Benchmarks by Michael Larabel for a future article for launch day review.
EPYC 7773X 2P Processor: 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 512GB, Disk: 3201GB Micron_7450_MTFDKCC3T2TFS, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 23.04, Kernel: 6.2.0-23-generic (x86_64), Desktop: GNOME Shell 44.0, Display Server: X Server 1.21.1.7, Compiler: GCC 13.0.1 20230315, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001229Python Notes: Python 3.11.2Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
EPYC 9554 2P Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101121Python Notes: Python 3.11.2Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
EPYC 9554 2P - Power 400W Processor: 2 x AMD EPYC 9554 64-Core @ 3.10GHz (128 Cores / 256 Threads) , Motherboard: AMD Titanite_4G (RTI1007B BIOS) , Chipset: AMD Device 14a4 , Memory: 1520GB , Disk: 3201GB Micron_7450_MTFDKCC3T2TFS, Graphics: ASPEED, Monitor: VGA HDMI , Network: Broadcom NetXtreme BCM5720 PCIe
EPYC 9654 2P Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101121Java Notes: OpenJDK Runtime Environment (build 11.0.19+7-post-Ubuntu-0ubuntu123.04)Python Notes: Python 3.11.2Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
EPYC 9654 2P - Power 400W Changed Processor to 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads) .
EPYC 9684X 2P Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101121Python Notes: Python 3.11.2Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
EPYC 9684X 2P - Power 400W Changed Processor to 2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads) .
EPYC 9754 2P Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa0010bPython Notes: Python 3.11.2Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
EPYC 9754 2P - Power 400W Processor: 2 x AMD EPYC 9754 128-Core @ 2.25GHz (256 Cores / 512 Threads) , Motherboard: AMD Titanite_4G (RTI1007B BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 3201GB Micron_7450_MTFDKCC3T2TFS, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 23.04, Kernel: 6.2.0-23-generic (x86_64), Desktop: GNOME Shell 44.0, Display Server: X Server 1.21.1.7, Compiler: GCC 13.0.1 20230315, File-System: ext4, Screen Resolution: 1024x768
Xeon Platinum 8490H 2P Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads) , Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS) , Chipset: Intel Device 1bce , Memory: 1008GB , Disk: 3201GB Micron_7450_MTFDKCC3T2TFS, Graphics: ASPEED, Monitor: VGA HDMI , Network: 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T
OS: Ubuntu 23.04, Kernel: 6.2.0-23-generic (x86_64), Desktop: GNOME Shell 44.0, Display Server: X Server 1.21.1.7, Compiler: GCC 13.0.1 20230315, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b000181Java Notes: OpenJDK Runtime Environment (build 11.0.19+7-post-Ubuntu-0ubuntu123.04)Python Notes: Python 3.11.2Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Xeon Max 9480 2P Processor: 2 x Intel Xeon Max 9480 @ 3.50GHz (112 Cores / 224 Threads) , Motherboard: Supermicro X13DEM v1.10 (1.3 BIOS) , Chipset: Intel Device 1bce, Memory: 512GB , Disk: 3201GB Micron_7450_MTFDKCC3T2TFS + 250GB SABRENT , Graphics: ASPEED, Monitor: VE228 , Network: 2 x Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb/200Gb
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0x2c0001d1Java Notes: OpenJDK Runtime Environment (build 11.0.19+7-post-Ubuntu-0ubuntu123.04)Python Notes: Python 3.11.2Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Xeon Max 9480 2P - HBM Only Processor: 2 x Intel Xeon Max 9480 @ 3.50GHz (112 Cores / 224 Threads), Motherboard: Supermicro X13DEM v1.10 (1.3 BIOS), Chipset: Intel Device 1bce, Memory: 128GB , Disk: 3201GB Micron_7450_MTFDKCC3T2TFS , Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb/200Gb
OS: Ubuntu 23.04, Kernel: 6.2.0-23-generic (x86_64), Desktop: GNOME Shell 44.0, Display Server: X Server 1.21.1.7, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-Pa930Z/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Pa930Z/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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_cpufreq performance - CPU Microcode: 0x2c0001d1Python Notes: Python 3.11.2Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
AMD EPYC 9684X 2P Genoa-X Benchmarks Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Compiler File-System Screen Resolution EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads) AMD DAYTONA_X (RYM1009B BIOS) AMD Starship/Matisse 512GB 3201GB Micron_7450_MTFDKCC3T2TFS ASPEED VE228 2 x Mellanox MT27710 Ubuntu 23.04 6.2.0-23-generic (x86_64) GNOME Shell 44.0 X Server 1.21.1.7 GCC 13.0.1 20230315 ext4 1920x1080 2 x AMD EPYC 9554 64-Core @ 3.10GHz (128 Cores / 256 Threads) AMD Titanite_4G (RTI1007B BIOS) AMD Device 14a4 1520GB VGA HDMI Broadcom NetXtreme BCM5720 PCIe 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads) 2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads) 2 x AMD EPYC 9754 128-Core @ 2.25GHz (256 Cores / 512 Threads) 1024x768 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads) Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS) Intel Device 1bce 1008GB VGA HDMI 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T 1920x1080 2 x Intel Xeon Max 9480 @ 3.50GHz (112 Cores / 224 Threads) Supermicro X13DEM v1.10 (1.3 BIOS) 512GB 3201GB Micron_7450_MTFDKCC3T2TFS + 250GB SABRENT VE228 2 x Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb/200Gb 128GB 3201GB Micron_7450_MTFDKCC3T2TFS GCC 12.2.0 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - EPYC 7773X 2P: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - EPYC 9554 2P: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - EPYC 9554 2P - Power 400W: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - EPYC 9654 2P: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - EPYC 9654 2P - Power 400W: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - EPYC 9684X 2P: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - EPYC 9684X 2P - Power 400W: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - EPYC 9754 2P: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - EPYC 9754 2P - Power 400W: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Xeon Platinum 8490H 2P: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Xeon Max 9480 2P: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Xeon Max 9480 2P - HBM Only: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-Pa930Z/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Pa930Z/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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 - EPYC 7773X 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001229 - EPYC 9554 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101121 - EPYC 9554 2P - Power 400W: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101121 - EPYC 9654 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101121 - EPYC 9654 2P - Power 400W: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101121 - EPYC 9684X 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101121 - EPYC 9684X 2P - Power 400W: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101121 - EPYC 9754 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa0010b - EPYC 9754 2P - Power 400W: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa0010b - Xeon Platinum 8490H 2P: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b000181 - Xeon Max 9480 2P: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0x2c0001d1 - Xeon Max 9480 2P - HBM Only: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0x2c0001d1 Python Details - Python 3.11.2 Security Details - EPYC 7773X 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9554 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9554 2P - Power 400W: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9654 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9654 2P - Power 400W: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9684X 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9684X 2P - Power 400W: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9754 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9754 2P - Power 400W: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - Xeon Platinum 8490H 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected - Xeon Max 9480 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected - Xeon Max 9480 2P - HBM Only: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected Java Details - EPYC 9654 2P, EPYC 9654 2P - Power 400W, Xeon Platinum 8490H 2P, Xeon Max 9480 2P: OpenJDK Runtime Environment (build 11.0.19+7-post-Ubuntu-0ubuntu123.04)
EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only Result Overview Phoronix Test Suite 100% 231% 363% 494% 625% Embree PostgreSQL PETSc Xmrig Blender OSPRay Studio miniFE srsRAN Project ASKAP RELION High Performance Conjugate Gradient Algebraic Multi-Grid Benchmark Kvazaar HeFFTe - Highly Efficient FFT for Exascale LeelaChessZero GPAW Xcompact3d Incompact3d NAS Parallel Benchmarks Timed Linux Kernel Compilation Timed Godot Game Engine Compilation Liquid-DSP Timed PHP Compilation Z3 Theorem Prover
EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only Logarithmic Per Watt Result Overview Phoronix Test Suite miniFE Xmrig Kvazaar High Performance Conjugate Gradient HeFFTe - Highly Efficient FFT for Exascale PETSc ASKAP NAS Parallel Benchmarks LeelaChessZero srsRAN Project Embree Algebraic Multi-Grid Benchmark Liquid-DSP P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M
AMD EPYC 9684X 2P Genoa-X Benchmarks openfoam: drivaerFastback, Medium Mesh Size - Execution Time wrf: conus 2.5km cp2k: H2O-DFT-LS gpaw: Carbon Nanotube minife: Small askap: tConvolve MPI - Degridding askap: tConvolve MPI - Gridding askap: tConvolve MT - Degridding incompact3d: input.i3d 129 Cells Per Direction incompact3d: input.i3d 193 Cells Per Direction incompact3d: X3D-benchmarking input.i3d heffte: r2c - FFTW - float - 512 heffte: r2c - FFTW - double - 256 heffte: r2c - FFTW - double - 512 heffte: c2c - FFTW - float - 512 heffte: c2c - FFTW - double - 512 relion: Basic - CPU amg: hpcg: 104 104 104 - 60 hpcg: 144 144 144 - 60 hpcg: 160 160 160 - 60 hpcg: 192 192 192 - 60 npb: BT.C npb: LU.C npb: SP.C npb: IS.D npb: MG.C npb: CG.C openvino: Vehicle Detection FP16 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU petsc: Streams pgbench: 100 - 1000 - Read Only pgbench: 100 - 1000 - Read Only - Average Latency build-nodejs: Time To Compile build-llvm: Ninja build-llvm: Unix Makefiles build-linux-kernel: defconfig build-php: Time To Compile build-godot: Time To Compile srsran: PUSCH Processor Benchmark, Throughput Total liquid-dsp: 224 - 256 - 32 z3: 1.smt2 z3: 2.smt2 kvazaar: Bosphorus 4K - Slow kvazaar: Bosphorus 4K - Medium blender: Barbershop - CPU-Only ospray-studio: 1 - 1080p - 32 - Path Tracer ospray-studio: 1 - 4K - 32 - Path Tracer ospray-studio: 3 - 1080p - 16 - Path Tracer ospray-studio: 3 - 1080p - 32 - Path Tracer ospray-studio: 3 - 4K - 1 - Path Tracer ospray-studio: 3 - 4K - 16 - Path Tracer ospray-studio: 3 - 4K - 32 - Path Tracer embree: Pathtracer - Asian Dragon embree: Pathtracer - Asian Dragon Obj embree: Pathtracer ISPC - Asian Dragon embree: Pathtracer ISPC - Asian Dragon Obj embree: Pathtracer ISPC - Crown lczero: BLAS xmrig: Monero - 1M xmrig: Wownero - 1M libxsmm: 32 libxsmm: 64 libxsmm: 128 libxsmm: 256 EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 165.25603 10994.34 38.212 23547.7 61441.9 65262.5 11018.44 2.24475327 9.62580643 264.851715 304.967 149.946 125.108 146.156 60.9986 155.502 1988543333 38.5289 38.3063 38.1718 375894.53 395342.95 230772.86 5104.50 124155.94 51653.20 247183.4949 2940406 0.340 174.558 200.895 417.794 36.678 75.019 194.497 19272.8 6684733333 23.003 74.565 32.88 33.26 136.45 8939 35271 5276 10550 1305 20971 42055 86.1879 75.2567 82.7288 76.1899 116.9461 6388 44133.3 49842.9 1387.2 2479.6 3010.3 1816.7 131.27556 5138.985 2023.486 22.834 51915.1 60853.9 72808.3 12762.4 1.44945346 4.80414799 209.934991 477.755 305.716 235.833 247.150 127.807 141.494 3911914333 56.0619 54.6082 53.2119 54.6976 466102.69 480255.42 244961.40 7725.20 233525.20 87564.20 5986.33 5.33 7429.33 4.3 780.72 40.94 501964.6207 3377813 0.296 138.486 156.748 344.018 29.495 66.027 165.241 29598.0 7461400000 26.786 69.029 46.03 46.64 97.24 5859 23210 3498 6994 866 13801 27662 163.8870 146.6541 181.2046 154.7801 154.7283 11066 83001.5 99547.5 1398.8 2672.3 3969.1 4613.5 127.46175 5060.635 1999.239 22.138 52687.4 60555.6 74108.5 15165.2 1.44751305 4.90615211 210.674052 480.331 311.873 235.958 249.474 127.404 140.515 3948722533 56.4716 54.4866 54.2032 52.7608 461016.80 486004.49 247051.81 7582.72 238244.69 86896.70 6269.79 5.09 7536.10 4.24 804.67 39.72 491308.0840 3426783 0.292 137.125 153.603 343.027 28.508 66.202 163.309 33145.4 7538066667 26.410 68.844 46.19 46.75 87.96 5371 21243 3213 6407 795 12717 25414 168.2334 150.4166 186.2801 159.3917 164.3641 11285 83722.1 101344.8 1405.8 2669.9 4083.5 4973.8 109.34592 5333.319 2355.94 21.536 55164.1 81812.9 89976.4 12817.6 1.37331832 4.19870104 221.992011 555.828 349.104 251.047 278.868 132.059 120.435 3235269000 50.6604 50.1240 49.8877 43.3762 513456.93 503710.85 269429.29 7816.33 207828.63 84056.04 7369.29 6.50 9128.21 5.25 953.22 50.30 498825.9270 3277193 0.305 134.416 144.852 342.673 28.706 67.253 164.591 34984.6 7146733333 26.478 70.072 64.99 65.99 83.29 4858 19160 2895 5788 716 11419 22886 194.9779 174.4107 214.5794 183.9434 181.7287 11144 104948.9 128571.3 1680.9 2970.2 4581.2 5695.5 105.61812 4301.371 2009.737 19.854 53638.5 86299.0 98445.7 11420.4 1.33808986 4.19422695 202.564627 566.202 345.253 253.789 281.561 133.517 138.411 2872242308 47.1495 43.7615 43.5451 43.0112 556402.91 517505.91 272856.60 7697.45 202036.80 86108.56 7969.63 6.01 9766.42 4.91 1001.16 47.89 440996.4963 3251179 0.308 131.196 138.072 341.389 27.679 66.888 161.276 38529.2 7566000000 26.751 70.114 65.69 66.17 72.94 4182 16507 2497 4990 613 9856 19769 218.9603 195.7776 240.4117 205.1349 209.1992 11607 111812.1 139145.3 1701.8 3012.0 4939.0 5980.1 94.639803 4229.354 1977.283 22.179 70954.3 115913 134030 18298.9 1.32560567 3.96554245 172.525892 728.137 352.652 319.374 388.655 153.300 98.475 3382724467 53.0510 51.5503 50.4826 49.2181 621820.27 506243.28 353333.76 9151.12 243282.67 81336.72 7322.69 6.54 9040.44 5.3 938.66 51.07 519663.4905 3467303 0.288 132.891 141.745 339.454 28.533 65.430 159.604 36154.9 6735933333 21.727 68.062 64.22 64.60 78.83 4714 18498 2790 5593 686 10948 21999 211.1147 190.0161 235.3684 201.5685 200.9968 11387 114127.1 121765.6 5033.4 5858.1 6630.3 5848.9 83.807218 3501.107 1653.835 19.371 66383.1 126807 147615 12311.0 1.19703488 3.74949122 121.400538 763.648 361.982 322.636 398.272 153.758 88.495 4526544000 68.1100 62.2039 58.8330 69.5167 727314.54 562925.84 402805.72 9261.03 233932.00 87838.87 8124.98 5.90 10005.21 4.79 1065.11 45.03 502329.4249 3427229 0.293 127.865 135.230 333.946 27.597 65.191 156.152 41390.8 7574166667 21.736 68.426 66.12 66.70 71.26 4129 16225 2452 4892 601 9644 19367 236.2182 213.4161 263.8853 226.3855 226.9873 13458 124603.8 133768.7 5468.2 6224.3 6972.9 6284.6 116.15901 5684.005 2227.217 21.951 59986.6 58059.1 61459.5 12273.6 1.28036321 4.56930038 213.559554 424.729 229.199 206.559 217.098 110.010 167.712 3091981500 52.1722 52.7757 52.6000 52.0057 501819.67 598185.37 219855.27 9289.82 249822.83 67108.57 6180.67 10.35 9753.64 6.55 1163.45 54.95 449040.0922 2847041 0.352 150.154 152.370 402.710 33.056 80.491 196.882 19500.1 6452800000 35.104 86.664 59.30 60.70 70.03 3935 15622 2362 4717 582 9255 18453 234.3144 210.2346 254.8691 219.9523 210.7757 8483 88748.3 141784.6 1493.3 2828.6 4833.8 6099.1 115.41027 4962.047 1935.64 20.799 59651.0 56000.1 58015.7 15582.4 1.28601799 4.59087753 237.081622 426.974 234.667 208.484 220.808 112.182 171.079 3009367231 57.2149 508790.75 597743.03 223859.81 9057.55 246501.36 66770.55 7097.48 9.01 10290.10 6.21 1248.90 51.19 402880.3672 2820486 0.356 148.601 148.797 402.386 33.464 80.259 194.909 18353.0 6448133333 34.734 86.693 60.37 59.28 63.97 3582 13981 2138 4282 525 8387 16839 242.5743 216.9415 259.3375 224.0609 222.6037 8410 88765.2 149757.5 1493.0 2844.0 5108.1 6454.4 192.29532 6580.632 2454.147 30.860 40387.7 34833.1 41871.6 16676.7 1.70772321 6.23976103 193.820658 251.569 159.797 128.819 133.919 70.1138 194.174 3076320333 63.6551 61.6504 61.0864 61.3303 335827.19 263499.10 150552.39 3643.82 167917.37 58253.89 3678.64 8.14 7617.07 15.72 692.55 43.11 382936.0068 772029 1.358 174.727 205.435 395.680 35.959 74.278 200.214 17947.3 5662633333 21.716 86.542 32.26 33.02 147.34 6859 27148 4121 8233 1027 16304 32645 125.1909 113.6990 152.4517 131.6672 122.4240 11087 45711.2 61567.6 196.5745 6866.03 43.438 20503.9 29155.1 34120.2 11840.95 1.82508324 6.27515658 157.258347 289.918 177.072 154.346 165.383 83.1382 251.379 3287419800 85.6764 54.7329 47.6945 322599.69 273751.97 176292.33 2867.34 238922.48 48170.79 2888.05 9.67 6216.01 17.98 586.50 47.66 822547.7809 637417 1.594 218.176 256.921 458.506 51.099 80.214 231.605 12708.8 4488833333 27.669 86.562 24.27 24.32 256.12 12189 47356 7375 14270 1832 28382 66114 41.1575 34.7441 39.2181 34.3512 37.2021 5935 28561.9 31710.2 30.513 23471.2 38003.0 46113.0 12870.8 1.35084410 4.45004143 104.391843 415.333 241.480 221.062 227.698 115.197 169.319 5438558200 105.904 407912.91 305114.30 244889.16 3976.14 291332.66 61740.12 3607.03 7.74 7652.31 14.60 688.49 40.60 1244507.9395 653193 1.559 33.086 49.820 134.869 17844.3 5276333333 26.983 85.938 26.69 27.46 199.26 9151 36859 5675 11242 1401 22389 44373 51.0971 46.8092 49.2754 44.5141 54.7857 8193 35445.8 39637.2 OpenBenchmarking.org
OpenFOAM OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.
