Benchmarks by Michael Larabel for a future article on Phoronix.com.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2308110-NE-2307106NE96 Amazon AWS Graviton3E vs. Graviton 2/3 benchmarks - Phoronix Test Suite Amazon AWS Graviton3E vs. Graviton 2/3 benchmarks Benchmarks by Michael Larabel for a future article on Phoronix.com.
HTML result view exported from: https://openbenchmarking.org/result/2308110-NE-2307106NE96&sro&grw .
Amazon AWS Graviton3E vs. Graviton 2/3 benchmarks Processor Motherboard Chipset Memory Disk Network OS Kernel Compiler File-System System Layer Vulkan m7g.16xlarge Graviton3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E c6a.16xlarge AMD Zen 3 ARMv8 Neoverse-V1 (64 Cores) Amazon EC2 m7g.16xlarge (1.0 BIOS) Amazon Device 0200 256GB 215GB Amazon Elastic Block Store Amazon Elastic Ubuntu 22.04 5.19.0-1025-aws (aarch64) GCC 11.3.0 ext4 amazon ARMv8 Neoverse-N1 (64 Cores) Amazon EC2 c6g.16xlarge (1.0 BIOS) 128GB ARMv8 Neoverse-V1 (64 Cores) Amazon EC2 c7g.16xlarge (1.0 BIOS) Amazon EC2 c7gn.16xlarge (1.0 BIOS) AMD EPYC 7R13 (32 Cores / 64 Threads) Amazon EC2 c6a.16xlarge (1.0 BIOS) Intel 440FX 82441FX PMC 322GB Amazon Elastic Block Store 5.19.0-1025-aws (x86_64) 1.3.238 GCC 11.4.0 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - m7g.16xlarge Graviton3: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-bootstrap --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-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto -v - c6g.16xlarge Graviton2: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-bootstrap --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-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto -v - c7g.16xlarge Graviton3: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-bootstrap --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-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto -v - c7gn.16xlarge Graviton3E: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-bootstrap --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-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto -v - c6a.16xlarge AMD Zen 3: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/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-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 Python Details - m7g.16xlarge Graviton3: Python 3.10.6 - c6g.16xlarge Graviton2: Python 3.10.6 - c7g.16xlarge Graviton3: Python 3.10.6 - c7gn.16xlarge Graviton3E: Python 3.10.6 - c6a.16xlarge AMD Zen 3: Python 3.10.12 Security Details - m7g.16xlarge Graviton3: 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 __user pointer sanitization + spectre_v2: Mitigation of CSV2 BHB + srbds: Not affected + tsx_async_abort: Not affected - c6g.16xlarge Graviton2: 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 __user pointer sanitization + spectre_v2: Mitigation of CSV2 BHB + srbds: Not affected + tsx_async_abort: Not affected - c7g.16xlarge Graviton3: 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 __user pointer sanitization + spectre_v2: Mitigation of CSV2 BHB + srbds: Not affected + tsx_async_abort: Not affected - c7gn.16xlarge Graviton3E: 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 __user pointer sanitization + spectre_v2: Mitigation of CSV2 BHB + srbds: Not affected + tsx_async_abort: Not affected - c6a.16xlarge AMD Zen 3: 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: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected Processor Details - c6a.16xlarge AMD Zen 3: CPU Microcode: 0xa0011cf
Amazon AWS Graviton3E vs. Graviton 2/3 benchmarks heffte: c2c - FFTW - float - 128 heffte: c2c - FFTW - float - 256 laghos: Triple Point Problem laghos: Sedov Blast Wave, ube_922_hex.mesh stress-ng: NUMA stress-ng: CPU Cache stress-ng: Matrix Math stress-ng: Vector Math stress-ng: Matrix 3D Math stress-ng: Vector Shuffle heffte: c2c - FFTW - float - 512 stress-ng: Memory Copying stress-ng: Wide Vector Math stress-ng: Fused Multiply-Add stress-ng: Vector Floating Point graph500: 26 heffte: r2c - FFTW - float - 128 graph500: 26 heffte: r2c - FFTW - float - 256 graph500: 26 graph500: 26 heffte: r2c - FFTW - double - 256 heffte: r2c - FFTW - double - 512 heffte: r2c - FFTW - double - 128 heffte: c2c - FFTW - double - 512 heffte: c2c - FFTW - double - 256 heffte: c2c - FFTW - double - 128 nekrs: Kershaw nekrs: TurboPipe Periodic lczero: BLAS lczero: Eigen gromacs: MPI CPU - water_GMX50_bare lammps: 20k Atoms heffte: r2c - FFTW - float - 512 lammps: Rhodopsin Protein remhos: Sample Remap Example brl-cad: VGR Performance Metric npb: CG.C npb: EP.D npb: LU.C npb: MG.C npb: SP.C rodinia: OpenMP LavaMD rodinia: OpenMP CFD Solver rodinia: OpenMP Streamcluster mt-dgemm: Sustained Floating-Point Rate pennant: sedovbig pennant: leblancbig amg: kripke: lulesh: nwchem: C240 Buckyball mocassin: Gas HII40 mocassin: Dust 2D tau100.0 qmcpack: Li2_STO_ae qmcpack: simple-H2O qmcpack: FeCO6_b3lyp_gms qmcpack: FeCO6_b3lyp_gms incompact3d: input.i3d 129 Cells Per Direction incompact3d: input.i3d 193 Cells Per Direction gpaw: Carbon Nanotube coremark: CoreMark Size 666 - Iterations Per Second stockfish: Total Time compress-7zip: Compression Rating compress-7zip: Decompression Rating build-godot: Time To Compile build-gem5: Time To Compile build-nodejs: Time To Compile liquid-dsp: 32 - 256 - 32 liquid-dsp: 32 - 256 - 57 liquid-dsp: 64 - 256 - 32 liquid-dsp: 