.82 Blend File: Classroom - Compute: CPU-Only 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 80 160 240 320 400 Min: 165.68 / Avg: 165.96 / Max: 166.31 Min: 328.21 / Avg: 328.81 / Max: 329.54 Min: 197.81 / Avg: 198.25 / Max: 198.96 Min: 99.99 / Avg: 100.47 / Max: 100.86 Min: 433.1 / Avg: 433.42 / Max: 433.99 Min: 431.84 / Avg: 432.11 / Max: 432.51 Min: 321.25 / Avg: 321.53 / Max: 321.79 Min: 162.78 / Avg: 163.32 / Max: 164.35 Min: 217.79 / Avg: 218.06 / Max: 218.43 Min: 212.88 / Avg: 213.36 / Max: 213.97 Min: 108.85 / Avg: 108.97 / Max: 109.2 Min: 108.61 / Avg: 108.94 / Max: 109.52 Min: 100.56 / Avg: 101.34 / Max: 101.89
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
Result
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_1d - Data Type: f32 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 1.1949 2.3898 3.5847 4.7796 5.9745 SE +/- 0.00174, N = 3 SE +/- 0.00527, N = 3 SE +/- 0.00157, N = 3 SE +/- 0.00318, N = 3 SE +/- 0.00570, N = 3 SE +/- 0.01140, N = 3 SE +/- 0.00272, N = 3 SE +/- 0.00475, N = 3 SE +/- 0.00576, N = 3 SE +/- 0.01273, N = 3 SE +/- 0.00979, N = 3 SE +/- 0.00024, N = 3 SE +/- 0.01972, N = 3 2.12680 3.36432 1.46232 1.24029 3.99488 5.31087 2.23126 1.49724 3.06590 1.74515 1.33109 1.25116 2.22540 MIN: 2.06 MIN: 3.3 MIN: 1.44 MIN: 1.17 MIN: 3.95 MIN: 5.16 MIN: 2.17 MIN: 1.43 MIN: 2.99 MIN: 1.55 MIN: 1.26 MIN: 1.19 MIN: 2.11 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl Result Confidence
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_1d - Data Type: f32 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 4 6 8 10 Min: 2.12 / Avg: 2.13 / Max: 2.13 Min: 3.36 / Avg: 3.36 / Max: 3.37 Min: 1.46 / Avg: 1.46 / Max: 1.47 Min: 1.23 / Avg: 1.24 / Max: 1.25 Min: 3.98 / Avg: 3.99 / Max: 4 Min: 5.29 / Avg: 5.31 / Max: 5.33 Min: 2.23 / Avg: 2.23 / Max: 2.24 Min: 1.49 / Avg: 1.5 / Max: 1.5 Min: 3.06 / Avg: 3.07 / Max: 3.08 Min: 1.73 / Avg: 1.75 / Max: 1.77 Min: 1.32 / Avg: 1.33 / Max: 1.35 Min: 1.25 / Avg: 1.25 / Max: 1.25 Min: 2.19 / Avg: 2.23 / Max: 2.26 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
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
Result
OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.13 ATPase Simulation - 327,506 Atoms 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 EPYC 2 7R32 0.3414 0.6828 1.0242 1.3656 1.707 SE +/- 0.00612, N = 3 SE +/- 0.00122, N = 3 SE +/- 0.00060, N = 3 SE +/- 0.00133, N = 3 SE +/- 0.00100, N = 3 SE +/- 0.00193, N = 3 SE +/- 0.00117, N = 3 SE +/- 0.00104, N = 3 SE +/- 0.00193, N = 3 SE +/- 0.00775, N = 15 SE +/- 0.00084, N = 3 0.60333 1.15745 0.70709 0.36226 1.51168 1.51721 1.13586 0.58237 0.76982 0.81434 0.48614 Perf Per Core
OpenBenchmarking.org days/ns x Core, Fewer Is Better NAMD 2.13 Performance Per Core - ATPase Simulation - 327,506 Atoms 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 EPYC 2 7R32 6 12 18 24 30 21.72 20.83 19.80 20.29 24.19 24.28 18.17 18.64 24.63 22.80 23.34 1. 2 x Xeon Gold 5220R: Detected core count of 36 2. Xeon Gold 5220R: Detected core count of 18 3. Xeon Platinum 8280: Detected core count of 28 4. 2 x Xeon Platinum 8280: Detected core count of 56 5. Xeon Gold 5218: Detected core count of 16 6. Xeon Silver 4216: Detected core count of 16 7. Xeon Gold 6226R: Detected core count of 16 8. 2 x Xeon Gold 6226R: Detected core count of 32 9. 2 x Xeon Silver 4216: Detected core count of 32 10. Xeon W-3275M: Detected core count of 28 11. EPYC 2 7R32: Detected core count of 48 Perf Per Thread
