Graviton4 r8g.16xlarge Processor: ARMv8 Neoverse-V2 (64 Cores), Motherboard: Amazon EC2 r8g.16xlarge (1.0 BIOS), Chipset: Amazon Device 0200, Memory: 496GB, Disk: 429GB Amazon Elastic Block Store, Network: Amazon Elastic
OS: Ubuntu 24.04, Kernel: 6.8.0-1009-aws (aarch64), Compiler: GCC 13.2.0, File-System: ext4, System Layer: amazon
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --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 -vPython Notes: Python 3.12.3Security Notes: 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
Graviton3 r7g.16xlarge Changed Processor to ARMv8 Neoverse-V1 (64 Cores) .
Changed Motherboard to Amazon EC2 r7g.16xlarge (1.0 BIOS) .
Security Change: 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
Graviton4 vs. Graviton3 Processor Motherboard Chipset Memory Disk Network OS Kernel Compiler File-System System Layer Graviton4 r8g.16xlarge Graviton3 r7g.16xlarge ARMv8 Neoverse-V2 (64 Cores) Amazon EC2 r8g.16xlarge (1.0 BIOS) Amazon Device 0200 496GB 429GB Amazon Elastic Block Store Amazon Elastic Ubuntu 24.04 6.8.0-1009-aws (aarch64) GCC 13.2.0 ext4 amazon ARMv8 Neoverse-V1 (64 Cores) Amazon EC2 r7g.16xlarge (1.0 BIOS) OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --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 Python Details - Python 3.12.3 Security Details - Graviton4 r8g.16xlarge: 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 - Graviton3 r7g.16xlarge: 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
Graviton4 r8g.16xlarge vs. Graviton3 r7g.16xlarge Comparison Phoronix Test Suite Baseline +45.7% +45.7% +91.4% +91.4% +137.1% +137.1% 2.7% 2.7% GhostRider - 1M 182.6% Small 79.9% 100 - 1000 - Read Only 79.1% 100 - 1000 - Read Only - Average Latency 79% i.i.1.C.P.D 77.2% d.S.M.S - Execution Time 64.9% d.M.M.S - Execution Time 60.6% Time To Compile 56.4% Update Rand 55.9% KawPow - 1M 50.7% CryptoNight-Heavy - 1M 50.2% C.F.U - 1M 50.2% Monero - 1M 50.2% Chess Benchmark 46.6% Rand Read 42.5% Ninja 41.6% Wownero - 1M 38.7% 5K - 16 36.7% 4K - 16 36.5% d.S.M.S - Mesh Time 34.8% Time To Compile 34.6% Time To Compile 32.2% d.M.M.S - Mesh Time 31.9% R.R.W.R 31.2% 1.R.H.D.T.R 29.5% Compression Rating 29.2% Barbershop - CPU-Only 29.1% 1.R.H.D.F.R.C.C 29% 1.R.H.D.S.R 27.9% 64 - 256 - 32 26.6% P.P.B.T.T 26.4% HMAC-SHA512 24.7% Read While Writing 24% BMW27 - CPU-Only 24% Classroom - CPU-Only 22.9% Pabellon Barcelona - CPU-Only 22.4% Fishy Cat - CPU-Only 21.5% SHA256 20.2% 64 - 256 - 57 16.6% D.R 16.5% MPI CPU - water_GMX50_bare 16% SHA512 15.5% P.P.B.T.T 14.2% Blowfish 12.5% bcrypt 12.5% 64 - 256 - 512 11.2% WPA PSK 9.1% MD5 8.8% ChaCha20-Poly1305 8.3% ChaCha20 8.2% AES-256-GCM 6.8% AES-128-GCM 4.2% 100 - 1000 - Read Write 100 - 1000 - Read Write - Average Latency Xmrig miniFE PostgreSQL PostgreSQL Xcompact3d Incompact3d OpenFOAM OpenFOAM Timed Node.js Compilation RocksDB Xmrig Xmrig Xmrig Xmrig Stockfish RocksDB Timed LLVM Compilation Xmrig C-Ray C-Ray OpenFOAM Timed Gem5 Compilation Timed Godot Game Engine Compilation OpenFOAM RocksDB ClickHouse 7-Zip Compression Blender ClickHouse ClickHouse Liquid-DSP srsRAN Project John The Ripper RocksDB Blender Blender Blender Blender OpenSSL Liquid-DSP 7-Zip Compression GROMACS OpenSSL srsRAN Project John The Ripper John The Ripper Liquid-DSP John The Ripper John The Ripper OpenSSL OpenSSL OpenSSL OpenSSL PostgreSQL PostgreSQL Graviton4 r8g.16xlarge Graviton3 r7g.16xlarge