WRF WRF, the Weather Research and Forecasting Model, is a "next-generation mesoscale numerical weather prediction system designed for both atmospheric research and operational forecasting applications. It features two dynamical cores, a data assimilation system, and a software architecture supporting parallel computation and system extensibility." Learn more via the OpenBenchmarking.org test page.
CP2K Molecular Dynamics CP2K is an open-source molecular dynamics software package focused on quantum chemistry and solid-state physics. More details on the CP2K benchmark test cases and details can be found @ https://www.cp2k.org/performance Learn more via the OpenBenchmarking.org test page.
Input: H2O-DFT-LS
EPYC 7773X 2P: The test quit with a non-zero exit status. E: mpirun noticed that process rank 77 with PID 0 on node phoronix-SYS-221H-TNR exited on signal 9 (Killed).
Xeon Max 9480 2P: The test quit with a non-zero exit status. E: mpirun noticed that process rank 106 with PID 0 on node phoronix-SYS-221H-TNR exited on signal 9 (Killed).
GPAW GPAW is a density-functional theory (DFT) Python code based on the projector-augmented wave (PAW) method and the atomic simulation environment (ASE). Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better GPAW 23.6 Input: Carbon Nanotube EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 10 20 30 40 50 SE +/- 0.13, N = 3 SE +/- 0.13, N = 3 SE +/- 0.04, N = 3 SE +/- 0.31, N = 3 SE +/- 0.26, N = 3 SE +/- 0.23, N = 3 SE +/- 0.03, N = 3 SE +/- 0.24, N = 5 SE +/- 0.26, N = 4 SE +/- 0.14, N = 3 SE +/- 0.56, N = 3 SE +/- 0.08, N = 3 38.21 22.83 22.14 21.54 19.85 22.18 19.37 21.95 20.80 30.86 43.44 30.51 1. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better GPAW 23.6 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 150 300 450 600 750 Min: 76.87 / Avg: 475.2 / Max: 569.09 Min: 52.06 / Avg: 555.48 / Max: 677.65 Min: 57.41 / Avg: 577.21 / Max: 722.55 Min: 63.8 / Avg: 578.23 / Max: 704.8 Min: 60.38 / Avg: 661.16 / Max: 817.57 Min: 113.14 / Avg: 556.84 / Max: 657.81 Min: 65.54 / Avg: 671.39 / Max: 818.94 Min: 43.42 / Avg: 561.8 / Max: 682.39 Min: 55.22 / Avg: 626.04 / Max: 791.1 Min: 198.07 / Avg: 639.24 / Max: 744.18 Min: 303.78 / Avg: 556.38 / Max: 657.29 Min: 289.03 / Avg: 652.98 / Max: 856.85
miniFE MiniFE Finite Element is an application for unstructured implicit finite element codes. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org CG Mflops, More Is Better miniFE 2.2 Problem Size: Small EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 15K 30K 45K 60K 75K SE +/- 570.34, N = 15 SE +/- 436.84, N = 5 SE +/- 176.36, N = 5 SE +/- 540.67, N = 5 SE +/- 1244.67, N = 15 SE +/- 2965.57, N = 12 SE +/- 548.90, N = 15 SE +/- 1371.46, N = 15 SE +/- 491.71, N = 5 SE +/- 243.91, N = 4 SE +/- 640.81, N = 15 SE +/- 537.92, N = 15 23547.7 51915.1 52687.4 55164.1 53638.5 70954.3 66383.1 59986.6 59651.0 40387.7 20503.9 23471.2 1. (CXX) g++ options: -O3 -fopenmp -lmpi_cxx -lmpi
CG Mflops Per Watt
OpenBenchmarking.org CG Mflops Per Watt, More Is Better miniFE 2.2 Problem Size: Small EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 50 100 150 200 250 83.06 205.51 206.22 190.71 181.10 229.79 208.53 246.74 240.11 91.28 41.50 44.66
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better miniFE 2.2 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 130 260 390 520 650 Min: 75.02 / Avg: 283.5 / Max: 484.61 Min: 52.04 / Avg: 253.61 / Max: 467.17 Min: 55.63 / Avg: 255.49 / Max: 475.29 Min: 62.5 / Avg: 289.26 / Max: 567.73 Min: 58.67 / Avg: 296.18 / Max: 594.85 Min: 111.43 / Avg: 308.78 / Max: 612.72 Min: 65.76 / Avg: 318.34 / Max: 691.99 Min: 43.63 / Avg: 243.12 / Max: 499.25 Min: 53 / Avg: 248.43 / Max: 486.52 Min: 189.31 / Avg: 442.47 / Max: 726.32 Min: 309.77 / Avg: 494.12 / Max: 641.85 Min: 279.39 / Avg: 525.56 / Max: 696.94
ASKAP ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Degridding EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 30K 60K 90K 120K 150K SE +/- 298.23, N = 3 SE +/- 509.24, N = 3 SE +/- 289.77, N = 3 SE +/- 1048.90, N = 3 SE +/- 1166.20, N = 3 SE +/- 706.67, N = 3 SE +/- 856.67, N = 3 SE +/- 748.64, N = 15 SE +/- 945.08, N = 15 SE +/- 178.00, N = 3 SE +/- 0.00, N = 3 SE +/- 131.50, N = 3 61441.9 60853.9 60555.6 81812.9 86299.0 115913.0 126807.0 58059.1 56000.1 34833.1 29155.1 38003.0 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
Result
OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Gridding EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 30K 60K 90K 120K 150K SE +/- 336.40, N = 3 SE +/- 423.30, N = 3 SE +/- 861.73, N = 3 SE +/- 742.18, N = 3 SE +/- 1514.53, N = 3 SE +/- 1646.73, N = 3 SE +/- 1162.33, N = 3 SE +/- 804.21, N = 15 SE +/- 977.32, N = 15 SE +/- 0.00, N = 3 SE +/- 105.97, N = 3 SE +/- 193.77, N = 3 65262.5 72808.3 74108.5 89976.4 98445.7 134030.0 147615.0 61459.5 58015.7 41871.6 34120.2 46113.0 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
Mpix/sec Per Watt
OpenBenchmarking.org Mpix/sec Per Watt, More Is Better ASKAP 1.0 Test: tConvolve MPI - Gridding EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 60 120 180 240 300 150.35 165.99 167.73 172.46 180.09 254.09 237.90 125.29 111.03 65.48 61.82 71.27
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ASKAP 1.0 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 140 280 420 560 700 Min: 78.57 / Avg: 434.07 / Max: 556.2 Min: 52.73 / Avg: 438.62 / Max: 647.93 Min: 55.8 / Avg: 441.83 / Max: 691.32 Min: 61.78 / Avg: 521.71 / Max: 674.94 Min: 58.11 / Avg: 546.65 / Max: 813.97 Min: 112.25 / Avg: 527.49 / Max: 668.13 Min: 66.68 / Avg: 620.49 / Max: 819.21 Min: 42.96 / Avg: 490.53 / Max: 657.14 Min: 45.12 / Avg: 522.54 / Max: 783.89 Min: 192.88 / Avg: 639.47 / Max: 729.32 Min: 309.68 / Avg: 551.95 / Max: 597.77 Min: 289.65 / Avg: 647.01 / Max: 741.42
Result
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Degridding EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 4K 8K 12K 16K 20K SE +/- 279.37, N = 9 SE +/- 460.78, N = 3 SE +/- 772.33, N = 9 SE +/- 224.95, N = 3 SE +/- 255.26, N = 3 SE +/- 1833.85, N = 6 SE +/- 80.53, N = 3 SE +/- 79.95, N = 3 SE +/- 1355.45, N = 9 SE +/- 913.08, N = 9 SE +/- 594.43, N = 9 SE +/- 350.77, N = 9 11018.44 12762.40 15165.20 12817.60 11420.40 18298.90 12311.00 12273.60 15582.40 16676.70 11840.95 12870.80 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
Million Grid Points Per Second Per Watt
OpenBenchmarking.org Million Grid Points Per Second Per Watt, More Is Better ASKAP 1.0 Test: tConvolve MT - Degridding EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 13 26 39 52 65 42.06 45.76 54.42 39.62 34.61 53.00 33.53 46.10 58.80 35.35 23.70 24.88