OpenBenchmarking.org days/ns x Thread, Fewer Is Better NAMD 2.13 Performance Per Thread - ATPase Simulation - 327,506 Atoms 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 EPYC 2 7R32 11 22 33 44 55 43.44 41.67 39.60 40.57 48.37 48.55 36.35 37.27 49.27 45.60 46.67 1. 2 x Xeon Gold 5220R: Detected thread count of 72 2. Xeon Gold 5220R: Detected thread count of 36 3. Xeon Platinum 8280: Detected thread count of 56 4. 2 x Xeon Platinum 8280: Detected thread count of 112 5. Xeon Gold 5218: Detected thread count of 32 6. Xeon Silver 4216: Detected thread count of 32 7. Xeon Gold 6226R: Detected thread count of 32 8. 2 x Xeon Gold 6226R: Detected thread count of 64 9. 2 x Xeon Silver 4216: Detected thread count of 64 10. Xeon W-3275M: Detected thread count of 56 11. EPYC 2 7R32: Detected thread count of 96 Perf Per Clock
OpenBenchmarking.org days/ns x GHz, Fewer Is Better NAMD 2.13 Performance Per Clock - ATPase Simulation - 327,506 Atoms 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 EPYC 2 7R32 1.3266 2.6532 3.9798 5.3064 6.633 2.353 4.514 2.828 1.449 5.896 4.855 4.430 2.271 2.463 3.746 1.361 1. 2 x Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 2. Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 3. Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 4. 2 x Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 5. Xeon Gold 5218: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 6. Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 7. Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 8. 2 x Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 9. 2 x Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 10. Xeon W-3275M: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.60 11. EPYC 2 7R32: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 2.80 Perf Per RAM Channel
OpenBenchmarking.org days/ns x Channel, Fewer Is Better NAMD 2.13 Performance Per Memory Channel - ATPase Simulation - 327,506 Atoms 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 EPYC 2 7R32 3 6 9 12 15 3.620 6.945 4.243 2.174 9.070 9.103 6.815 3.494 4.619 3.889 1. 2 x Xeon Gold 5220R: Detected channel count of 6 2. Xeon Gold 5220R: Detected channel count of 6 3. Xeon Platinum 8280: Detected channel count of 6 4. 2 x Xeon Platinum 8280: Detected channel count of 6 5. Xeon Gold 5218: Detected channel count of 6 6. Xeon Silver 4216: Detected channel count of 6 7. Xeon Gold 6226R: Detected channel count of 6 8. 2 x Xeon Gold 6226R: Detected channel count of 6 9. 2 x Xeon Silver 4216: Detected channel count of 6 10. EPYC 2 7R32: Detected channel count of 8 Result Confidence
OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.13 ATPase Simulation - 327,506 Atoms 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 EPYC 2 7R32 2 4 6 8 10 Min: 0.59 / Avg: 0.6 / Max: 0.62 Min: 1.16 / Avg: 1.16 / Max: 1.16 Min: 0.71 / Avg: 0.71 / Max: 0.71 Min: 0.36 / Avg: 0.36 / Max: 0.36 Min: 1.51 / Avg: 1.51 / Max: 1.51 Min: 1.51 / Avg: 1.52 / Max: 1.52 Min: 1.13 / Avg: 1.14 / Max: 1.14 Min: 0.58 / Avg: 0.58 / Max: 0.58 Min: 0.77 / Avg: 0.77 / Max: 0.77 Min: 0.78 / Avg: 0.81 / Max: 0.87 Min: 0.48 / Avg: 0.49 / Max: 0.49