64 - 256 - 57 liquid-dsp: 32 - 256 - 512 liquid-dsp: 64 - 256 - 512 srsran: Downlink Processor Benchmark srsran: PUSCH Processor Benchmark, Throughput Total srsran: PUSCH Processor Benchmark, Throughput Thread nginx: 500 nginx: 1000 openssl: SHA256 openssl: SHA512 openssl: RSA4096 openssl: RSA4096 openssl: ChaCha20 openssl: AES-128-GCM openssl: AES-256-GCM openssl: ChaCha20-Poly1305 m7g.16xlarge Graviton3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E c6a.16xlarge AMD Zen 3 186.356 81.4442 232.01 410.55 3759.10 3892396.34 368750.67 217235.59 10403.93 54143.40 88.0482 20484.24 1542834.94 63762252.76 76102.55 1194320000 306.540 1227790000 164.873 299497000 419754000 78.5049 84.4739 138.014 46.2504 40.8923 57.1503 3150680000 3976300000 1301 1398 4.223 36.927 162.956 37.558 14.040 783777 21988.99 3738.98 28341.68 50126.29 17244.85 43.788 4.375 11.663 24.362353 9.206490 6.720537 1646761667 339000400 28296.378 1940.2 13.575 82.669 112.61 28.041 211.60 205.72 3.09871038 13.9454180 61.831 1601880.342264 112119711 316825 285540 154.378 180.247 237.783 1136066667 721493333 2270500000 1442400000 81396667 162753333 318.5 5413.8 95.8 255768.44 255616.04 54212515580 32125448870 10181.9 713859.5 103226784517 332033171900 283333113630 74287460990 135.358 41.9816 180.80 322.37 2112.66 1921785.20 284713.63 147886.14 5752.17 35614.51 42.8284 11324.79 997272.65 37732190.54 42850.82 860432000 209.496 874389000 92.3996 209350000 284689000 40.1104 44.9297 81.4498 24.2658 20.6279 32.7468 1760336667 2220190000 947 891 2.767 25.171 81.9412 25.950 20.740 533020 13103.62 2216.26 18741.90 25671.29 9711.70 62.224 6.051 13.735 20.417952 16.48050 12.17683 1035586333 220120233 17557.485 2976.9 20.758 145.374 165.12 45.225 302.19 297.94 5.63720735 25.8825658 92.760 1260642.177024 86609284 240702 234202 218.276 225.305 287.814 765466667 489270000 1531400000 978200000 67486333 134926667 197.2 3938.7 63.8 148964.69 158676.40 42472798847 14393925490 2624.3 214040.9 67292541203 158436163857 129199593157 46717636807 184.026 81.0096 230.68 408.01 3523.58 3844101.98 368671.39 217446.12 10813.59 54472.07 88.1842 20478.67 1535336.57 63818458.61 76178.46 1177710000 301.418 1206990000 162.010 293826000 415758000 77.7685 84.7451 133.514 46.3706 40.8283 55.1055 3261853333 3978983333 1333 1382 4.200 36.862 163.276 37.412 14.120 789066 21911.02 3664.54 28375.71 49742.30 17219.95 43.963 4.442 11.625 24.140605 9.422270 6.961345 1765277667 354442733 28708.656 1962.7 13.659 82.822 112.64 27.990 211.32 204.77 3.14447999 13.8326693 62.083 1605948.674645 117316476 311056 285633 156.687 181.779 238.543 1136133333 721386667 2271966667 1442366667 81412000 162766667 319.7 5356.8 95.7 255145.52 255552.05 54216561263 32145914147 10181.4 713945.9 103275516997 332064349843 283373795737 74318842213 184.110 81.1671 236.22 423.11 3525.17 3860335.38 369258.89 217567.10 10882.02 54695.04 88.4551 20475.96 1530043.52 63723431.55 76911.74 1175640000 300.396 1207760000 162.361 296164000 411762000 78.1658 85.0060 133.422 46.5300 40.9708 55.1038 3302823333 4141440000 1392 1444 4.820 36.838 163.559 37.482 14.082 744743 22155.36 3657.67 28369.11 49860.68 17163.11 44.044 4.429 10.690 24.078529 9.340953 6.839998 1765966333 354234067 28736.226 1914 13.525 82.974 113.20 27.999 188.28 204.25 3.11489828 13.7606726 56.440 1611801.559265 117027121 312009 285677 155.951 182.471 238.636 1136000000 721380000 2266833333 1442666667 81394000 162756667 323.2 5431.2 97.4 253518.51 256585.83 54154218593 32126059040 10183.3 713754.8 114118119423 411130469943 351152465420 79969465487 98.7026 43.5907 227.40 275.92 552.68 1447265.35 147576.41 221776.15 4571.96 22255.84 44.3176 8080.43 1380146.63 30920910.92 96529.51 410571000 158.858 417777000 102.652 157688000 204550000 41.5868 42.4394 86.3730 23.5212 20.8719 48.9432 4308810000 4337536667 1316 1152 3.965 20.342 82.7584 19.563 22.104 485038 20210.00 3061.42 95221.40 45946.81 34025.35 64.179 9.342 8.396 9.388050 16.53050 9.917565 836999300 237087650 16708.258 3440.4 12.669 194.435 123.95 26.867 184.10 187.32 7.01975288 30.3145288 89.818 1466587.036580 96905609 230970 235787 147.737 192.118 230.423 1193966667 1444266667 2184866667 1710800000 274803333 460076667 691.3 6479.1 215.9 165847.75 163178.67 45857534777 15291283297 8392.4 548396.5 138389378753 151449269317 138457889450 92522999373 OpenBenchmarking.org
HeFFTe - Highly Efficient FFT for Exascale Test: c2c - Backend: FFTW - Precision: float - X Y Z: 128 OpenBenchmarking.org GFLOP/s, More Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 Test: c2c - Backend: FFTW - Precision: float - X Y Z: 128 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 40 80 120 160 200 SE +/- 1.25, N = 14 SE +/- 0.35, N = 3 SE +/- 0.47, N = 3 SE +/- 0.20, N = 3 SE +/- 0.27, N = 3 98.70 135.36 184.03 184.11 186.36 1. (CXX) g++ options: -O3
HeFFTe - Highly Efficient FFT for Exascale Test: c2c - Backend: FFTW - Precision: float - X Y Z: 256 OpenBenchmarking.org GFLOP/s, More Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 Test: c2c - Backend: FFTW - Precision: float - X Y Z: 256 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 20 40 60 80 100 SE +/- 0.42, N = 6 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 SE +/- 0.01, N = 3 43.59 41.98 81.01 81.17 81.44 1. (CXX) g++ options: -O3