Graviton4 vs. Graviton3 minife: Small incompact3d: input.i3d 193 Cells Per Direction openfoam: drivaerFastback, Small Mesh Size - Mesh Time openfoam: drivaerFastback, Small Mesh Size - Execution Time openfoam: drivaerFastback, Medium Mesh Size - Mesh Time openfoam: drivaerFastback, Medium Mesh Size - Execution Time xmrig: KawPow - 1M xmrig: Monero - 1M xmrig: Wownero - 1M xmrig: GhostRider - 1M xmrig: CryptoNight-Heavy - 1M xmrig: CryptoNight-Femto UPX2 - 1M srsran: PDSCH Processor Benchmark, Throughput Total srsran: PUSCH Processor Benchmark, Throughput Total john-the-ripper: bcrypt john-the-ripper: WPA PSK john-the-ripper: Blowfish john-the-ripper: HMAC-SHA512 john-the-ripper: MD5 compress-7zip: Compression Rating compress-7zip: Decompression Rating stockfish: Chess Benchmark build-gem5: Time To Compile build-godot: Time To Compile build-llvm: Ninja build-nodejs: Time To Compile c-ray: 4K - 16 c-ray: 5K - 16 liquid-dsp: 64 - 256 - 32 liquid-dsp: 64 - 256 - 57 liquid-dsp: 64 - 256 - 512 openssl: SHA256 openssl: SHA512 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 gromacs: MPI CPU - water_GMX50_bare pgbench: 100 - 1000 - Read Only pgbench: 100 - 1000 - Read Only - Average Latency pgbench: 100 - 1000 - Read Write pgbench: 100 - 1000 - Read Write - Average Latency rocksdb: Rand Read rocksdb: Update Rand rocksdb: Read While Writing rocksdb: Read Rand Write Rand blender: BMW27 - CPU-Only blender: Classroom - CPU-Only blender: Fishy Cat - CPU-Only blender: Barbershop - CPU-Only blender: Pabellon Barcelona - CPU-Only Graviton4 r8g.16xlarge Graviton3 r7g.16xlarge 65410.4 7.87502066 18.384768 41.413075 91.974527 344.1676 21906.0 21872.1 28304.0 5958.7 21867.2 21851.9 14402.5 1332.5 57038 57444 57032 108066333 1579667 383460 331505 81440801 186.768 147.870 182.063 365.024 28.323 50.247 3258733333 1929666667 185000000 56971174537 35412809363 101898720323 299797102137 266125150527 75190548707 449.44 479.94 495.03 4.831 1947525 0.514 4420 226.244 346532586 1274616 8522597 5584014 50.64 105.39 95.01 499.63 202.26 36361.7 13.9558484 24.784465 68.294615 121.27861 552.5657 14540.4 14564.0 20409.6 2108.5 14553.9 14547.5 12612.6 1053.8 50709 52631 50679 86689000 1451333 296731 284576 55548662 251.402 195.497 257.853 571.011 38.668 68.699 2573800000 1654733333 166313333 47395512363 30659465710 94147502077 287591524763 249095500597 69430704540 348.41 375.29 382.14 4.163 1087488 0.920 4541 220.273 243166771 817470 6872389 4254497 62.77 129.48 115.47 644.98 247.60 OpenBenchmarking.org
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.
OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 193 Cells Per Direction Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 4 8 12 16 20 SE +/- 0.01649632, N = 3 SE +/- 0.01884341, N = 3 13.95584840 7.87502066 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
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.
OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Mesh Time Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 6 12 18 24 30 24.78 18.38 1. (CXX) g++ options: -std=c++14 -O3 -mcpu=native -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Execution Time Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 15 30 45 60 75 68.29 41.41 1. (CXX) g++ options: -std=c++14 -O3 -mcpu=native -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Medium Mesh Size - Mesh Time Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 30 60 90 120 150 121.28 91.97 1. (CXX) g++ options: -std=c++14 -O3 -mcpu=native -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Medium Mesh Size - Execution Time Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 120 240 360 480 600 552.57 344.17 1. (CXX) g++ options: -std=c++14 -O3 -mcpu=native -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
Xmrig Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: KawPow - Hash Count: 1M Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 5K 10K 15K 20K 25K SE +/- 6.29, N = 3 SE +/- 59.25, N = 3 14540.4 21906.0 1. (CXX) g++ options: -fexceptions -fno-rtti -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: Monero - Hash Count: 1M Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 5K 10K 15K 20K 25K SE +/- 12.04, N = 3 SE +/- 40.15, N = 3 14564.0 21872.1 1. (CXX) g++ options: -fexceptions -fno-rtti -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: Wownero - Hash Count: 1M Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 6K 12K 18K 24K 30K SE +/- 8.34, N = 3 SE +/- 16.31, N = 3 20409.6 28304.0 1. (CXX) g++ options: -fexceptions -fno-rtti -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: GhostRider - Hash Count: 1M Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 1300 2600 3900 5200 6500 SE +/- 4.85, N = 3 SE +/- 47.30, N = 12 2108.5 5958.7 1. (CXX) g++ options: -fexceptions -fno-rtti -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: CryptoNight-Heavy - Hash Count: 1M Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 5K 10K 15K 20K 25K SE +/- 14.63, N = 3 SE +/- 16.81, N = 3 14553.9 21867.2 1. (CXX) g++ options: -fexceptions -fno-rtti -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: CryptoNight-Femto UPX2 - Hash Count: 1M Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 5K 10K 15K 20K 25K SE +/- 4.95, N = 3 SE +/- 9.16, N = 3 14547.5 21851.9 1. (CXX) g++ options: -fexceptions -fno-rtti -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
srsRAN Project srsRAN Project is a complete ORAN-native 5G RAN solution created by Software Radio Systems (SRS). The srsRAN Project radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240325 Test: PDSCH Processor Benchmark, Throughput Total Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 3K 6K 9K 12K 15K SE +/- 20.13, N = 3 SE +/- 34.15, N = 3 12612.6 14402.5 1. (CXX) g++ options: -O3 -fno-trapping-math -fno-math-errno -ldl
OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240325 Test: PUSCH Processor Benchmark, Throughput Total Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 300 600 900 1200 1500 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 1053.8 1332.5 MIN: 599.4 / MAX: 1053.9 MIN: 784 / MAX: 1332.6 1. (CXX) g++ options: -O3 -fno-trapping-math -fno-math-errno -ldl
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: WPA PSK Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 12K 24K 36K 48K 60K SE +/- 0.00, N = 3 SE +/- 10.97, N = 3 52631 57444 1. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: Blowfish Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 12K 24K 36K 48K 60K SE +/- 15.39, N = 3 SE +/- 9.29, N = 3 50679 57032 1. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: HMAC-SHA512 Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 20M 40M 60M 80M 100M SE +/- 76622.45, N = 3 SE +/- 640028.21, N = 3 86689000 108066333 1. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: MD5 Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 300K 600K 900K 1200K 1500K SE +/- 333.33, N = 3 SE +/- 1201.85, N = 3 1451333 1579667 1. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt