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ASKAP 1.0 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 200 400 600 800 1000 Min: 70.03 / Avg: 261.97 / Max: 505.07 Min: 52.46 / Avg: 278.88 / Max: 477.91 Min: 52.22 / Avg: 278.66 / Max: 517.39 Min: 60.9 / Avg: 323.5 / Max: 541.66 Min: 57.67 / Avg: 329.99 / Max: 564.89 Min: 114.02 / Avg: 345.26 / Max: 629.32 Min: 65.15 / Avg: 367.13 / Max: 617.96 Min: 42.96 / Avg: 266.26 / Max: 451.59 Min: 46.5 / Avg: 265.01 / Max: 549.91 Min: 172.94 / Avg: 471.71 / Max: 754.53 Min: 224.73 / Avg: 499.55 / Max: 759.83 Min: 214.84 / Avg: 517.23 / Max: 1060.63
Xcompact3d Incompact3d Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 129 Cells Per Direction EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 0.5051 1.0102 1.5153 2.0204 2.5255 SE +/- 0.02377940, N = 15 SE +/- 0.01444431, N = 15 SE +/- 0.01579407, N = 15 SE +/- 0.01339425, N = 15 SE +/- 0.01071769, N = 15 SE +/- 0.00998524, N = 15 SE +/- 0.01071562, N = 15 SE +/- 0.00468517, N = 10 SE +/- 0.00914658, N = 9 SE +/- 0.01614121, N = 15 SE +/- 0.02218952, N = 13 SE +/- 0.00626042, N = 10 2.24475327 1.44945346 1.44751305 1.37331832 1.33808986 1.32560567 1.19703488 1.28036321 1.28601799 1.70772321 1.82508324 1.35084410 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 140 280 420 560 700 Min: 75.52 / Avg: 247.72 / Max: 572.02 Min: 51.03 / Avg: 205.91 / Max: 582.31 Min: 50.61 / Avg: 206.49 / Max: 580.24 Min: 61.47 / Avg: 240.74 / Max: 654.19 Min: 58.41 / Avg: 243.94 / Max: 758.18 Min: 104.32 / Avg: 269.9 / Max: 622.79 Min: 64.51 / Avg: 273.28 / Max: 793.09 Min: 44.13 / Avg: 223.82 / Max: 636.41 Min: 45.34 / Avg: 213.26 / Max: 646.84 Min: 195.25 / Avg: 380.49 / Max: 754.71 Min: 308.35 / Avg: 423.29 / Max: 646.9 Min: 288.6 / Avg: 424.68 / Max: 780.04
Result
OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 193 Cells Per Direction EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 3 6 9 12 15 SE +/- 0.07207418, N = 5 SE +/- 0.01651966, N = 7 SE +/- 0.03696191, N = 7 SE +/- 0.01407862, N = 7 SE +/- 0.02775030, N = 7 SE +/- 0.02884245, N = 7 SE +/- 0.02948821, N = 10 SE +/- 0.02745951, N = 7 SE +/- 0.02935664, N = 7 SE +/- 0.01528686, N = 6 SE +/- 0.05183946, N = 6 SE +/- 0.01983325, N = 7 9.62580643 4.80414799 4.90615211 4.19870104 4.19422695 3.96554245 3.74949122 4.56930038 4.59087753 6.23976103 6.27515658 4.45004143 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 140 280 420 560 700 Min: 76.68 / Avg: 382.93 / Max: 541.82 Min: 52.55 / Avg: 322.9 / Max: 570.6 Min: 57.44 / Avg: 331.55 / Max: 587.07 Min: 60.72 / Avg: 361.08 / Max: 647.65 Min: 57.32 / Avg: 379.48 / Max: 750.02 Min: 110.27 / Avg: 374.05 / Max: 634.07 Min: 64.06 / Avg: 429.52 / Max: 809.94 Min: 42.29 / Avg: 334.53 / Max: 611.68 Min: 45.42 / Avg: 334.79 / Max: 628.93 Min: 192.83 / Avg: 510.22 / Max: 747.72 Min: 308.57 / Avg: 488.57 / Max: 670.37 Min: 288.96 / Avg: 514.29 / Max: 728.6
Result
OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: X3D-benchmarking input.i3d EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 60 120 180 240 300 SE +/- 0.60, N = 3 SE +/- 4.96, N = 12 SE +/- 4.85, N = 12 SE +/- 6.85, N = 12 SE +/- 6.42, N = 10 SE +/- 5.14, N = 12 SE +/- 2.39, N = 12 SE +/- 5.48, N = 12 SE +/- 7.88, N = 10 SE +/- 0.05, N = 3 SE +/- 0.27, N = 3 SE +/- 0.40, N = 3 264.85 209.93 210.67 221.99 202.56 172.53 121.40 213.56 237.08 193.82 157.26 104.39 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 200 400 600 800 1000 Min: 76.31 / Avg: 495.89 / Max: 539.44 Min: 52.8 / Avg: 555.71 / Max: 602.08 Min: 54.14 / Avg: 560.24 / Max: 611.03 Min: 62.91 / Avg: 648.46 / Max: 684.86 Min: 58.02 / Avg: 710.68 / Max: 771.3 Min: 112.81 / Avg: 613.76 / Max: 641.22 Min: 64.66 / Avg: 733.16 / Max: 794.25 Min: 44.4 / Avg: 584.45 / Max: 632.47 Min: 45.42 / Avg: 642.84 / Max: 708.21 Min: 198.83 / Avg: 686.16 / Max: 730.73 Min: 274.47 / Avg: 545.88 / Max: 887.32 Min: 290.01 / Avg: 689.98 / Max: 1116.33
HeFFTe - Highly Efficient FFT for Exascale HeFFTe is the Highly Efficient FFT for Exascale software developed as part of the Exascale Computing Project. This test profile uses HeFFTe's built-in speed benchmarks under a variety of configuration options and currently catering to CPU/processor testing. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GFLOP/s, More Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 Test: r2c - Backend: FFTW - Precision: float - X Y Z: 512 EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 160 320 480 640 800 SE +/- 0.38, N = 6 SE +/- 1.93, N = 7 SE +/- 3.25, N = 7 SE +/- 3.25, N = 8 SE +/- 2.70, N = 8 SE +/- 4.79, N = 8 SE +/- 4.08, N = 9 SE +/- 1.85, N = 7 SE +/- 1.06, N = 7 SE +/- 0.48, N = 5 SE +/- 3.18, N = 15 SE +/- 6.55, N = 15 304.97 477.76 480.33 555.83 566.20 728.14 763.65 424.73 426.97 251.57 289.92 415.33 1. (CXX) g++ options: -O3
GFLOP/s Per Watt
OpenBenchmarking.org GFLOP/s Per Watt, More Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 Test: r2c - Backend: FFTW - Precision: float - X Y Z: 512 EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 0.5006 1.0012 1.5018 2.0024 2.503 0.874 1.663 1.720 1.688 1.631 2.225 2.174 1.251 1.232 0.483 0.590 0.803
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 160 320 480 640 800 Min: 76.53 / Avg: 349.12 / Max: 559.83 Min: 51.61 / Avg: 287.34 / Max: 578.48 Min: 50.57 / Avg: 279.34 / Max: 580.98 Min: 60.57 / Avg: 329.25 / Max: 647.96 Min: 58.38 / Avg: 347.19 / Max: 750 Min: 102.42 / Avg: 327.3 / Max: 640.54 Min: 63.51 / Avg: 351.31 / Max: 798.16 Min: 43.07 / Avg: 339.49 / Max: 628.7 Min: 47.43 / Avg: 346.59 / Max: 686.84 Min: 193.04 / Avg: 520.73 / Max: 747.88 Min: 308.97 / Avg: 491.24 / Max: 781.19 Min: 289.8 / Avg: 517.18 / Max: 934.32
Result
OpenBenchmarking.org GFLOP/s, More Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 Test: r2c - Backend: FFTW - Precision: double - X Y Z: 256 EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 80 160 240 320 400 SE +/- 1.16, N = 10 SE +/- 3.53, N = 15 SE +/- 2.88, N = 15 SE +/- 2.63, N = 15 SE +/- 6.03, N = 15 SE +/- 1.76, N = 11 SE +/- 1.58, N = 11 SE +/- 0.80, N = 10 SE +/- 1.25, N = 10 SE +/- 0.79, N = 10 SE +/- 3.36, N = 15 SE +/- 2.97, N = 15 149.95 305.72 311.87 349.10 345.25 352.65 361.98 229.20 234.67 159.80 177.07 241.48 1. (CXX) g++ options: -O3
GFLOP/s Per Watt
OpenBenchmarking.org GFLOP/s Per Watt, More Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 Test: r2c - Backend: FFTW - Precision: double - X Y Z: 256 EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 0.4615 0.923 1.3845 1.846 2.3075 0.771 2.051 2.029 1.873 1.937 1.602 1.756 1.158 1.231 0.450 0.439 0.609
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 130 260 390 520 650 Min: 75.51 / Avg: 194.48 / Max: 519.36 Min: 27.4 / Avg: 149.05 / Max: 471.55 Min: 49.49 / Avg: 153.74 / Max: 474.17 Min: 60.35 / Avg: 186.34 / Max: 540.38 Min: 57 / Avg: 178.25 / Max: 662.8 Min: 93.2 / Avg: 220.15 / Max: 520.63 Min: 62.9 / Avg: 206.18 / Max: 602.52 Min: 42.05 / Avg: 197.99 / Max: 615.41 Min: 47.06 / Avg: 190.68 / Max: 660.08 Min: 195.09 / Avg: 355.45 / Max: 754.7 Min: 308.79 / Avg: 403.24 / Max: 644.97 Min: 288.1 / Avg: 396.28 / Max: 729.47