Laghos Test: Triple Point Problem OpenBenchmarking.org Major Kernels Total Rate, More Is Better Laghos 3.1 Test: Triple Point Problem c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 50 100 150 200 250 SE +/- 1.06, N = 3 SE +/- 0.48, N = 3 SE +/- 0.16, N = 3 SE +/- 0.27, N = 3 SE +/- 0.28, N = 3 227.40 180.80 230.68 236.22 232.01 1. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -lmpi_cxx -lmpi
Laghos Test: Sedov Blast Wave, ube_922_hex.mesh OpenBenchmarking.org Major Kernels Total Rate, More Is Better Laghos 3.1 Test: Sedov Blast Wave, ube_922_hex.mesh c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 90 180 270 360 450 SE +/- 0.48, N = 3 SE +/- 0.89, N = 3 SE +/- 0.89, N = 3 SE +/- 0.79, N = 3 SE +/- 0.42, N = 3 275.92 322.37 408.01 423.11 410.55 1. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -lmpi_cxx -lmpi
Stress-NG Test: NUMA OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.10 Test: NUMA c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 800 1600 2400 3200 4000 SE +/- 9.75, N = 15 SE +/- 1.53, N = 3 SE +/- 3.39, N = 3 SE +/- 7.31, N = 3 SE +/- 5.17, N = 3 552.68 2112.66 3523.58 3525.17 3759.10 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.10 Test: CPU Cache c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 800K 1600K 2400K 3200K 4000K SE +/- 30785.49, N = 12 SE +/- 21905.72, N = 15 SE +/- 59376.56, N = 15 SE +/- 40698.46, N = 15 SE +/- 57217.78, N = 15 1447265.35 1921785.20 3844101.98 3860335.38 3892396.34 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.10 Test: Matrix Math c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 80K 160K 240K 320K 400K SE +/- 167.77, N = 3 SE +/- 8.13, N = 3 SE +/- 38.76, N = 3 SE +/- 28.60, N = 3 SE +/- 53.44, N = 3 147576.41 284713.63 368671.39 369258.89 368750.67 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.10 Test: Vector Math c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 50K 100K 150K 200K 250K SE +/- 100.78, N = 3 SE +/- 37.96, N = 3 SE +/- 20.95, N = 3 SE +/- 27.00, N = 3 SE +/- 47.94, N = 3 221776.15 147886.14 217446.12 217567.10 217235.59 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
Stress-NG Test: Matrix 3D Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.10 Test: Matrix 3D Math c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 2K 4K 6K 8K 10K SE +/- 1.96, N = 3 SE +/- 1.40, N = 3 SE +/- 9.35, N = 3 SE +/- 19.16, N = 3 SE +/- 6.38, N = 3 4571.96 5752.17 10813.59 10882.02 10403.93 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
Stress-NG Test: Vector Shuffle OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.10 Test: Vector Shuffle c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 12K 24K 36K 48K 60K SE +/- 0.50, N = 3 SE +/- 74.80, N = 3 SE +/- 139.03, N = 3 SE +/- 294.96, N = 3 SE +/- 21.44, N = 3 22255.84 35614.51 54472.07 54695.04 54143.40 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
HeFFTe - Highly Efficient FFT for Exascale Test: c2c - Backend: FFTW - Precision: float - X Y Z: 512 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 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 20 40 60 80 100 SE +/- 0.14, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 44.32 42.83 88.18 88.46 88.05 1. (CXX) g++ options: -O3
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.10 Test: Memory Copying c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 4K 8K 12K 16K 20K SE +/- 0.46, N = 3 SE +/- 1.12, N = 3 SE +/- 4.65, N = 3 SE +/- 1.36, N = 3 SE +/- 3.80, N = 3 8080.43 11324.79 20478.67 20475.96 20484.24 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
Stress-NG Test: Wide Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.10 Test: Wide Vector Math c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 300K 600K 900K 1200K 1500K SE +/- 2507.18, N = 3 SE +/- 505.84, N = 3 SE +/- 16521.46, N = 15 SE +/- 16444.95, N = 15 SE +/- 16116.93, N = 15 1380146.63 997272.65 1535336.57 1530043.52 1542834.94 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
Stress-NG Test: Fused Multiply-Add OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.10 Test: Fused Multiply-Add c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 14M 28M 42M 56M 70M SE +/- 32747.05, N = 3 SE +/- 3687.67, N = 3 SE +/- 4431.60, N = 3 SE +/- 10061.51, N = 3 SE +/- 4870.19, N = 3 30920910.92 37732190.54 63818458.61 63723431.55 63762252.76 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
Stress-NG Test: Vector Floating Point OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.10 Test: Vector Floating Point c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 20K 40K 60K 80K 100K SE +/- 864.23, N = 13 SE +/- 31.31, N = 3 SE +/- 71.97, N = 3 SE +/- 1.74, N = 3 SE +/- 190.19, N = 3 96529.51 42850.82 76178.46 76911.74 76102.55 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lpthread -lrt -lsctp -lz
Graph500 Scale: 26 OpenBenchmarking.org bfs median_TEPS, More Is Better Graph500 3.0 Scale: 26 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 300M 600M 900M 1200M 1500M 410571000 860432000 1177710000 1175640000 1194320000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
HeFFTe - Highly Efficient FFT for Exascale Test: r2c - Backend: FFTW - Precision: float - X Y Z: 128 OpenBenchmarking.org GFLOP/s, More Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 Test: r2c - Backend: FFTW - Precision: float - X Y Z: 128 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 70 140 210 280 350 SE +/- 1.94, N = 3 SE +/- 0.64, N = 3 SE +/- 0.56, N = 3 SE +/- 1.62, N = 3 SE +/- 0.83, N = 3 158.86 209.50 301.42 300.40 306.54 1. (CXX) g++ options: -O3
