Google Axion C4A 48 vCPU vs. C4 Xeon vs. T2A Ampere Altra 48 vCPU Google GCE comparison of Axion C4A instance compared to 48 vCPU Xeon C4 (Emerald Rapids) and T2A Ampere Altra instances. Benchmarks by Michael Larabel for a future article.
HTML result view exported from: https://openbenchmarking.org/result/2410309-NE-AXIONC4A532 .
Google Axion C4A 48 vCPU vs. C4 Xeon vs. T2A Ampere Altra Processor Motherboard Memory Disk Network Chipset OS Kernel Compiler File-System System Layer C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra ARMv8 Neoverse-V2 (48 Cores) KVM Google Compute Engine 12 x 16GB RAM 215GB nvme_card-pd Google Compute Engine Virtual Ubuntu 24.04 6.8.0-1015-gcp (aarch64) GCC 13.2.0 ext4 google INTEL XEON PLATINUM 8581C (24 Cores / 48 Threads) Google Compute Engine c4-standard-48 Intel 440FX 82441FX PMC 16 + 16 + 16 + 16 + 16 + 16 + 16 + 16 + 16 + 16 + 16 + 4 RAM 6.8.0-1015-gcp (x86_64) ARMv8 Neoverse-N1 (48 Cores) KVM Google Compute Engine 12 x 16GB RAM 6.8.0-1015-gcp (aarch64) OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - C4A Axion: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-dIwDw0/gcc-13-13.2.0/debian/tmp-nvptx/usr --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto --without-cuda-driver -v - C4 Xeon Platinum EMR: --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-backtrace --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-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/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 - T2A Ampere Altra: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-dIwDw0/gcc-13-13.2.0/debian/tmp-nvptx/usr --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto --without-cuda-driver -v Java Details - C4A Axion, C4 Xeon Platinum EMR: OpenJDK Runtime Environment (build 11.0.24+8-post-Ubuntu-1ubuntu324.04.1) Python Details - Python 3.12.3 Security Details - C4A Axion: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected - C4 Xeon Platinum EMR: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: SW sequence; BHI: SW loop KVM: SW loop + srbds: Not affected + tsx_async_abort: Not affected - T2A Ampere Altra: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of CSV2 BHB + srbds: Not affected + tsx_async_abort: Not affected Processor Details - C4 Xeon Platinum EMR: CPU Microcode: 0xffffffff
Google Axion C4A 48 vCPU vs. C4 Xeon vs. T2A Ampere Altra hpcg: 104 104 104 - 60 hpcg: 144 144 144 - 60 minife: Small cloverleaf: clover_bm64_short rodinia: OpenMP LavaMD rodinia: OpenMP CFD Solver amg: pennant: sedovbig pennant: leblancbig incompact3d: input.i3d 193 Cells Per Direction lammps: 20k Atoms lulesh: xmrig: GhostRider - 1M john-the-ripper: bcrypt john-the-ripper: Blowfish john-the-ripper: HMAC-SHA512 coremark: CoreMark Size 666 - Iterations Per Second compress-7zip: Compression Rating compress-7zip: Decompression Rating build-godot: Time To Compile build-llvm: Ninja build-nodejs: Time To Compile openssl: ChaCha20 openssl: AES-128-GCM openssl: AES-256-GCM openssl: ChaCha20-Poly1305 clickhouse: 100M Rows Hits Dataset, First Run / Cold Cache clickhouse: 100M Rows Hits Dataset, Second Run clickhouse: 100M Rows Hits Dataset, Third Run memcached: 1:10 memcached: 1:100 askap: tConvolve MT - Gridding askap: tConvolve MT - Degridding askap: tConvolve MPI - Degridding askap: tConvolve MPI - Gridding askap: tConvolve OpenMP - Gridding askap: tConvolve OpenMP - Degridding askap: Hogbom Clean OpenMP gromacs: MPI CPU - water_GMX50_bare rocksdb: Rand Read rocksdb: Update Rand rocksdb: Read While Writing rocksdb: Read Rand Write Rand C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 42.7522 43.1385 47199.6 26.15 41.177 3.106 2188353000 7.310130 5.041512 9.67658011 40.831 20794.052 4298.2 45749 45763 89864667 1441191.863234 306082 266745 153.601 204.046 260.461 100837228180 266141028803 231857666003 70429152870 438.85 465.02 480.41 4672917.72 4416447.73 11899.7 15472.6 17695.6 17890.6 25980.1 43530.7 2254.71 3.984 288511691 999493 6282429 4550050 17.7551 17.4443 20576.7 71.41 77.061 6.621 916723067 28.32594 9.512217 30.5046978 19.767 10358.893 3421.0 46521 46328 165604000 1027241.721365 208023 145509 176.754 309.393 393.115 146568391977 466561387338 344315542484 101608292900 326.71 357.96 357.96 5999388.74 5970099.59 4496.42 6342.58 13938.0 18321.2 17158.7 20822.6 1456.38 4.387 136103586 794557 5175867 3564333 24741.6 54.23 68.607 5.552 1088577000 16.97260 12.67227 26.9445116 23.310 9812.8071 1618.8 40399 40398 54735000 1052843.691802 193705 206064 317.423 882.034 60151706780 140585904447 113470981097 41733619623 237.24 256.07 257.30 4143638.41 3966685.26 4732.27 6569.72 5355.18 4161.39 9510.54 12198.6 1080.45 2.397 149212901 531284 3830272 2179030 OpenBenchmarking.org