7-Zip Compression OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 24.05 Test: Compression Rating Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 80K 160K 240K 320K 400K SE +/- 546.41, N = 3 SE +/- 397.84, N = 3 296731 383460 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 24.05 Test: Decompression Rating Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 70K 140K 210K 280K 350K SE +/- 70.02, N = 3 SE +/- 107.45, N = 3 284576 331505 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
Stockfish This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 1024 CPU threads. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 16.1 Chess Benchmark Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 20M 40M 60M 80M 100M SE +/- 1152869.30, N = 12 SE +/- 2235406.92, N = 15 55548662 81440801 1. (CXX) g++ options: -lgcov -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -flto -flto-partition=one -flto=jobserver
C-Ray OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 2.0 Resolution: 4K - Rays Per Pixel: 16 Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 9 18 27 36 45 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 38.67 28.32 1. (CC) gcc options: -lpthread -lm
OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 2.0 Resolution: 5K - Rays Per Pixel: 16 Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 15 30 45 60 75 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 68.70 50.25 1. (CC) gcc options: -lpthread -lm
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 32 Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 700M 1400M 2100M 2800M 3500M SE +/- 404145.19, N = 3 SE +/- 533333.33, N = 3 2573800000 3258733333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 57 Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 400M 800M 1200M 1600M 2000M SE +/- 133333.33, N = 3 SE +/- 33333.33, N = 3 1654733333 1929666667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 512 Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 40M 80M 120M 160M 200M SE +/- 3333.33, N = 3 SE +/- 0.00, N = 3 166313333 185000000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenSSL OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: SHA256 Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 12000M 24000M 36000M 48000M 60000M SE +/- 29159419.58, N = 3 SE +/- 10002237.60, N = 3 47395512363 56971174537 1. OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)
OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: SHA512 Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 8000M 16000M 24000M 32000M 40000M SE +/- 3137583.25, N = 3 SE +/- 8695334.33, N = 3 30659465710 35412809363 1. OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)
Algorithm: RSA4096
Graviton4 r8g.16xlarge: The test run did not produce a result.
Graviton3 r7g.16xlarge: The test run did not produce a result.
OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: ChaCha20 Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 20000M 40000M 60000M 80000M 100000M SE +/- 4627810.23, N = 3 SE +/- 66408.09, N = 3 94147502077 101898720323 1. OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)
OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: AES-128-GCM Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 60000M 120000M 180000M 240000M 300000M SE +/- 3618954.21, N = 3 SE +/- 7802917.99, N = 3 287591524763 299797102137 1. OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)
OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: AES-256-GCM Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 60000M 120000M 180000M 240000M 300000M SE +/- 4988409.71, N = 3 SE +/- 6417811.59, N = 3 249095500597 266125150527 1. OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)
OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: ChaCha20-Poly1305 Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 16000M 32000M 48000M 64000M 80000M SE +/- 6321669.59, N = 3 SE +/- 558939.35, N = 3 69430704540 75190548707 1. OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)
ClickHouse ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ / https://github.com/ClickHouse/ClickBench/tree/main/clickhouse with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all separate queries performed as an aggregate. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, First Run / Cold Cache Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 100 200 300 400 500 SE +/- 5.68, N = 9 SE +/- 4.96, N = 9 348.41 449.44 MIN: 33.19 / MAX: 5000 MIN: 42.7 / MAX: 6666.67