Graph500 Scale: 26 OpenBenchmarking.org bfs max_TEPS, More Is Better Graph500 3.0 Scale: 26 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 300M 600M 900M 1200M 1500M 417777000 874389000 1206990000 1207760000 1227790000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
HeFFTe - Highly Efficient FFT for Exascale Test: r2c - Backend: FFTW - Precision: float - X Y Z: 256 OpenBenchmarking.org GFLOP/s, More Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 Test: r2c - Backend: FFTW - Precision: float - X Y Z: 256 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 40 80 120 160 200 SE +/- 1.28, N = 3 SE +/- 0.19, N = 3 SE +/- 0.11, N = 3 SE +/- 0.04, N = 3 SE +/- 0.27, N = 3 102.65 92.40 162.01 162.36 164.87 1. (CXX) g++ options: -O3
Graph500 Scale: 26 OpenBenchmarking.org sssp median_TEPS, More Is Better Graph500 3.0 Scale: 26 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 60M 120M 180M 240M 300M 157688000 209350000 293826000 296164000 299497000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
Graph500 Scale: 26 OpenBenchmarking.org sssp max_TEPS, More Is Better Graph500 3.0 Scale: 26 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 90M 180M 270M 360M 450M 204550000 284689000 415758000 411762000 419754000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
HeFFTe - Highly Efficient FFT for Exascale Test: r2c - Backend: FFTW - Precision: double - X Y Z: 256 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 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 20 40 60 80 100 SE +/- 0.17, N = 3 SE +/- 0.01, N = 3 SE +/- 0.31, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 41.59 40.11 77.77 78.17 78.50 1. (CXX) g++ options: -O3
HeFFTe - Highly Efficient FFT for Exascale Test: r2c - Backend: FFTW - Precision: double - X Y Z: 512 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 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 20 40 60 80 100 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 42.44 44.93 84.75 85.01 84.47 1. (CXX) g++ options: -O3
HeFFTe - Highly Efficient FFT for Exascale Test: r2c - Backend: FFTW - Precision: double - X Y Z: 128 OpenBenchmarking.org GFLOP/s, More Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 Test: r2c - Backend: FFTW - Precision: double - X Y Z: 128 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 30 60 90 120 150 SE +/- 1.46, N = 12 SE +/- 0.61, N = 3 SE +/- 0.47, N = 3 SE +/- 0.04, N = 3 SE +/- 0.12, N = 3 86.37 81.45 133.51 133.42 138.01 1. (CXX) g++ options: -O3
HeFFTe - Highly Efficient FFT for Exascale Test: c2c - Backend: FFTW - Precision: double - X Y Z: 512 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 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 11 22 33 44 55 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 23.52 24.27 46.37 46.53 46.25 1. (CXX) g++ options: -O3
HeFFTe - Highly Efficient FFT for Exascale Test: c2c - Backend: FFTW - Precision: double - X Y Z: 256 OpenBenchmarking.org GFLOP/s, More Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 Test: c2c - Backend: FFTW - Precision: double - X Y Z: 256 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 9 18 27 36 45 SE +/- 0.17, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 20.87 20.63 40.83 40.97 40.89 1. (CXX) g++ options: -O3
HeFFTe - Highly Efficient FFT for Exascale Test: c2c - Backend: FFTW - Precision: double - X Y Z: 128 OpenBenchmarking.org GFLOP/s, More Is Better HeFFTe - Highly Efficient FFT for Exascale 2.3 Test: c2c - Backend: FFTW - Precision: double - X Y Z: 128 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 13 26 39 52 65 SE +/- 0.85, N = 15 SE +/- 0.08, N = 3 SE +/- 0.15, N = 3 SE +/- 0.32, N = 3 SE +/- 0.28, N = 3 48.94 32.75 55.11 55.10 57.15 1. (CXX) g++ options: -O3
nekRS Input: Kershaw OpenBenchmarking.org flops/rank, More Is Better nekRS 23.0 Input: Kershaw c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 900M 1800M 2700M 3600M 4500M SE +/- 22342148.51, N = 3 SE +/- 737119.02, N = 3 SE +/- 2490845.46, N = 3 SE +/- 5414395.42, N = 3 SE +/- 1575066.14, N = 3 4308810000 1760336667 3261853333 3302823333 3150680000 1. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -rdynamic -lmpi_cxx -lmpi
nekRS Input: TurboPipe Periodic OpenBenchmarking.org flops/rank, More Is Better nekRS 23.0 Input: TurboPipe Periodic c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 900M 1800M 2700M 3600M 4500M SE +/- 12801180.07, N = 3 SE +/- 144222.05, N = 3 SE +/- 169148.19, N = 3 SE +/- 1394740.12, N = 3 SE +/- 1199180.28, N = 3 4337536667 2220190000 3978983333 4141440000 3976300000 1. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -rdynamic -lmpi_cxx -lmpi
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: BLAS c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 300 600 900 1200 1500 SE +/- 13.29, N = 5 SE +/- 11.79, N = 3 SE +/- 3.53, N = 3 SE +/- 7.22, N = 3 SE +/- 4.67, N = 3 1316 947 1333 1392 1301 1. (CXX) g++ options: -flto -pthread
LeelaChessZero Backend: Eigen OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: Eigen c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 300 600 900 1200 1500 SE +/- 7.37, N = 3 SE +/- 4.73, N = 3 SE +/- 15.65, N = 3 SE +/- 14.88, N = 3 SE +/- 8.74, N = 3 1152 891 1382 1444 1398 1. (CXX) g++ options: -flto -pthread