High Performance Conjugate Gradient X Y Z: 104 104 104 - RT: 60 OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 X Y Z: 104 104 104 - RT: 60 C4A Axion C4 Xeon Platinum EMR 10 20 30 40 50 SE +/- 0.16, N = 3 SE +/- 0.00, N = 3 42.75 17.76 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi
High Performance Conjugate Gradient X Y Z: 144 144 144 - RT: 60 OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 X Y Z: 144 144 144 - RT: 60 C4A Axion C4 Xeon Platinum EMR 10 20 30 40 50 SE +/- 0.18, N = 3 SE +/- 0.00, N = 3 43.14 17.44 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi
miniFE Problem Size: Small OpenBenchmarking.org CG Mflops, More Is Better miniFE 2.2 Problem Size: Small C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 10K 20K 30K 40K 50K SE +/- 12.79, N = 3 SE +/- 4.08, N = 3 SE +/- 53.66, N = 3 47199.6 20576.7 24741.6 1. (CXX) g++ options: -O3 -fopenmp -lmpi_cxx -lmpi
CloverLeaf Input: clover_bm64_short OpenBenchmarking.org Seconds, Fewer Is Better CloverLeaf 1.3 Input: clover_bm64_short C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 16 32 48 64 80 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.16, N = 3 26.15 71.41 54.23 1. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
Rodinia Test: OpenMP LavaMD OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP LavaMD C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 20 40 60 80 100 SE +/- 0.12, N = 3 SE +/- 0.16, N = 3 SE +/- 0.02, N = 3 41.18 77.06 68.61 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP CFD Solver OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP CFD Solver C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 2 4 6 8 10 SE +/- 0.024, N = 3 SE +/- 0.020, N = 3 SE +/- 0.014, N = 3 3.106 6.621 5.552 1. (CXX) g++ options: -O2 -lOpenCL
Algebraic Multi-Grid Benchmark OpenBenchmarking.org Figure Of Merit, More Is Better Algebraic Multi-Grid Benchmark 1.2 C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 500M 1000M 1500M 2000M 2500M SE +/- 2463059.28, N = 3 SE +/- 341457.48, N = 3 SE +/- 10220970.27, N = 3 2188353000 916723067 1088577000 1. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi
Pennant Test: sedovbig OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: sedovbig C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 7 14 21 28 35 SE +/- 0.029628, N = 3 SE +/- 0.080167, N = 3 SE +/- 0.094168, N = 3 7.310130 28.325940 16.972600 1. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
Pennant Test: leblancbig OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: leblancbig C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 3 6 9 12 15 SE +/- 0.017045, N = 3 SE +/- 0.012783, N = 3 SE +/- 0.010185, N = 3 5.041512 9.512217 12.672270 1. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
Xcompact3d Incompact3d Input: input.i3d 193 Cells Per Direction OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 193 Cells Per Direction C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 7 14 21 28 35 SE +/- 0.00471123, N = 3 SE +/- 0.28274140, N = 6 SE +/- 0.18163136, N = 13 9.67658011 30.50469780 26.94451160 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
LAMMPS Molecular Dynamics Simulator Model: 20k Atoms OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: 20k Atoms C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 9 18 27 36 45 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.04, N = 3 40.83 19.77 23.31 1. (CXX) g++ options: -O3 -lm -ldl
LULESH OpenBenchmarking.org z/s, More Is Better LULESH 2.0.3 C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 4K 8K 12K 16K 20K SE +/- 282.43, N = 3 SE +/- 45.91, N = 3 SE +/- 34.22, N = 3 20794.05 10358.89 9812.81 1. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi
Xmrig Variant: GhostRider - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: GhostRider - Hash Count: 1M C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 900 1800 2700 3600 4500 SE +/- 12.97, N = 3 SE +/- 7.01, N = 3 SE +/- 18.74, N = 3 4298.2 3421.0 1618.8 -maes 1. (CXX) g++ options: -fexceptions -fno-rtti -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
John The Ripper Test: bcrypt OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: bcrypt C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 10K 20K 30K 40K 50K SE +/- 25.03, N = 3 SE +/- 54.04, N = 3 SE +/- 13.96, N = 3 45749 46521 40399 -m64 1. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt
John The Ripper Test: Blowfish OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: Blowfish C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 10K 20K 30K 40K 50K SE +/- 14.62, N = 3 SE +/- 34.85, N = 3 SE +/- 27.71, N = 3 45763 46328 40398 -m64 1. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt
John The Ripper Test: HMAC-SHA512 OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: HMAC-SHA512 C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 40M 80M 120M 160M 200M SE +/- 28852.11, N = 3 SE +/- 65317.17, N = 3 SE +/- 1525107.00, N = 12 89864667 165604000 54735000 -m64 1. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 300K 600K 900K 1200K 1500K SE +/- 20293.48, N = 3 SE +/- 1293.04, N = 3 SE +/- 1902.13, N = 3 1441191.86 1027241.72 1052843.69 1. (CC) gcc options: -O2 -lrt" -lrt
7-Zip Compression Test: Compression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 24.05 Test: Compression Rating C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 70K 140K 210K 280K 350K SE +/- 748.65, N = 3 SE +/- 191.64, N = 3 SE +/- 1305.07, N = 3 306082 208023 193705 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
7-Zip Compression Test: Decompression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 24.05 Test: Decompression Rating C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 60K 120K 180K 240K 300K SE +/- 67.68, N = 3 SE +/- 206.03, N = 3 SE +/- 42.51, N = 3 266745 145509 206064 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
Timed Godot Game Engine Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 4.0 Time To Compile C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 70 140 210 280 350 SE +/- 0.21, N = 3 SE +/- 0.35, N = 3 SE +/- 0.18, N = 3 153.60 176.75 317.42
Timed LLVM Compilation Build System: Ninja OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 16.0 Build System: Ninja C4A Axion C4 Xeon Platinum EMR 70 140 210 280 350 SE +/- 0.23, N = 3 SE +/- 0.29, N = 3 204.05 309.39
Timed Node.js Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 21.7.2 Time To Compile C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 200 400 600 800 1000 SE +/- 0.26, N = 3 SE +/- 2.47, N = 3 SE +/- 1.32, N = 3 260.46 393.12 882.03
OpenSSL Algorithm: ChaCha20 OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: ChaCha20 C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 30000M 60000M 90000M 120000M 150000M SE +/- 48601049.47, N = 3 SE +/- 34658260.13, N = 3 SE +/- 7423321.42, N = 3 100837228180 146568391977 60151706780 1. C4A Axion: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) 2. C4 Xeon Platinum EMR: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8 3. T2A Ampere Altra: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)
OpenSSL Algorithm: AES-128-GCM OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: AES-128-GCM C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 100000M 200000M 300000M 400000M 500000M SE +/- 7311961.78, N = 3 SE +/- 6674463163.95, N = 12 SE +/- 13254818.21, N = 3 266141028803 466561387338 140585904447 1. C4A Axion: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) 2. C4 Xeon Platinum EMR: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8 3. T2A Ampere Altra: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)
OpenSSL Algorithm: AES-256-GCM OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: AES-256-GCM C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 70000M 140000M 210000M 280000M 350000M SE +/- 119817516.04, N = 3 SE +/- 5252124128.24, N = 12 SE +/- 18912120.18, N = 3 231857666003 344315542484 113470981097 1. C4A Axion: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) 2. C4 Xeon Platinum EMR: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8 3. T2A Ampere Altra: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)
OpenSSL Algorithm: ChaCha20-Poly1305 OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: ChaCha20-Poly1305 C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 20000M 40000M 60000M 80000M 100000M SE +/- 36045318.84, N = 3 SE +/- 317228455.16, N = 3 SE +/- 1266565.62, N = 3 70429152870 101608292900 41733619623 1. C4A Axion: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) 2. C4 Xeon Platinum EMR: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8 3. T2A Ampere Altra: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)
ClickHouse 100M Rows Hits Dataset, First Run / Cold Cache OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, First Run / Cold Cache C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 100 200 300 400 500 SE +/- 5.15, N = 9 SE +/- 1.91, N = 3 SE +/- 3.01, N = 3 438.85 326.71 237.24 MIN: 35.57 / MAX: 6666.67 MIN: 20.51 / MAX: 6666.67 MIN: 18.69 / MAX: 4000
ClickHouse 100M Rows Hits Dataset, Second Run OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 100 200 300 400 500 SE +/- 4.32, N = 9 SE +/- 1.96, N = 3 SE +/- 4.17, N = 3 465.02 357.96 256.07 MIN: 35.65 / MAX: 7500 MIN: 21.12 / MAX: 7500 MIN: 18.78 / MAX: 4285.71