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
Result
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.3 Scene: DLSC 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 4 6 8 10 SE +/- 0.0120, N = 3 SE +/- 0.0243, N = 3 SE +/- 0.0032, N = 3 SE +/- 0.0948, N = 3 SE +/- 0.0034, N = 3 SE +/- 0.0165, N = 3 SE +/- 0.0145, N = 3 SE +/- 0.0036, N = 3 SE +/- 0.0265, N = 3 SE +/- 0.0035, N = 3 SE +/- 0.0262, N = 3 SE +/- 0.0164, N = 3 SE +/- 0.0970, N = 3 4.4400 2.3200 3.7900 7.1900 1.7400 1.7700 2.3500 4.5183 3.4300 3.5300 6.7300 6.7500 7.2800 MIN: 4.34 / MAX: 4.63 MIN: 2.2 / MAX: 2.43 MIN: 3.65 / MAX: 3.94 MIN: 6.83 / MAX: 7.6 MIN: 1.67 / MAX: 1.79 MIN: 1.68 / MAX: 1.85 MIN: 2.24 / MAX: 2.46 MIN: 4.4 / MAX: 4.76 MIN: 3.33 / MAX: 3.63 MIN: 3.46 / MAX: 3.66 MIN: 6.54 / MAX: 7.08 MIN: 6.62 / MAX: 7.08 MIN: 7.01 / MAX: 7.86 Result Confidence
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.3 Scene: DLSC 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 3 6 9 12 15 Min: 4.42 / Avg: 4.44 / Max: 4.46 Min: 2.29 / Avg: 2.32 / Max: 2.36 Min: 3.79 / Avg: 3.79 / Max: 3.79 Min: 7 / Avg: 7.19 / Max: 7.31 Min: 1.74 / Avg: 1.74 / Max: 1.75 Min: 1.75 / Avg: 1.77 / Max: 1.8 Min: 2.33 / Avg: 2.35 / Max: 2.38 Min: 4.51 / Avg: 4.52 / Max: 4.53 Min: 3.39 / Avg: 3.43 / Max: 3.48 Min: 3.52 / Avg: 3.53 / Max: 3.53 Min: 6.68 / Avg: 6.73 / Max: 6.76 Min: 6.72 / Avg: 6.75 / Max: 6.78 Min: 7.13 / Avg: 7.28 / Max: 7.46
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
Result
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_1d - Data Type: bf16bf16bf16 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 4 8 12 16 20 SE +/- 0.00772, N = 3 SE +/- 0.04579, N = 3 SE +/- 0.00167, N = 3 SE +/- 0.00661, N = 3 SE +/- 0.00105, N = 3 SE +/- 0.00867, N = 3 SE +/- 0.00392, N = 3 SE +/- 0.00747, N = 3 SE +/- 0.01001, N = 3 SE +/- 0.03740, N = 3 SE +/- 0.01030, N = 3 SE +/- 0.00401, N = 3 7.22975 13.14280 6.55374 4.06847 16.54840 16.55160 9.90362 5.38402 8.86913 7.61595 3.96906 3.96510 MIN: 7.13 MIN: 12.96 MIN: 6.5 MIN: 3.93 MIN: 16.51 MIN: 16.51 MIN: 9.85 MIN: 5.3 MIN: 8.78 MIN: 6.95 MIN: 3.86 MIN: 3.88 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl Result Confidence
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_1d - Data Type: bf16bf16bf16 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 4 8 12 16 20 Min: 7.21 / Avg: 7.23 / Max: 7.24 Min: 13.07 / Avg: 13.14 / Max: 13.23 Min: 6.55 / Avg: 6.55 / Max: 6.56 Min: 4.06 / Avg: 4.07 / Max: 4.08 Min: 16.55 / Avg: 16.55 / Max: 16.55 Min: 16.54 / Avg: 16.55 / Max: 16.57 Min: 9.9 / Avg: 9.9 / Max: 9.91 Min: 5.37 / Avg: 5.38 / Max: 5.4 Min: 8.86 / Avg: 8.87 / Max: 8.89 Min: 7.54 / Avg: 7.62 / Max: 7.66 Min: 3.95 / Avg: 3.97 / Max: 3.98 Min: 3.96 / Avg: 3.97 / Max: 3.97 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
Result