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2023 Implementation: MPI CPU - Input: water_GMX50_bare c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 1.0845 2.169 3.2535 4.338 5.4225 SE +/- 0.013, N = 3 SE +/- 0.002, N = 3 SE +/- 0.004, N = 3 SE +/- 0.003, N = 3 SE +/- 0.003, N = 3 3.965 2.767 4.200 4.820 4.223 1. (CXX) g++ options: -O3
LAMMPS Molecular Dynamics Simulator Model: 20k Atoms OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: 20k Atoms c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 8 16 24 32 40 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 20.34 25.17 36.86 36.84 36.93 -lm 1. (CXX) g++ options: -O3 -ldl
HeFFTe - Highly Efficient FFT for Exascale Test: r2c - Backend: FFTW - Precision: float - X Y Z: 512 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 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 40 80 120 160 200 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.13, N = 3 82.76 81.94 163.28 163.56 162.96 1. (CXX) g++ options: -O3
LAMMPS Molecular Dynamics Simulator Model: Rhodopsin Protein OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: Rhodopsin Protein c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 9 18 27 36 45 SE +/- 0.26, N = 12 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 19.56 25.95 37.41 37.48 37.56 -lm 1. (CXX) g++ options: -O3 -ldl
Remhos Test: Sample Remap Example OpenBenchmarking.org Seconds, Fewer Is Better Remhos 1.0 Test: Sample Remap Example c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 5 10 15 20 25 SE +/- 0.11, N = 3 SE +/- 0.08, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 22.10 20.74 14.12 14.08 14.04 1. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -lmpi_cxx -lmpi
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.34 VGR Performance Metric c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 200K 400K 600K 800K 1000K 485038 533020 789066 744743 783777 -m64 1. (CXX) g++ options: -std=c++14 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lregex_brl -lz_brl -lnetpbm -ldl -lm -ltk8.6
NAS Parallel Benchmarks Test / Class: CG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 5K 10K 15K 20K 25K SE +/- 14.83, N = 3 SE +/- 31.56, N = 3 SE +/- 283.23, N = 3 SE +/- 125.21, N = 3 SE +/- 130.18, N = 3 20210.00 13103.62 21911.02 22155.36 21988.99 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 4.1.2
NAS Parallel Benchmarks Test / Class: EP.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 800 1600 2400 3200 4000 SE +/- 4.77, N = 3 SE +/- 2.22, N = 3 SE +/- 34.07, N = 15 SE +/- 32.06, N = 15 SE +/- 1.69, N = 3 3061.42 2216.26 3664.54 3657.67 3738.98 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 4.1.2
NAS Parallel Benchmarks Test / Class: LU.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 20K 40K 60K 80K 100K SE +/- 90.22, N = 3 SE +/- 26.12, N = 3 SE +/- 36.09, N = 3 SE +/- 43.73, N = 3 SE +/- 48.62, N = 3 95221.40 18741.90 28375.71 28369.11 28341.68 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 4.1.2
NAS Parallel Benchmarks Test / Class: MG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 11K 22K 33K 44K 55K SE +/- 167.32, N = 3 SE +/- 7.02, N = 3 SE +/- 32.94, N = 3 SE +/- 14.65, N = 3 SE +/- 24.30, N = 3 45946.81 25671.29 49742.30 49860.68 50126.29 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 4.1.2
NAS Parallel Benchmarks Test / Class: SP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 7K 14K 21K 28K 35K SE +/- 20.85, N = 3 SE +/- 1.54, N = 3 SE +/- 7.21, N = 3 SE +/- 31.31, N = 3 SE +/- 10.19, N = 3 34025.35 9711.70 17219.95 17163.11 17244.85 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 4.1.2
Rodinia Test: OpenMP LavaMD OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP LavaMD c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 14 28 42 56 70 SE +/- 0.53, N = 3 SE +/- 0.04, N = 3 SE +/- 0.11, N = 3 SE +/- 0.15, N = 3 SE +/- 0.15, N = 3 64.18 62.22 43.96 44.04 43.79 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP CFD Solver OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP CFD Solver c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 3 6 9 12 15 SE +/- 0.002, N = 3 SE +/- 0.016, N = 3 SE +/- 0.021, N = 3 SE +/- 0.027, N = 3 SE +/- 0.011, N = 3 9.342 6.051 4.442 4.429 4.375 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP Streamcluster OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Streamcluster c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 4 8 12 16 20 SE +/- 0.101, N = 15 SE +/- 0.211, N = 15 SE +/- 0.099, N = 8 SE +/- 0.233, N = 12 SE +/- 0.138, N = 3 8.396 13.735 11.625 10.690 11.663 1. (CXX) g++ options: -O2 -lOpenCL
ACES DGEMM Sustained Floating-Point Rate OpenBenchmarking.org GFLOP/s, More Is Better ACES DGEMM 1.0 Sustained Floating-Point Rate c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 6 12 18 24 30 SE +/- 0.038051, N = 3 SE +/- 0.154503, N = 3 SE +/- 0.285590, N = 4 SE +/- 0.297525, N = 4 SE +/- 0.171001, N = 13 9.388050 20.417952 24.140605 24.078529 24.362353 1. (CC) gcc options: -O3 -march=native -fopenmp
Pennant Test: sedovbig OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: sedovbig c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 4 8 12 16 20 SE +/- 0.036687, N = 3 SE +/- 0.018218, N = 3 SE +/- 0.011497, N = 3 SE +/- 0.003721, N = 3 SE +/- 0.011347, N = 3 16.530500 16.480500 9.422270 9.340953 9.206490 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 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 3 6 9 12 15 SE +/- 0.013289, N = 3 SE +/- 0.018924, N = 3 SE +/- 0.005468, N = 3 SE +/- 0.000467, N = 3 SE +/- 0.000869, N = 3 9.917565 12.176830 6.961345 6.839998 6.720537 1. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