Result
OpenBenchmarking.org GFLOP/s, More Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 Test: r2c - Backend: FFTW - Precision: double - X Y Z: 512 EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 70 140 210 280 350 SE +/- 0.34, N = 4 SE +/- 0.31, N = 5 SE +/- 1.23, N = 5 SE +/- 1.03, N = 5 SE +/- 0.91, N = 5 SE +/- 2.12, N = 6 SE +/- 2.22, N = 6 SE +/- 0.88, N = 5 SE +/- 1.19, N = 5 SE +/- 0.63, N = 4 SE +/- 1.72, N = 15 SE +/- 2.98, N = 12 125.11 235.83 235.96 251.05 253.79 319.37 322.64 206.56 208.48 128.82 154.35 221.06 1. (CXX) g++ options: -O3
GFLOP/s Per Watt
OpenBenchmarking.org GFLOP/s Per Watt, More Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 Test: r2c - Backend: FFTW - Precision: double - X Y Z: 512 EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 0.1735 0.347 0.5205 0.694 0.8675 0.297 0.704 0.697 0.613 0.600 0.771 0.690 0.512 0.498 0.221 0.304 0.386
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 200 400 600 800 1000 Min: 76.8 / Avg: 421.2 / Max: 546.28 Min: 51.01 / Avg: 335.22 / Max: 537.39 Min: 50.59 / Avg: 338.68 / Max: 552.93 Min: 60.96 / Avg: 409.3 / Max: 640.96 Min: 57.67 / Avg: 423.31 / Max: 728.03 Min: 58.32 / Avg: 414.19 / Max: 638.48 Min: 64.47 / Avg: 467.42 / Max: 789.28 Min: 41.93 / Avg: 403.47 / Max: 601.74 Min: 48.47 / Avg: 418.77 / Max: 642.04 Min: 198.7 / Avg: 583.2 / Max: 736.8 Min: 292.69 / Avg: 508.43 / Max: 721.34 Min: 288.96 / Avg: 572.88 / Max: 1052.21
Result
OpenBenchmarking.org GFLOP/s, More Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 Test: c2c - Backend: FFTW - Precision: float - X Y Z: 512 EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 90 180 270 360 450 SE +/- 1.32, N = 4 SE +/- 1.99, N = 5 SE +/- 1.21, N = 5 SE +/- 1.04, N = 6 SE +/- 1.26, N = 6 SE +/- 2.14, N = 7 SE +/- 1.84, N = 7 SE +/- 1.41, N = 5 SE +/- 1.16, N = 5 SE +/- 0.40, N = 4 SE +/- 1.96, N = 4 SE +/- 1.58, N = 13 146.16 247.15 249.47 278.87 281.56 388.66 398.27 217.10 220.81 133.92 165.38 227.70 1. (CXX) g++ options: -O3
GFLOP/s Per Watt
OpenBenchmarking.org GFLOP/s Per Watt, More Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 Test: c2c - Backend: FFTW - Precision: float - X Y Z: 512 EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 0.2196 0.4392 0.6588 0.8784 1.098 0.353 0.736 0.752 0.688 0.667 0.976 0.892 0.549 0.537 0.229 0.321 0.404
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 160 320 480 640 800 Min: 75.74 / Avg: 413.52 / Max: 551.49 Min: 52.2 / Avg: 335.98 / Max: 560.01 Min: 56.96 / Avg: 331.92 / Max: 552.59 Min: 63.94 / Avg: 405.62 / Max: 638.08 Min: 58.47 / Avg: 422.07 / Max: 728.72 Min: 110.21 / Avg: 398.24 / Max: 638.12 Min: 63.41 / Avg: 446.67 / Max: 791.11 Min: 44.06 / Avg: 395.68 / Max: 611.7 Min: 44.82 / Avg: 411.07 / Max: 658.47 Min: 191.88 / Avg: 584.05 / Max: 738.4 Min: 309.8 / Avg: 515.6 / Max: 650.09 Min: 289.21 / Avg: 564.08 / Max: 904.76
Result
OpenBenchmarking.org GFLOP/s, More Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 Test: c2c - Backend: FFTW - Precision: double - X Y Z: 512 EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 30 60 90 120 150 SE +/- 0.12, N = 3 SE +/- 0.88, N = 4 SE +/- 1.45, N = 4 SE +/- 0.69, N = 4 SE +/- 0.45, N = 4 SE +/- 1.05, N = 4 SE +/- 0.31, N = 4 SE +/- 1.36, N = 3 SE +/- 0.22, N = 3 SE +/- 0.23, N = 3 SE +/- 0.70, N = 15 SE +/- 1.62, N = 3 61.00 127.81 127.40 132.06 133.52 153.30 153.76 110.01 112.18 70.11 83.14 115.20 1. (CXX) g++ options: -O3
GFLOP/s Per Watt
OpenBenchmarking.org GFLOP/s Per Watt, More Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 Test: c2c - Backend: FFTW - Precision: double - X Y Z: 512 EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 0.0763 0.1526 0.2289 0.3052 0.3815 0.133 0.339 0.334 0.280 0.271 0.320 0.280 0.249 0.238 0.112 0.155 0.187
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 150 300 450 600 750 Min: 75.98 / Avg: 457.76 / Max: 538.09 Min: 51.21 / Avg: 377.46 / Max: 533.09 Min: 50.78 / Avg: 381.2 / Max: 552.17 Min: 60.35 / Avg: 472.11 / Max: 624.79 Min: 59.56 / Avg: 493.35 / Max: 710.69 Min: 102.34 / Avg: 478.92 / Max: 634.84 Min: 67.61 / Avg: 548.72 / Max: 764 Min: 41.02 / Avg: 441.33 / Max: 588.46 Min: 45.82 / Avg: 470.89 / Max: 646.61 Min: 197.43 / Avg: 624.7 / Max: 728.83 Min: 138.49 / Avg: 535.06 / Max: 837.42 Min: 289.47 / Avg: 615.72 / Max: 864.46
RELION RELION - REgularised LIkelihood OptimisatioN - is a stand-alone computer program for Maximum A Posteriori refinement of (multiple) 3D reconstructions or 2D class averages in cryo-electron microscopy (cryo-EM). It is developed in the research group of Sjors Scheres at the MRC Laboratory of Molecular Biology. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better RELION 4.0.1 Test: Basic - Device: CPU EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 50 100 150 200 250 SE +/- 2.23, N = 3 SE +/- 2.02, N = 3 SE +/- 1.64, N = 12 SE +/- 1.05, N = 3 SE +/- 3.12, N = 12 SE +/- 1.08, N = 15 SE +/- 0.64, N = 15 SE +/- 4.04, N = 12 SE +/- 5.96, N = 12 SE +/- 3.19, N = 12 SE +/- 1.06, N = 3 SE +/- 2.20, N = 3 155.50 141.49 140.52 120.44 138.41 98.48 88.50 167.71 171.08 194.17 251.38 169.32 1. (CXX) g++ options: -fopenmp -std=c++11 -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -ljpeg -lmpi_cxx -lmpi
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better RELION 4.0.1 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 140 280 420 560 700 Min: 74.95 / Avg: 546.31 / Max: 572.75 Min: 53.92 / Avg: 617.17 / Max: 689.59 Min: 56.42 / Avg: 660.09 / Max: 714.99 Min: 61.55 / Avg: 627.16 / Max: 713.65 Min: 60.79 / Avg: 723.77 / Max: 819.03 Min: 113.74 / Avg: 627.68 / Max: 666.42 Min: 64.1 / Avg: 765.54 / Max: 819.44 Min: 43.82 / Avg: 569.08 / Max: 686.87 Min: 52.16 / Avg: 578.71 / Max: 809.69 Min: 195.45 / Avg: 683.68 / Max: 754.92 Min: 275.62 / Avg: 580.93 / Max: 700.21 Min: 289.27 / Avg: 686.24 / Max: 765.4
Algebraic Multi-Grid Benchmark AMG is a parallel algebraic multigrid solver for linear systems arising from problems on unstructured grids. The driver provided with AMG builds linear systems for various 3-dimensional problems. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Figure Of Merit, More Is Better Algebraic Multi-Grid Benchmark 1.2 EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 1200M 2400M 3600M 4800M 6000M SE +/- 2267723.11, N = 3 SE +/- 49833209.25, N = 12 SE +/- 36198694.29, N = 15 SE +/- 54793231.38, N = 15 SE +/- 59753635.01, N = 13 SE +/- 93606095.21, N = 15 SE +/- 9434203.22, N = 3 SE +/- 44262083.97, N = 14 SE +/- 46561867.68, N = 13 SE +/- 5128608.17, N = 3 SE +/- 39591478.78, N = 15 SE +/- 54284212.92, N = 5 1988543333 3911914333 3948722533 3235269000 2872242308 3382724467 4526544000 3091981500 3009367231 3076320333 3287419800 5438558200 1. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi
Figure Of Merit Per Watt