ClickHouse 100M Rows Hits Dataset, Third Run OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 100 200 300 400 500 SE +/- 3.70, N = 9 SE +/- 2.07, N = 3 SE +/- 2.67, N = 3 480.41 357.96 257.30 MIN: 35.46 / MAX: 6666.67 MIN: 20.98 / MAX: 6666.67 MIN: 18.79 / MAX: 3750
Memcached Set To Get Ratio: 1:10 OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:10 C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 1.3M 2.6M 3.9M 5.2M 6.5M SE +/- 200017.70, N = 12 SE +/- 66686.31, N = 5 SE +/- 57647.92, N = 3 4672917.72 5999388.74 4143638.41 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Memcached Set To Get Ratio: 1:100 OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:100 C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 1.3M 2.6M 3.9M 5.2M 6.5M SE +/- 203945.72, N = 12 SE +/- 55898.73, N = 15 SE +/- 26632.42, N = 3 4416447.73 5970099.59 3966685.26 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
ASKAP Test: tConvolve MT - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Gridding C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 3K 6K 9K 12K 15K SE +/- 11.07, N = 3 SE +/- 6.07, N = 3 SE +/- 0.58, N = 3 11899.70 4496.42 4732.27 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
ASKAP Test: tConvolve MT - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Degridding C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 3K 6K 9K 12K 15K SE +/- 32.45, N = 3 SE +/- 3.63, N = 3 SE +/- 5.63, N = 3 15472.60 6342.58 6569.72 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
ASKAP Test: tConvolve MPI - Degridding OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Degridding C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 4K 8K 12K 16K 20K SE +/- 229.66, N = 3 SE +/- 159.30, N = 4 SE +/- 21.03, N = 3 17695.60 13938.00 5355.18 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
ASKAP Test: tConvolve MPI - Gridding OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Gridding C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 4K 8K 12K 16K 20K SE +/- 0.00, N = 3 SE +/- 294.55, N = 4 SE +/- 9.69, N = 3 17890.60 18321.20 4161.39 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
ASKAP Test: tConvolve OpenMP - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve OpenMP - Gridding C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 6K 12K 18K 24K 30K SE +/- 286.07, N = 15 SE +/- 147.92, N = 15 SE +/- 156.68, N = 12 25980.10 17158.70 9510.54 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
ASKAP Test: tConvolve OpenMP - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve OpenMP - Degridding C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 9K 18K 27K 36K 45K SE +/- 575.94, N = 15 SE +/- 182.46, N = 15 SE +/- 64.77, N = 12 43530.7 20822.6 12198.6 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
ASKAP Test: Hogbom Clean OpenMP OpenBenchmarking.org Iterations Per Second, More Is Better ASKAP 1.0 Test: Hogbom Clean OpenMP C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 500 1000 1500 2000 2500 SE +/- 37.89, N = 15 SE +/- 7.10, N = 3 SE +/- 11.98, N = 5 2254.71 1456.38 1080.45 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2024 Implementation: MPI CPU - Input: water_GMX50_bare C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 0.9871 1.9742 2.9613 3.9484 4.9355 SE +/- 0.001, N = 3 SE +/- 0.012, N = 3 SE +/- 0.006, N = 3 3.984 4.387 2.397 1. (CXX) g++ options: -O3 -lm
RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Random Read C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 60M 120M 180M 240M 300M SE +/- 88148.93, N = 3 SE +/- 599927.22, N = 3 SE +/- 344165.60, N = 3 288511691 136103586 149212901 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
RocksDB Test: Update Random OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Update Random C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 200K 400K 600K 800K 1000K SE +/- 9437.64, N = 3 SE +/- 5276.32, N = 3 SE +/- 5458.72, N = 4 999493 794557 531284 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Read While Writing C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 1.3M 2.6M 3.9M 5.2M 6.5M SE +/- 42437.10, N = 3 SE +/- 8881.77, N = 3 SE +/- 21345.21, N = 3 6282429 5175867 3830272 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
RocksDB Test: Read Random Write Random OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Read Random Write Random C4A Axion C4 Xeon Platinum EMR T2A Ampere Altra 1000K 2000K 3000K 4000K 5000K SE +/- 4377.96, N = 3 SE +/- 17653.14, N = 3 SE +/- 27299.12, N = 3 4550050 3564333 2179030 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
Phoronix Test Suite v10.8.5