Algebraic Multi-Grid Benchmark OpenBenchmarking.org Figure Of Merit, More Is Better Algebraic Multi-Grid Benchmark 1.2 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 400M 800M 1200M 1600M 2000M SE +/- 1055539.30, N = 3 SE +/- 140169.34, N = 3 SE +/- 192645.90, N = 3 SE +/- 488508.39, N = 3 SE +/- 103191.30, N = 3 836999300 1035586333 1765277667 1765966333 1646761667 1. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi
Kripke OpenBenchmarking.org Throughput FoM, More Is Better Kripke 1.2.6 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 80M 160M 240M 320M 400M SE +/- 2932840.19, N = 4 SE +/- 102787.75, N = 3 SE +/- 525406.56, N = 3 SE +/- 445212.18, N = 3 SE +/- 619419.33, N = 3 237087650 220120233 354442733 354234067 339000400 1. (CXX) g++ options: -O3 -fopenmp -ldl
LULESH OpenBenchmarking.org z/s, More Is Better LULESH 2.0.3 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 6K 12K 18K 24K 30K SE +/- 90.11, N = 3 SE +/- 38.55, N = 3 SE +/- 11.81, N = 3 SE +/- 12.73, N = 3 SE +/- 27.09, N = 3 16708.26 17557.49 28708.66 28736.23 28296.38 1. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi
NWChem Input: C240 Buckyball OpenBenchmarking.org Seconds, Fewer Is Better NWChem 7.0.2 Input: C240 Buckyball c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 700 1400 2100 2800 3500 3440.4 2976.9 1962.7 1914.0 1940.2 -m64 1. (F9X) gfortran options: -lnwctask -lccsd -lmcscf -lselci -lmp2 -lmoints -lstepper -ldriver -loptim -lnwdft -lgradients -lcphf -lesp -lddscf -ldangchang -lguess -lhessian -lvib -lnwcutil -lrimp2 -lproperty -lsolvation -lnwints -lprepar -lnwmd -lnwpw -lofpw -lpaw -lpspw -lband -lnwpwlib -lcafe -lspace -lanalyze -lqhop -lpfft -ldplot -ldrdy -lvscf -lqmmm -lqmd -letrans -ltce -lbq -lmm -lcons -lperfm -ldntmc -lccca -ldimqm -lga -larmci -lpeigs -l64to32 -lopenblas -lpthread -lrt -llapack -lnwcblas -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -lcomex -ffast-math -std=legacy -fdefault-integer-8 -finline-functions -O2
Monte Carlo Simulations of Ionised Nebulae Input: Gas HII40 OpenBenchmarking.org Seconds, Fewer Is Better Monte Carlo Simulations of Ionised Nebulae 2.02.73.3 Input: Gas HII40 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.17, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 12.67 20.76 13.66 13.53 13.58 1. (F9X) gfortran options: -cpp -Jsource/ -ffree-line-length-0 -lm -std=legacy -O2 -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lz
Monte Carlo Simulations of Ionised Nebulae Input: Dust 2D tau100.0 OpenBenchmarking.org Seconds, Fewer Is Better Monte Carlo Simulations of Ionised Nebulae 2.02.73.3 Input: Dust 2D tau100.0 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 40 80 120 160 200 SE +/- 1.84, N = 7 SE +/- 0.86, N = 3 SE +/- 0.00, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 194.44 145.37 82.82 82.97 82.67 1. (F9X) gfortran options: -cpp -Jsource/ -ffree-line-length-0 -lm -std=legacy -O2 -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lz
QMCPACK Input: Li2_STO_ae OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.16 Input: Li2_STO_ae c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 40 80 120 160 200 SE +/- 0.13, N = 3 SE +/- 1.13, N = 3 SE +/- 0.12, N = 3 SE +/- 0.31, N = 3 SE +/- 0.08, N = 3 123.95 165.12 112.64 113.20 112.61 -march=native -mcpu=native -mcpu=native -mcpu=native -mcpu=native 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -O3 -lm -ldl
QMCPACK Input: simple-H2O OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.16 Input: simple-H2O c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 10 20 30 40 50 SE +/- 0.08, N = 3 SE +/- 0.24, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 26.87 45.23 27.99 28.00 28.04 -march=native -mcpu=native -mcpu=native -mcpu=native -mcpu=native 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -O3 -lm -ldl
QMCPACK Input: FeCO6_b3lyp_gms OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.16 Input: FeCO6_b3lyp_gms c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 70 140 210 280 350 SE +/- 1.03, N = 3 SE +/- 0.37, N = 3 SE +/- 0.19, N = 3 SE +/- 0.29, N = 3 SE +/- 0.22, N = 3 184.10 302.19 211.32 188.28 211.60 -march=native -mcpu=native -mcpu=native -mcpu=native -mcpu=native 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -O3 -lm -ldl
QMCPACK Input: FeCO6_b3lyp_gms OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.16 Input: FeCO6_b3lyp_gms c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 60 120 180 240 300 SE +/- 2.30, N = 3 SE +/- 1.75, N = 3 SE +/- 0.82, N = 3 SE +/- 0.21, N = 3 SE +/- 0.45, N = 3 187.32 297.94 204.77 204.25 205.72 -march=native -mcpu=native -mcpu=native -mcpu=native -mcpu=native 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -O3 -lm -ldl
Xcompact3d Incompact3d Input: input.i3d 129 Cells Per Direction OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 129 Cells Per Direction c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 2 4 6 8 10 SE +/- 0.08686597, N = 15 SE +/- 0.02560507, N = 3 SE +/- 0.03233273, N = 3 SE +/- 0.01738352, N = 3 SE +/- 0.02702838, N = 3 7.01975288 5.63720735 3.14447999 3.11489828 3.09871038 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