OpenBenchmarking.org Figure Of Merit Per Watt, More Is Better Algebraic Multi-Grid Benchmark 1.2 EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 2M 4M 6M 8M 10M 4723406.26 8542003.87 8504327.34 5954295.35 4711726.92 6301791.10 7358994.28 6114789.83 5552079.16 5018378.41 6683607.66 9111436.68
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Algebraic Multi-Grid Benchmark 1.2 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 140 280 420 560 700 Min: 75.05 / Avg: 421 / Max: 541.93 Min: 52.38 / Avg: 457.96 / Max: 601.19 Min: 52.33 / Avg: 464.32 / Max: 635.07 Min: 62.05 / Avg: 543.35 / Max: 652.92 Min: 59.59 / Avg: 609.59 / Max: 749.68 Min: 115.47 / Avg: 536.79 / Max: 637.17 Min: 67.23 / Avg: 615.1 / Max: 775.7 Min: 43.27 / Avg: 505.66 / Max: 632.39 Min: 52.59 / Avg: 542.03 / Max: 694.43 Min: 201.24 / Avg: 613.01 / Max: 729.78 Min: 272.72 / Avg: 491.86 / Max: 621.77 Min: 290.07 / Avg: 596.89 / Max: 745.38
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 X Y Z: 104 104 104 - RT: 60 EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 20 40 60 80 100 SE +/- 0.01, N = 3 SE +/- 0.40, N = 12 SE +/- 0.95, N = 12 SE +/- 0.70, N = 3 SE +/- 0.38, N = 9 SE +/- 0.16, N = 3 SE +/- 0.75, N = 9 SE +/- 0.47, N = 3 SE +/- 0.14, N = 3 SE +/- 0.52, N = 3 SE +/- 1.53, N = 12 38.53 56.06 56.47 50.66 47.15 53.05 68.11 52.17 57.21 63.66 85.68 105.90 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi
GFLOP/s Per Watt
OpenBenchmarking.org GFLOP/s Per Watt, More Is Better High Performance Conjugate Gradient 3.1 X Y Z: 104 104 104 - RT: 60 EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 0.0619 0.1238 0.1857 0.2476 0.3095 0.085 0.104 0.104 0.083 0.071 0.090 0.096 0.096 0.275 0.093 0.157 0.153
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better High Performance Conjugate Gradient 3.1 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 200 400 600 800 1000 Min: 75.69 / Avg: 455.66 / Max: 557.23 Min: 51.38 / Avg: 537.49 / Max: 613.81 Min: 50.77 / Avg: 540.82 / Max: 626.47 Min: 62.75 / Avg: 611.13 / Max: 663.73 Min: 60.3 / Avg: 663.62 / Max: 787.4 Min: 118.87 / Avg: 587.13 / Max: 623.16 Min: 67.62 / Avg: 711.65 / Max: 801.75 Min: 44.28 / Avg: 546.24 / Max: 649.47 Min: 42.28 / Avg: 208.23 / Max: 735.95 Min: 201.54 / Avg: 685.34 / Max: 722.58 Min: 272.37 / Avg: 545.82 / Max: 603.19 Min: 290.07 / Avg: 690.42 / Max: 1240.53
Result
OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 X Y Z: 144 144 144 - RT: 60 EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P 14 28 42 56 70 SE +/- 0.03, N = 3 SE +/- 0.16, N = 3 SE +/- 0.15, N = 3 SE +/- 0.27, N = 3 SE +/- 0.06, N = 3 SE +/- 0.21, N = 3 SE +/- 0.99, N = 9 SE +/- 0.10, N = 3 SE +/- 0.09, N = 3 SE +/- 0.40, N = 3 38.31 54.61 54.49 50.12 43.76 51.55 62.20 52.78 61.65 54.73 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi
GFLOP/s Per Watt
OpenBenchmarking.org GFLOP/s Per Watt, More Is Better High Performance Conjugate Gradient 3.1 X Y Z: 144 144 144 - RT: 60 EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P 0.0227 0.0454 0.0681 0.0908 0.1135 0.083 0.099 0.099 0.081 0.064 0.087 0.086 0.096 0.089 0.101
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better High Performance Conjugate Gradient 3.1 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P 140 280 420 560 700 Min: 76.42 / Avg: 463 / Max: 553.18 Min: 52.24 / Avg: 548.85 / Max: 627.94 Min: 57.46 / Avg: 549.49 / Max: 633.34 Min: 62.61 / Avg: 618.71 / Max: 690.03 Min: 60.03 / Avg: 682.8 / Max: 793.83 Min: 107.47 / Avg: 592.74 / Max: 640.1 Min: 66.11 / Avg: 721 / Max: 810.75 Min: 47.04 / Avg: 551.01 / Max: 644 Min: 199.6 / Avg: 691.01 / Max: 732.89 Min: 276.28 / Avg: 541.57 / Max: 611.8
X Y Z: 144 144 144 - RT: 60
EPYC 9754 2P - Power 400W: The test run did not produce a result. E: sh: 1: exec: ./hpcg: not found
Result
OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 X Y Z: 160 160 160 - RT: 60 EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P 14 28 42 56 70 SE +/- 0.01, N = 3 SE +/- 0.15, N = 3 SE +/- 0.28, N = 3 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 SE +/- 0.23, N = 3 SE +/- 1.00, N = 9 SE +/- 0.35, N = 3 SE +/- 0.49, N = 3 SE +/- 0.03, N = 3 38.17 53.21 54.20 49.89 43.55 50.48 58.83 52.60 61.09 47.69 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi
GFLOP/s Per Watt
OpenBenchmarking.org GFLOP/s Per Watt, More Is Better High Performance Conjugate Gradient 3.1 X Y Z: 160 160 160 - RT: 60 EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P 0.0218 0.0436 0.0654 0.0872 0.109 0.082 0.096 0.097 0.081 0.064 0.085 0.081 0.095 0.088 0.088
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better High Performance Conjugate Gradient 3.1 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P 140 280 420 560 700 Min: 76.49 / Avg: 466.52 / Max: 566.01 Min: 52.38 / Avg: 552.4 / Max: 653.93 Min: 50.75 / Avg: 557.31 / Max: 659.18 Min: 62.54 / Avg: 619.55 / Max: 690.02 Min: 58.63 / Avg: 683.63 / Max: 800.97 Min: 103.45 / Avg: 594.96 / Max: 641.79 Min: 66.83 / Avg: 725.32 / Max: 817.34 Min: 45.03 / Avg: 552.16 / Max: 650.63 Min: 200.47 / Avg: 692.87 / Max: 734.47 Min: 274.01 / Avg: 542.3 / Max: 598.17
X Y Z: 160 160 160 - RT: 60
EPYC 9754 2P - Power 400W: The test run did not produce a result. E: sh: 1: exec: ./hpcg: not found
Result
OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 X Y Z: 192 192 192 - RT: 60 EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P Xeon Platinum 8490H 2P 15 30 45 60 75 SE +/- 0.32, N = 3 SE +/- 0.22, N = 3 SE +/- 0.64, N = 9 SE +/- 0.07, N = 3 SE +/- 0.17, N = 3 SE +/- 0.70, N = 6 SE +/- 0.45, N = 3 SE +/- 0.41, N = 3 54.70 52.76 43.38 43.01 49.22 69.52 52.01 61.33 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi
GFLOP/s Per Watt
OpenBenchmarking.org GFLOP/s Per Watt, More Is Better High Performance Conjugate Gradient 3.1 X Y Z: 192 192 192 - RT: 60 EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P Xeon Platinum 8490H 2P 0.0223 0.0446 0.0669 0.0892 0.1115 0.099 0.094 0.071 0.063 0.082 0.096 0.093 0.088
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better High Performance Conjugate Gradient 3.1 CPU Power Consumption Monitor EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P Xeon Platinum 8490H 2P 140 280 420 560 700 Min: 50.89 / Avg: 551.62 / Max: 652.66 Min: 53.78 / Avg: 559.48 / Max: 697.45 Min: 62.44 / Avg: 610.35 / Max: 704.59 Min: 59.41 / Avg: 684.19 / Max: 813.81 Min: 110.35 / Avg: 596.66 / Max: 647.4 Min: 65.23 / Avg: 720.56 / Max: 817.89 Min: 44.16 / Avg: 558.52 / Max: 659.8 Min: 202.08 / Avg: 694.66 / Max: 719.74
X Y Z: 192 192 192 - RT: 60
EPYC 7773X 2P: The test quit with a non-zero exit status. E: cat: 'HPCG-Benchmark*.txt': No such file or directory
EPYC 9754 2P - Power 400W: The test run did not produce a result. E: sh: 1: exec: ./hpcg: not found
Xeon Max 9480 2P: The test quit with a non-zero exit status. E: cat: 'HPCG-Benchmark*.txt': No such file or directory