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 100 200 300 400 500 SE +/- 3.03, N = 9 SE +/- 5.05, N = 9 375.29 479.94 MIN: 33.15 / MAX: 5000 MIN: 43.1 / MAX: 6000
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 110 220 330 440 550 SE +/- 2.76, N = 9 SE +/- 6.71, N = 9 382.14 495.03 MIN: 33.22 / MAX: 4615.38 MIN: 43.07 / MAX: 6666.67
GROMACS The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2024 Implementation: MPI CPU - Input: water_GMX50_bare Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 1.087 2.174 3.261 4.348 5.435 SE +/- 0.001, N = 3 SE +/- 0.004, N = 3 4.163 4.831 1. (CXX) g++ options: -O3 -lm
PostgreSQL This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 400K 800K 1200K 1600K 2000K SE +/- 5453.81, N = 3 SE +/- 6233.51, N = 3 1087488 1947525 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 0.207 0.414 0.621 0.828 1.035 SE +/- 0.005, N = 3 SE +/- 0.002, N = 3 0.920 0.514 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write Graviton4 r8g.16xlarge Graviton3 r7g.16xlarge 1000 2000 3000 4000 5000 SE +/- 14.53, N = 3 SE +/- 45.23, N = 3 4420 4541 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency Graviton4 r8g.16xlarge Graviton3 r7g.16xlarge 50 100 150 200 250 SE +/- 0.74, N = 3 SE +/- 2.18, N = 3 226.24 220.27 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
RocksDB This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Random Read Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 70M 140M 210M 280M 350M SE +/- 36358.69, N = 3 SE +/- 1371022.17, N = 3 243166771 346532586 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Update Random Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 300K 600K 900K 1200K 1500K SE +/- 7555.40, N = 15 SE +/- 11457.12, N = 3 817470 1274616 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Read While Writing Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 2M 4M 6M 8M 10M SE +/- 6592.32, N = 3 SE +/- 26974.32, N = 3 6872389 8522597 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Read Random Write Random Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 1.2M 2.4M 3.6M 4.8M 6M SE +/- 1357.98, N = 3 SE +/- 11170.68, N = 3 4254497 5584014 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
Blender Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.0.2 Blend File: BMW27 - Compute: CPU-Only Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 14 28 42 56 70 SE +/- 0.02, N = 3 SE +/- 0.10, N = 3 62.77 50.64
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.0.2 Blend File: Classroom - Compute: CPU-Only Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 30 60 90 120 150 SE +/- 0.06, N = 3 SE +/- 0.11, N = 3 129.48 105.39
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.0.2 Blend File: Fishy Cat - Compute: CPU-Only Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 30 60 90 120 150 SE +/- 0.23, N = 3 SE +/- 0.26, N = 3 115.47 95.01
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.0.2 Blend File: Barbershop - Compute: CPU-Only Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 140 280 420 560 700 SE +/- 0.24, N = 3 SE +/- 0.76, N = 3 644.98 499.63
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.0.2 Blend File: Pabellon Barcelona - Compute: CPU-Only Graviton3 r7g.16xlarge Graviton4 r8g.16xlarge 50 100 150 200 250 SE +/- 0.13, N = 3 SE +/- 0.34, N = 3 247.60 202.26
Graviton4 r8g.16xlarge Processor: ARMv8 Neoverse-V2 (64 Cores), Motherboard: Amazon EC2 r8g.16xlarge (1.0 BIOS), Chipset: Amazon Device 0200, Memory: 496GB, Disk: 429GB Amazon Elastic Block Store, Network: Amazon Elastic
OS: Ubuntu 24.04, Kernel: 6.8.0-1009-aws (aarch64), Compiler: GCC 13.2.0, File-System: ext4, System Layer: amazon
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --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 -vPython Notes: Python 3.12.3Security Notes: 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
Testing initiated at 10 July 2024 00:59 by user ubuntu.
Graviton3 r7g.16xlarge Processor: ARMv8 Neoverse-V1 (64 Cores), Motherboard: Amazon EC2 r7g.16xlarge (1.0 BIOS), Chipset: Amazon Device 0200, Memory: 496GB, Disk: 429GB Amazon Elastic Block Store, Network: Amazon Elastic
OS: Ubuntu 24.04, Kernel: 6.8.0-1009-aws (aarch64), Compiler: GCC 13.2.0, File-System: ext4, System Layer: amazon
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --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 -vPython Notes: Python 3.12.3Security Notes: 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
Testing initiated at 10 July 2024 12:48 by user ubuntu.