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 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 7 14 21 28 35 SE +/- 0.28, N = 3 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 30.31 25.88 13.83 13.76 13.95 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
GPAW Input: Carbon Nanotube OpenBenchmarking.org Seconds, Fewer Is Better GPAW 23.6 Input: Carbon Nanotube c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 20 40 60 80 100 SE +/- 0.13, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 89.82 92.76 62.08 56.44 61.83 1. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 300K 600K 900K 1200K 1500K SE +/- 6710.50, N = 3 SE +/- 153.60, N = 3 SE +/- 13274.76, N = 15 SE +/- 14869.41, N = 7 SE +/- 11449.37, N = 15 1466587.04 1260642.18 1605948.67 1611801.56 1601880.34 1. (CC) gcc options: -O2 -lrt" -lrt
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 15 Total Time c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 30M 60M 90M 120M 150M SE +/- 1430593.84, N = 15 SE +/- 2597495.37, N = 15 SE +/- 2998209.87, N = 12 SE +/- 1531345.46, N = 15 SE +/- 2854071.93, N = 15 96905609 86609284 117316476 117027121 112119711 -m64 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -mbmi2 1. (CXX) g++ options: -lgcov -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -flto -flto=jobserver
7-Zip Compression Test: Compression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Compression Rating c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 70K 140K 210K 280K 350K SE +/- 670.46, N = 3 SE +/- 209.44, N = 3 SE +/- 72.90, N = 3 SE +/- 308.14, N = 3 SE +/- 154.72, N = 3 230970 240702 311056 312009 316825 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
7-Zip Compression Test: Decompression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Decompression Rating c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 60K 120K 180K 240K 300K SE +/- 1190.65, N = 3 SE +/- 15.43, N = 3 SE +/- 146.43, N = 3 SE +/- 54.90, N = 3 SE +/- 93.51, N = 3 235787 234202 285633 285677 285540 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 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 50 100 150 200 250 SE +/- 0.12, N = 3 SE +/- 0.30, N = 3 SE +/- 0.63, N = 3 SE +/- 0.45, N = 3 SE +/- 0.32, N = 3 147.74 218.28 156.69 155.95 154.38
Timed Gem5 Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Gem5 Compilation 21.2 Time To Compile c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 50 100 150 200 250 SE +/- 0.26, N = 3 SE +/- 0.35, N = 3 SE +/- 0.26, N = 3 SE +/- 0.38, N = 3 SE +/- 0.13, N = 3 192.12 225.31 181.78 182.47 180.25
Timed Node.js Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 19.8.1 Time To Compile c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 60 120 180 240 300 SE +/- 0.40, N = 3 SE +/- 0.16, N = 3 SE +/- 0.20, N = 3 SE +/- 0.32, N = 3 SE +/- 0.33, N = 3 230.42 287.81 238.54 238.64 237.78
Liquid-DSP Threads: 32 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 32 - Buffer Length: 256 - Filter Length: 32 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 300M 600M 900M 1200M 1500M SE +/- 578311.72, N = 3 SE +/- 456520.66, N = 3 SE +/- 33333.33, N = 3 SE +/- 57735.03, N = 3 SE +/- 233333.33, N = 3 1193966667 765466667 1136133333 1136000000 1136066667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Liquid-DSP Threads: 32 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 32 - Buffer Length: 256 - Filter Length: 57 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 300M 600M 900M 1200M 1500M SE +/- 9533333.33, N = 3 SE +/- 23094.01, N = 3 SE +/- 168358.08, N = 3 SE +/- 150111.07, N = 3 SE +/- 3333.33, N = 3 1444266667 489270000 721386667 721380000 721493333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Liquid-DSP Threads: 64 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 32 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 500M 1000M 1500M 2000M 2500M SE +/- 218581.28, N = 3 SE +/- 251661.15, N = 3 SE +/- 284800.12, N = 3 SE +/- 2915666.50, N = 3 SE +/- 435889.89, N = 3 2184866667 1531400000 2271966667 2266833333 2270500000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Liquid-DSP Threads: 64 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 57 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 400M 800M 1200M 1600M 2000M SE +/- 1014889.16, N = 3 SE +/- 11547.01, N = 3 SE +/- 284800.12, N = 3 SE +/- 88191.71, N = 3 SE +/- 152752.52, N = 3 1710800000 978200000 1442366667 1442666667 1442400000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Liquid-DSP Threads: 32 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 32 - Buffer Length: 256 - Filter Length: 512 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 60M 120M 180M 240M 300M SE +/- 193419.52, N = 3 SE +/- 333.33, N = 3 SE +/- 1000.00, N = 3 SE +/- 577.35, N = 3 SE +/- 1855.92, N = 3 274803333 67486333 81412000 81394000 81396667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Liquid-DSP Threads: 64 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 512 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 100M 200M 300M 400M 500M SE +/- 392527.42, N = 3 SE +/- 3333.33, N = 3 SE +/- 3333.33, N = 3 SE +/- 8819.17, N = 3 SE +/- 6666.67, N = 3 460076667 134926667 162766667 162756667 162753333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