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 160K 320K 480K 640K 800K SE +/- 1238.38, N = 5 SE +/- 2209.25, N = 6 SE +/- 1894.85, N = 6 SE +/- 2609.81, N = 6 SE +/- 2687.60, N = 7 SE +/- 4824.10, N = 15 SE +/- 2463.95, N = 7 SE +/- 4198.29, N = 15 SE +/- 4835.04, N = 15 SE +/- 807.78, N = 5 SE +/- 1676.04, N = 5 SE +/- 320.97, N = 6 375894.53 466102.69 461016.80 513456.93 556402.91 621820.27 727314.54 501819.67 508790.75 335827.19 322599.69 407912.91 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.4
Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 400 800 1200 1600 2000 974.31 1198.19 1186.01 1268.28 1236.88 1553.01 1690.64 1275.38 1200.42 619.80 632.95 730.82
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 140 280 420 560 700 Min: 75.13 / Avg: 385.8 / Max: 573.63 Min: 51.35 / Avg: 389.01 / Max: 634.97 Min: 55.36 / Avg: 388.71 / Max: 648.29 Min: 61.61 / Avg: 404.84 / Max: 662.04 Min: 58.22 / Avg: 449.84 / Max: 809.4 Min: 99.61 / Avg: 400.4 / Max: 643.9 Min: 65.16 / Avg: 430.2 / Max: 819.67 Min: 41.95 / Avg: 393.47 / Max: 658.97 Min: 48.16 / Avg: 423.84 / Max: 763.5 Min: 194.95 / Avg: 541.84 / Max: 754.83 Min: 310.8 / Avg: 509.68 / Max: 600.11 Min: 288.41 / Avg: 558.16 / Max: 751.51
Result
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 130K 260K 390K 520K 650K SE +/- 5780.29, N = 15 SE +/- 3539.12, N = 15 SE +/- 4424.60, N = 7 SE +/- 3172.98, N = 7 SE +/- 4093.98, N = 7 SE +/- 4498.91, N = 7 SE +/- 4343.25, N = 8 SE +/- 7170.23, N = 12 SE +/- 2807.48, N = 7 SE +/- 331.60, N = 5 SE +/- 1520.10, N = 6 SE +/- 213.51, N = 6 395342.95 480255.42 486004.49 503710.85 517505.91 506243.28 562925.84 598185.37 597743.03 263499.10 273751.97 305114.30 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.4
Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 400 800 1200 1600 2000 1160.08 1425.55 1438.18 1454.66 1437.82 1423.34 1414.44 1826.88 1723.70 505.76 552.82 561.23
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 130 260 390 520 650 Min: 75.99 / Avg: 340.79 / Max: 574.89 Min: 51.41 / Avg: 336.89 / Max: 632.31 Min: 50.35 / Avg: 337.93 / Max: 639.34 Min: 61.16 / Avg: 346.28 / Max: 628.16 Min: 57.95 / Avg: 359.92 / Max: 687.01 Min: 110.23 / Avg: 355.67 / Max: 599.44 Min: 63.28 / Avg: 397.99 / Max: 749.66 Min: 43.14 / Avg: 327.44 / Max: 654.93 Min: 44.79 / Avg: 346.78 / Max: 736.65 Min: 193.49 / Avg: 521 / Max: 710.8 Min: 309.42 / Avg: 495.2 / Max: 605.36 Min: 289.65 / Avg: 543.66 / Max: 703.68
Result
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 90K 180K 270K 360K 450K SE +/- 1149.47, N = 6 SE +/- 1003.27, N = 6 SE +/- 674.41, N = 6 SE +/- 1413.59, N = 6 SE +/- 1050.85, N = 6 SE +/- 912.34, N = 7 SE +/- 2287.87, N = 8 SE +/- 1446.03, N = 6 SE +/- 1347.73, N = 6 SE +/- 176.69, N = 5 SE +/- 1735.47, N = 5 SE +/- 1541.94, N = 6 230772.86 244961.40 247051.81 269429.29 272856.60 353333.76 402805.72 219855.27 223859.81 150552.39 176292.33 244889.16 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.4
Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 200 400 600 800 1000 640.32 664.55 659.87 687.27 616.59 925.30 949.69 545.21 544.23 272.93 350.71 452.18
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 140 280 420 560 700 Min: 76.23 / Avg: 360.4 / Max: 573.64 Min: 51.84 / Avg: 368.61 / Max: 641.71 Min: 49.78 / Avg: 374.4 / Max: 639.97 Min: 61.64 / Avg: 392.03 / Max: 665.34 Min: 58.3 / Avg: 442.52 / Max: 803.87 Min: 108.13 / Avg: 381.86 / Max: 654.82 Min: 64.29 / Avg: 424.14 / Max: 818.64 Min: 43.13 / Avg: 403.25 / Max: 655.03 Min: 46.95 / Avg: 411.33 / Max: 717.04 Min: 194.97 / Avg: 551.62 / Max: 754.01 Min: 309.82 / Avg: 502.67 / Max: 612.08 Min: 290.37 / Avg: 541.57 / Max: 756.78
Result
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 2K 4K 6K 8K 10K SE +/- 69.03, N = 15 SE +/- 198.65, N = 15 SE +/- 127.05, N = 15 SE +/- 169.13, N = 15 SE +/- 169.04, N = 15 SE +/- 227.70, N = 15 SE +/- 297.02, N = 15 SE +/- 146.87, N = 15 SE +/- 192.87, N = 15 SE +/- 19.30, N = 4 SE +/- 149.62, N = 15 SE +/- 232.54, N = 15 5104.50 7725.20 7582.72 7816.33 7697.45 9151.12 9261.03 9289.82 9057.55 3643.82 2867.34 3976.14 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.4
Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 7 14 21 28 35 16.302 27.617 26.454 24.999 25.275 28.442 27.551 29.119 27.719 7.247 5.505 7.145
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 130 260 390 520 650 Min: 75.34 / Avg: 313.13 / Max: 540.33 Min: 50.85 / Avg: 279.72 / Max: 571.62 Min: 50.56 / Avg: 286.64 / Max: 586.7 Min: 62.05 / Avg: 312.66 / Max: 592.38 Min: 58.95 / Avg: 304.55 / Max: 634.68 Min: 102.23 / Avg: 321.74 / Max: 579.82 Min: 64.83 / Avg: 336.14 / Max: 677.28 Min: 42.76 / Avg: 319.03 / Max: 648.26 Min: 47.42 / Avg: 326.76 / Max: 695.89 Min: 197.95 / Avg: 502.83 / Max: 704.5 Min: 279.82 / Avg: 520.84 / Max: 752.65 Min: 290.42 / Avg: 556.48 / Max: 748.04
Result
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 60K 120K 180K 240K 300K SE +/- 816.89, N = 14 SE +/- 1627.62, N = 15 SE +/- 2528.43, N = 15 SE +/- 2856.20, N = 15 SE +/- 1682.35, N = 15 SE +/- 4555.29, N = 15 SE +/- 5124.21, N = 15 SE +/- 1814.99, N = 11 SE +/- 3185.64, N = 15 SE +/- 931.04, N = 11 SE +/- 2783.68, N = 15 SE +/- 1216.61, N = 12 124155.94 233525.20 238244.69 207828.63 202036.80 243282.67 233932.00 249822.83 246501.36 167917.37 238922.48 291332.66 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.4
Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 300 600 900 1200 1500 619.97 1507.20 1442.52 1034.00 1105.36 1094.35 1065.73 1387.33 1450.36 515.35 614.71 754.05
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 120 240 360 480 600 Min: 75.95 / Avg: 200.26 / Max: 543.85 Min: 50.72 / Avg: 154.94 / Max: 494.76 Min: 50.65 / Avg: 165.16 / Max: 489.4 Min: 61.27 / Avg: 200.99 / Max: 570.69 Min: 57.39 / Avg: 182.78 / Max: 600.07 Min: 105.65 / Avg: 222.31 / Max: 545.81 Min: 64.64 / Avg: 219.51 / Max: 644.85 Min: 43.35 / Avg: 180.07 / Max: 518.57 Min: 44.53 / Avg: 169.96 / Max: 548.76 Min: 193.79 / Avg: 325.83 / Max: 696.29 Min: 310.03 / Avg: 388.67 / Max: 578.93 Min: 288.72 / Avg: 386.36 / Max: 647.79
Result
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 20K 40K 60K 80K 100K SE +/- 372.47, N = 11 SE +/- 732.46, N = 15 SE +/- 898.57, N = 15 SE +/- 756.73, N = 15 SE +/- 1489.58, N = 15 SE +/- 812.95, N = 15 SE +/- 1142.40, N = 15 SE +/- 387.99, N = 8 SE +/- 516.11, N = 8 SE +/- 116.10, N = 9 SE +/- 324.14, N = 8 SE +/- 245.57, N = 9 51653.20 87564.20 86896.70 84056.04 86108.56 81336.72 87838.87 67108.57 66770.55 58253.89 48170.79 61740.12 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.4
Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 80 160 240 320 400 207.51 372.08 359.44 318.73 335.66 285.50 300.13 244.35 251.69 140.70 105.24 130.24