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: MD5 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 2M 4M 6M 8M 10M SE +/- 9643.65, N = 3 SE +/- 6806.86, N = 3 SE +/- 14468.36, N = 3 SE +/- 67263.16, N = 3 SE +/- 8171.77, N = 3 SE +/- 1452.97, N = 3 SE +/- 11015.14, N = 3 SE +/- 17032.65, N = 3 SE +/- 4509.25, N = 3 SE +/- 14294.52, N = 3 SE +/- 5783.12, N = 3 SE +/- 39218.76, N = 3 SE +/- 30550.50, N = 3 4821000 2506000 4090000 7880000 1912667 1893333 2583000 4977667 3764000 3654000 7388333 7350667 3972000 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2 Perf Per Core
OpenBenchmarking.org Real C/S Per Core, More Is Better John The Ripper 1.9.0-jumbo-1 Performance Per Core - Test: MD5 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 30K 60K 90K 120K 150K 133916.67 139222.22 146071.43 140714.29 119541.69 118333.31 161437.50 155552.09 117625.00 130500.00 153923.60 153138.90 82750.00 1. 2 x Xeon Gold 5220R: Detected core count of 36 2. Xeon Gold 5220R: Detected core count of 18 3. Xeon Platinum 8280: Detected core count of 28 4. 2 x Xeon Platinum 8280: Detected core count of 56 5. Xeon Gold 5218: Detected core count of 16 6. Xeon Silver 4216: Detected core count of 16 7. Xeon Gold 6226R: Detected core count of 16 8. 2 x Xeon Gold 6226R: Detected core count of 32 9. 2 x Xeon Silver 4216: Detected core count of 32 10. Xeon W-3275M: Detected core count of 28 11. 2 x Xeon Platinum 8275CL: Detected core count of 48 12. 2 x Xeon Platinum 8275CL NUMA off: Detected core count of 48 13. EPYC 2 7R32: Detected core count of 48 Perf Per Thread
OpenBenchmarking.org Real C/S Per Thread, More Is Better John The Ripper 1.9.0-jumbo-1 Performance Per Thread - Test: MD5 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 20K 40K 60K 80K 100K 66958.33 69611.11 73035.71 70357.14 59770.84 59166.66 80718.75 77776.05 58812.50 65250.00 76961.80 76569.45 41375.00 1. 2 x Xeon Gold 5220R: Detected thread count of 72 2. Xeon Gold 5220R: Detected thread count of 36 3. Xeon Platinum 8280: Detected thread count of 56 4. 2 x Xeon Platinum 8280: Detected thread count of 112 5. Xeon Gold 5218: Detected thread count of 32 6. Xeon Silver 4216: Detected thread count of 32 7. Xeon Gold 6226R: Detected thread count of 32 8. 2 x Xeon Gold 6226R: Detected thread count of 64 9. 2 x Xeon Silver 4216: Detected thread count of 64 10. Xeon W-3275M: Detected thread count of 56 11. 2 x Xeon Platinum 8275CL: Detected thread count of 96 12. 2 x Xeon Platinum 8275CL NUMA off: Detected thread count of 96 13. EPYC 2 7R32: Detected thread count of 96 Perf Per Clock
OpenBenchmarking.org Real C/S Per GHz, More Is Better John The Ripper 1.9.0-jumbo-1 Performance Per Clock - Test: MD5 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 400K 800K 1200K 1600K 2000K 1236153.85 642564.10 1022500.00 1970000.00 490427.44 591666.56 662307.69 1276324.87 1176250.00 794347.83 1894444.36 1884786.41 1418571.43 1. 2 x Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 2. Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 3. Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 4. 2 x Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 5. Xeon Gold 5218: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 6. Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 7. Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 8. 2 x Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 9. 2 x Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 10. Xeon W-3275M: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.60 11. 2 x Xeon Platinum 8275CL: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 12. 2 x Xeon Platinum 8275CL NUMA off: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 13. EPYC 2 7R32: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 2.80 Perf Per RAM Channel