srsRAN Project Test: Downlink Processor Benchmark OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.5 Test: Downlink Processor Benchmark c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 150 300 450 600 750 SE +/- 1.26, N = 3 SE +/- 0.25, N = 3 SE +/- 0.95, N = 3 SE +/- 0.06, N = 3 SE +/- 0.91, N = 3 691.3 197.2 319.7 323.2 318.5 -march=native -mfma 1. (CXX) g++ options: -O3 -fno-trapping-math -fno-math-errno -lgtest
srsRAN Project Test: PUSCH Processor Benchmark, Throughput Total OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.5 Test: PUSCH Processor Benchmark, Throughput Total c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 1400 2800 4200 5600 7000 SE +/- 21.76, N = 3 SE +/- 2.53, N = 3 SE +/- 1.80, N = 3 SE +/- 3.32, N = 3 SE +/- 4.08, N = 3 6479.1 3938.7 5356.8 5431.2 5413.8 -march=native -mfma 1. (CXX) g++ options: -O3 -fno-trapping-math -fno-math-errno -lgtest
srsRAN Project Test: PUSCH Processor Benchmark, Throughput Thread OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.5 Test: PUSCH Processor Benchmark, Throughput Thread c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 50 100 150 200 250 SE +/- 0.55, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 215.9 63.8 95.7 97.4 95.8 -march=native -mfma 1. (CXX) g++ options: -O3 -fno-trapping-math -fno-math-errno -lgtest
nginx Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 500 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 50K 100K 150K 200K 250K SE +/- 60.38, N = 3 SE +/- 90.87, N = 3 SE +/- 243.69, N = 3 SE +/- 317.05, N = 3 SE +/- 323.56, N = 3 165847.75 148964.69 255145.52 253518.51 255768.44 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
nginx Connections: 1000 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 1000 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 50K 100K 150K 200K 250K SE +/- 136.82, N = 3 SE +/- 185.79, N = 3 SE +/- 55.97, N = 3 SE +/- 402.16, N = 3 SE +/- 137.20, N = 3 163178.67 158676.40 255552.05 256585.83 255616.04 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenSSL Algorithm: SHA256 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.1 Algorithm: SHA256 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 12000M 24000M 36000M 48000M 60000M SE +/- 26770675.21, N = 3 SE +/- 245440310.03, N = 3 SE +/- 16491036.11, N = 3 SE +/- 19542665.92, N = 3 SE +/- 18610524.10, N = 3 45857534777 42472798847 54216561263 54154218593 54212515580 -m64 1. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: SHA512 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.1 Algorithm: SHA512 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 7000M 14000M 21000M 28000M 35000M SE +/- 207279.55, N = 3 SE +/- 9173912.49, N = 3 SE +/- 4573992.60, N = 3 SE +/- 16155877.53, N = 3 SE +/- 17714077.14, N = 3 15291283297 14393925490 32145914147 32126059040 32125448870 -m64 1. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.1 Algorithm: RSA4096 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 2K 4K 6K 8K 10K SE +/- 3.06, N = 3 SE +/- 1.71, N = 3 SE +/- 1.54, N = 3 SE +/- 0.84, N = 3 SE +/- 1.27, N = 3 8392.4 2624.3 10181.4 10183.3 10181.9 -m64 1. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org verify/s, More Is Better OpenSSL 3.1 Algorithm: RSA4096 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 150K 300K 450K 600K 750K SE +/- 34.73, N = 3 SE +/- 88.30, N = 3 SE +/- 12.03, N = 3 SE +/- 198.10, N = 3 SE +/- 21.82, N = 3 548396.5 214040.9 713945.9 713754.8 713859.5 -m64 1. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: ChaCha20 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.1 Algorithm: ChaCha20 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 30000M 60000M 90000M 120000M 150000M SE +/- 36376378.52, N = 3 SE +/- 35952887.59, N = 3 SE +/- 1725060.95, N = 3 SE +/- 771581.87, N = 3 SE +/- 1293723.80, N = 3 138389378753 67292541203 103275516997 114118119423 103226784517 -m64 1. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: AES-128-GCM OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.1 Algorithm: AES-128-GCM c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 90000M 180000M 270000M 360000M 450000M SE +/- 4227452.23, N = 3 SE +/- 9833681.11, N = 3 SE +/- 12264074.61, N = 3 SE +/- 11273100.69, N = 3 SE +/- 81289574.27, N = 3 151449269317 158436163857 332064349843 411130469943 332033171900 -m64 1. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: AES-256-GCM OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.1 Algorithm: AES-256-GCM c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 80000M 160000M 240000M 320000M 400000M SE +/- 41584947.90, N = 3 SE +/- 2312792.64, N = 3 SE +/- 33807617.40, N = 3 SE +/- 24279491.44, N = 3 SE +/- 6411836.47, N = 3 138457889450 129199593157 283373795737 351152465420 283333113630 -m64 1. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: ChaCha20-Poly1305 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.1 Algorithm: ChaCha20-Poly1305 c6a.16xlarge AMD Zen 3 c6g.16xlarge Graviton2 c7g.16xlarge Graviton3 c7gn.16xlarge Graviton3E m7g.16xlarge Graviton3 20000M 40000M 60000M 80000M 100000M SE +/- 232372675.93, N = 3 SE +/- 1132293.08, N = 3 SE +/- 1218886.42, N = 3 SE +/- 1769561.47, N = 3 SE +/- 1340503.89, N = 3 92522999373 46717636807 74318842213 79969465487 74287460990 -m64 1. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl
Phoronix Test Suite v10.8.4