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 130 260 390 520 650 Min: 76.36 / Avg: 248.92 / Max: 525.8 Min: 50.37 / Avg: 235.34 / Max: 656.75 Min: 53.19 / Avg: 241.76 / Max: 657.59 Min: 61.62 / Avg: 263.72 / Max: 649.57 Min: 57.89 / Avg: 256.54 / Max: 695.38 Min: 110.95 / Avg: 284.89 / Max: 611.14 Min: 63.09 / Avg: 292.67 / Max: 756.55 Min: 43.02 / Avg: 274.64 / Max: 643.58 Min: 47.25 / Avg: 265.29 / Max: 696.85 Min: 101.45 / Avg: 414.04 / Max: 754.25 Min: 308.9 / Avg: 457.73 / Max: 621.83 Min: 289.01 / Avg: 474.04 / Max: 754.98
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Vehicle Detection FP16 - Device: CPU EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 2K 4K 6K 8K 10K SE +/- 4.41, N = 3 SE +/- 4.86, N = 3 SE +/- 9.27, N = 3 SE +/- 0.73, N = 3 SE +/- 1.84, N = 3 SE +/- 4.86, N = 3 SE +/- 59.43, N = 15 SE +/- 6.01, N = 3 SE +/- 1.48, N = 3 SE +/- 5.45, N = 3 SE +/- 4.09, N = 3 5986.33 6269.79 7369.29 7969.63 7322.69 8124.98 6180.67 7097.48 3678.64 2888.05 3607.03 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Vehicle Detection FP16 - Device: CPU EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.09, N = 15 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 5.33 5.09 6.50 6.01 6.54 5.90 10.35 9.01 8.14 9.67 7.74 MIN: 4.91 / MAX: 41.3 MIN: 4.92 / MAX: 33.49 MIN: 4.98 / MAX: 54.72 MIN: 4.98 / MAX: 58.98 MIN: 4.9 / MAX: 53.1 MIN: 4.91 / MAX: 56.09 MIN: 6.16 / MAX: 86.39 MIN: 6.22 / MAX: 79.34 MIN: 7.19 / MAX: 56.27 MIN: 7.08 / MAX: 76.72 MIN: 6.8 / MAX: 72.28 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.3 CPU Power Consumption Monitor EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 140 280 420 560 700 Min: 53.13 / Avg: 627.22 / Max: 677.11 Min: 52.22 / Avg: 704.38 / Max: 757.93 Min: 65.89 / Avg: 640.97 / Max: 691.48 Min: 60.6 / Avg: 741.68 / Max: 808.86 Min: 116.06 / Avg: 613.76 / Max: 657.75 Min: 66.85 / Avg: 729.92 / Max: 801.02 Min: 43.69 / Avg: 614.81 / Max: 678.08 Min: 52.7 / Avg: 720.33 / Max: 808.82 Min: 201.15 / Avg: 663.96 / Max: 752.87 Min: 309.31 / Avg: 572.83 / Max: 654.12 Min: 288.6 / Avg: 669.09 / Max: 756.3
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Person Vehicle Bike Detection FP16 - Device: CPU EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 2K 4K 6K 8K 10K SE +/- 3.86, N = 3 SE +/- 6.85, N = 3 SE +/- 6.84, N = 3 SE +/- 6.54, N = 3 SE +/- 3.29, N = 3 SE +/- 11.35, N = 3 SE +/- 11.29, N = 3 SE +/- 8.20, N = 3 SE +/- 0.62, N = 3 SE +/- 30.37, N = 3 SE +/- 5.68, N = 3 7429.33 7536.10 9128.21 9766.42 9040.44 10005.21 9753.64 10290.10 7617.07 6216.01 7652.31 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Person Vehicle Bike Detection FP16 - Device: CPU EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 4 8 12 16 20 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.09, N = 3 SE +/- 0.01, N = 3 4.30 4.24 5.25 4.91 5.30 4.79 6.55 6.21 15.72 17.98 14.60 MIN: 4.13 / MAX: 22.63 MIN: 4.09 / MAX: 21.93 MIN: 4.36 / MAX: 36.19 MIN: 4.36 / MAX: 20.8 MIN: 4.47 / MAX: 37.31 MIN: 4.34 / MAX: 21.51 MIN: 5.82 / MAX: 56.8 MIN: 5.67 / MAX: 53.74 MIN: 12.18 / MAX: 76.76 MIN: 12.98 / MAX: 146.53 MIN: 12.54 / MAX: 125.98 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.3 CPU Power Consumption Monitor EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 140 280 420 560 700 Min: 55.54 / Avg: 587.59 / Max: 645.98 Min: 57.17 / Avg: 601.24 / Max: 652.47 Min: 64.35 / Avg: 602.8 / Max: 665.93 Min: 60.98 / Avg: 676.19 / Max: 752.33 Min: 107.69 / Avg: 580.78 / Max: 630.49 Min: 66.57 / Avg: 724.66 / Max: 802.23 Min: 44.57 / Avg: 561.61 / Max: 628.41 Min: 53.33 / Avg: 628.04 / Max: 704.62 Min: 200.92 / Avg: 636.88 / Max: 752.71 Min: 269.92 / Avg: 536.66 / Max: 638 Min: 289.56 / Avg: 648.17 / Max: 757.3
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Machine Translation EN To DE FP16 - Device: CPU EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 300 600 900 1200 1500 SE +/- 0.88, N = 3 SE +/- 1.12, N = 3 SE +/- 2.56, N = 3 SE +/- 2.52, N = 3 SE +/- 3.23, N = 3 SE +/- 1.70, N = 3 SE +/- 0.76, N = 3 SE +/- 4.41, N = 3 SE +/- 2.82, N = 3 SE +/- 1.71, N = 3 SE +/- 2.83, N = 3 780.72 804.67 953.22 1001.16 938.66 1065.11 1163.45 1248.90 692.55 586.50 688.49 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Machine Translation EN To DE FP16 - Device: CPU EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 12 24 36 48 60 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.14, N = 3 SE +/- 0.13, N = 3 SE +/- 0.18, N = 3 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.18, N = 3 SE +/- 0.18, N = 3 SE +/- 0.14, N = 3 SE +/- 0.17, N = 3 40.94 39.72 50.30 47.89 51.07 45.03 54.95 51.19 43.11 47.66 40.60 MIN: 35.1 / MAX: 136.15 MIN: 34.37 / MAX: 135.73 MIN: 38.4 / MAX: 207.06 MIN: 38.09 / MAX: 245.2 MIN: 37.29 / MAX: 248.17 MIN: 35.76 / MAX: 247.19 MIN: 41.5 / MAX: 164.45 MIN: 41.8 / MAX: 277.53 MIN: 28 / MAX: 268.31 MIN: 33.3 / MAX: 388.06 MIN: 31.78 / MAX: 382.85 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.3 CPU Power Consumption Monitor EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 140 280 420 560 700 Min: 54.21 / Avg: 621.41 / Max: 681.63 Min: 61.12 / Avg: 660.02 / Max: 724.09 Min: 65.68 / Avg: 640.6 / Max: 705.43 Min: 59.35 / Avg: 734.35 / Max: 813.98 Min: 115.32 / Avg: 593.32 / Max: 646.79 Min: 65.9 / Avg: 750.48 / Max: 819.64 Min: 44.87 / Avg: 610.25 / Max: 670.27 Min: 62.06 / Avg: 724.32 / Max: 817.49 Min: 195.17 / Avg: 650.31 / Max: 743.6 Min: 309.34 / Avg: 567.64 / Max: 645.55 Min: 291.07 / Avg: 663.09 / Max: 748.39
PETSc PETSc, the Portable, Extensible Toolkit for Scientific Computation, is for the scalable (parallel) solution of scientific applications modeled by partial differential equations. This test profile runs the PETSc "make streams" benchmark and records the throughput rate when all available cores are utilized for the MPI Streams build. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org MB/s, More Is Better PETSc 3.19 Test: Streams EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 300K 600K 900K 1200K 1500K SE +/- 226.13, N = 3 SE +/- 13801.50, N = 9 SE +/- 14054.14, N = 9 SE +/- 7104.67, N = 9 SE +/- 16940.03, N = 9 SE +/- 24624.10, N = 9 SE +/- 35873.33, N = 6 SE +/- 19305.47, N = 6 SE +/- 16038.68, N = 9 SE +/- 1463.10, N = 3 SE +/- 34939.31, N = 6 SE +/- 13204.52, N = 3 247183.49 501964.62 491308.08 498825.93 440996.50 519663.49 502329.42 449040.09 402880.37 382936.01 822547.78 1244507.94 1. (CC) gcc options: -fPIC -O3 -O2 -lpthread -ludev -lpciaccess -lm
MB/s Per Watt
OpenBenchmarking.org MB/s Per Watt, More Is Better PETSc 3.19 Test: Streams EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 400 800 1200 1600 2000 580.72 1188.33 1161.25 1073.62 931.31 1062.72 951.60 1230.16 1097.89 651.49 1584.95 1914.94
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PETSc 3.19 CPU Power Consumption Monitor EPYC 7773X 2P EPYC 9554 2P EPYC 9554 2P - Power 400W EPYC 9654 2P EPYC 9654 2P - Power 400W EPYC 9684X 2P EPYC 9684X 2P - Power 400W EPYC 9754 2P EPYC 9754 2P - Power 400W Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 2P - HBM Only 200 400 600 800 1000