OpenBenchmarking.org Real C/S Per Channel, More Is Better John The Ripper 1.9.0-jumbo-1 Performance Per Memory Channel - Test: MD5 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 EPYC 2 7R32 300K 600K 900K 1200K 1500K 803500.00 417666.67 681666.67 1313333.33 318777.83 315555.50 430500.00 829611.17 627333.33 496500.00 1. 2 x Xeon Gold 5220R: Detected channel count of 6 2. Xeon Gold 5220R: Detected channel count of 6 3. Xeon Platinum 8280: Detected channel count of 6 4. 2 x Xeon Platinum 8280: Detected channel count of 6 5. Xeon Gold 5218: Detected channel count of 6 6. Xeon Silver 4216: Detected channel count of 6 7. Xeon Gold 6226R: Detected channel count of 6 8. 2 x Xeon Gold 6226R: Detected channel count of 6 9. 2 x Xeon Silver 4216: Detected channel count of 6 10. EPYC 2 7R32: Detected channel count of 8 Result Confidence
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: MD5 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 1.4M 2.8M 4.2M 5.6M 7M Min: 4806000 / Avg: 4821000 / Max: 4839000 Min: 2493000 / Avg: 2506000 / Max: 2516000 Min: 4066000 / Avg: 4090000 / Max: 4116000 Min: 7749000 / Avg: 7880000 / Max: 7972000 Min: 1904000 / Avg: 1912666.67 / Max: 1929000 Min: 1891000 / Avg: 1893333.33 / Max: 1896000 Min: 2561000 / Avg: 2583000 / Max: 2595000 Min: 4944000 / Avg: 4977666.67 / Max: 4999000 Min: 3755000 / Avg: 3764000 / Max: 3769000 Min: 3626000 / Avg: 3654000 / Max: 3673000 Min: 7377000 / Avg: 7388333.33 / Max: 7396000 Min: 7273000 / Avg: 7350666.67 / Max: 7399000 Min: 3932000 / Avg: 3972000 / Max: 4032000 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
Blender Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.82 Blend File: Pabellon Barcelona - Compute: CPU-Only 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 120 240 360 480 600 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.26, N = 3 SE +/- 0.31, N = 3 SE +/- 0.46, N = 3 SE +/- 0.22, N = 3 SE +/- 0.09, N = 3 SE +/- 0.50, N = 3 SE +/- 0.73, N = 3 SE +/- 0.15, N = 3 SE +/- 0.11, N = 3 SE +/- 0.51, N = 3 208.30 404.78 246.31 129.01 531.98 531.39 400.96 207.41 272.72 265.41 139.11 139.00 132.04 Result Confidence
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.82 Blend File: Pabellon Barcelona - Compute: CPU-Only 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 90 180 270 360 450 Min: 208.1 / Avg: 208.3 / Max: 208.45 Min: 404.72 / Avg: 404.78 / Max: 404.82 Min: 246.23 / Avg: 246.31 / Max: 246.39 Min: 128.65 / Avg: 129.01 / Max: 129.51 Min: 531.42 / Avg: 531.98 / Max: 532.47 Min: 530.72 / Avg: 531.39 / Max: 532.27 Min: 400.53 / Avg: 400.96 / Max: 401.29 Min: 207.29 / Avg: 207.41 / Max: 207.58 Min: 272.04 / Avg: 272.72 / Max: 273.7 Min: 264.01 / Avg: 265.41 / Max: 266.46 Min: 138.96 / Avg: 139.11 / Max: 139.4 Min: 138.83 / Avg: 139 / Max: 139.2 Min: 131.01 / Avg: 132.04 / Max: 132.59
John The Ripper This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page
Result
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: Blowfish 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 20K 40K 60K 80K 100K SE +/- 12.50, N = 3 SE +/- 77.98, N = 3 SE +/- 99.39, N = 3 SE +/- 700.53, N = 3 SE +/- 6.03, N = 3 SE +/- 24.29, N = 3 SE +/- 60.93, N = 3 SE +/- 111.31, N = 3 SE +/- 91.33, N = 3 SE +/- 149.28, N = 3 SE +/- 465.66, N = 3 SE +/- 78.50, N = 3 SE +/- 203.51, N = 3 51324 25547 42864 84084 21403 20424 27126 53485 41021 40326 77771 78327 66475 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2 Perf Per Core
OpenBenchmarking.org Real C/S Per Core, More Is Better John The Ripper 1.9.0-jumbo-1 Performance Per Core - Test: Blowfish 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 400 800 1200 1600 2000 1425.67 1419.28 1530.86 1501.50 1337.69 1276.50 1695.38 1671.41 1281.91 1440.21 1620.23 1631.81 1384.90 1. 2 x Xeon Gold 5220R: Detected core count of 36 2. Xeon Gold 5220R: Detected core count of 18 3. Xeon Platinum 8280: Detected core count of 28 4. 2 x Xeon Platinum 8280: Detected core count of 56 5. Xeon Gold 5218: Detected core count of 16 6. Xeon Silver 4216: Detected core count of 16 7. Xeon Gold 6226R: Detected core count of 16 8. 2 x Xeon Gold 6226R: Detected core count of 32 9. 2 x Xeon Silver 4216: Detected core count of 32 10. Xeon W-3275M: Detected core count of 28 11. 2 x Xeon Platinum 8275CL: Detected core count of 48 12. 2 x Xeon Platinum 8275CL NUMA off: Detected core count of 48 13. EPYC 2 7R32: Detected core count of 48 Perf Per Thread
OpenBenchmarking.org Real C/S Per Thread, More Is Better John The Ripper 1.9.0-jumbo-1 Performance Per Thread - Test: Blowfish 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 200 400 600 800 1000 712.83 709.64 765.43 750.75 668.84 638.25 847.69 835.70 640.95 720.11 810.11 815.91 692.45 1. 2 x Xeon Gold 5220R: Detected thread count of 72 2. Xeon Gold 5220R: Detected thread count of 36 3. Xeon Platinum 8280: Detected thread count of 56 4. 2 x Xeon Platinum 8280: Detected thread count of 112 5. Xeon Gold 5218: Detected thread count of 32 6. Xeon Silver 4216: Detected thread count of 32 7. Xeon Gold 6226R: Detected thread count of 32 8. 2 x Xeon Gold 6226R: Detected thread count of 64 9. 2 x Xeon Silver 4216: Detected thread count of 64 10. Xeon W-3275M: Detected thread count of 56 11. 2 x Xeon Platinum 8275CL: Detected thread count of 96 12. 2 x Xeon Platinum 8275CL NUMA off: Detected thread count of 96 13. EPYC 2 7R32: Detected thread count of 96 Perf Per Clock
OpenBenchmarking.org Real C/S Per GHz, More Is Better John The Ripper 1.9.0-jumbo-1 Performance Per Clock - Test: Blowfish 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 5K 10K 15K 20K 25K 13160.00 6550.51 10716.00 21021.00 5487.95 6382.50 6955.38 13714.10 12819.06 8766.52 19941.28 20083.85 23741.07 1. 2 x Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 2. Xeon Gold 5220R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 3. Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 4. 2 x Xeon Platinum 8280: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.00 5. Xeon Gold 5218: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 6. Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 7. Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 8. 2 x Xeon Gold 6226R: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 9. 2 x Xeon Silver 4216: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.20 10. Xeon W-3275M: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 4.60 11. 2 x Xeon Platinum 8275CL: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 12. 2 x Xeon Platinum 8275CL NUMA off: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 3.90 13. EPYC 2 7R32: Detected GHz base clock speed (use PTS sensors for real-time frequency/sensor reporting) count of 2.80 Perf Per RAM Channel
OpenBenchmarking.org Real C/S Per Channel, More Is Better John The Ripper 1.9.0-jumbo-1 Performance Per Memory Channel - Test: Blowfish 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 EPYC 2 7R32 3K 6K 9K 12K 15K 8554.00 4257.83 7144.00 14014.00 3567.17 3404.00 4521.00 8914.17 6836.83 8309.38 1. 2 x Xeon Gold 5220R: Detected channel count of 6 2. Xeon Gold 5220R: Detected channel count of 6 3. Xeon Platinum 8280: Detected channel count of 6 4. 2 x Xeon Platinum 8280: Detected channel count of 6 5. Xeon Gold 5218: Detected channel count of 6 6. Xeon Silver 4216: Detected channel count of 6 7. Xeon Gold 6226R: Detected channel count of 6 8. 2 x Xeon Gold 6226R: Detected channel count of 6 9. 2 x Xeon Silver 4216: Detected channel count of 6 10. EPYC 2 7R32: Detected channel count of 8 Result Confidence
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: Blowfish 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 15K 30K 45K 60K 75K Min: 51304 / Avg: 51324 / Max: 51347 Min: 25414 / Avg: 25546.67 / Max: 25684 Min: 42674 / Avg: 42863.67 / Max: 43010 Min: 82930 / Avg: 84083.67 / Max: 85349 Min: 21391 / Avg: 21403 / Max: 21410 Min: 20383 / Avg: 20423.67 / Max: 20467 Min: 27043 / Avg: 27126.33 / Max: 27245 Min: 53299 / Avg: 53485.33 / Max: 53684 Min: 40838 / Avg: 41020.67 / Max: 41112 Min: 40071 / Avg: 40326.33 / Max: 40588 Min: 76870 / Avg: 77771.33 / Max: 78425 Min: 78220 / Avg: 78327 / Max: 78480 Min: 66240 / Avg: 66474.67 / Max: 66880 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
MKL-DNN DNNL This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page
Result
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_3d - Data Type: u8s8f32 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 3K 6K 9K 12K 15K SE +/- 3.52, N = 3 SE +/- 11.33, N = 3 SE +/- 11.11, N = 3 SE +/- 7.97, N = 3 SE +/- 2.59, N = 3 SE +/- 13.03, N = 3 SE +/- 9.11, N = 3 SE +/- 10.40, N = 3 SE +/- 109.20, N = 3 SE +/- 41.02, N = 3 SE +/- 4.78, N = 3 SE +/- 0.59, N = 3 SE +/- 25.92, N = 3 4896.41 9696.92 5919.94 3005.48 11821.30 12300.30 9374.60 4821.24 6329.94 6183.11 3250.89 3252.48 3076.76 MIN: 4854.07 MIN: 9656.48 MIN: 5895.99 MIN: 2934.55 MIN: 11811.3 MIN: 12254 MIN: 9350.22 MIN: 4760.44 MIN: 6190.58 MIN: 5934.01 MIN: 3176.52 MIN: 3175.14 MIN: 3011.81 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl Result Confidence
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_3d - Data Type: u8s8f32 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 2K 4K 6K 8K 10K