Amazon EC2 benchmarking for a future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2112046-TJ-2108199TJ92 Intel M6i Ice Lake vs. Graviton2 Amazon EC2 Benchmarks - Phoronix Test Suite Intel M6i Ice Lake vs. Graviton2 Amazon EC2 Benchmarks Amazon EC2 benchmarking for a future article.
HTML result view exported from: https://openbenchmarking.org/result/2112046-TJ-2108199TJ92&grr&sro .
Intel M6i Ice Lake vs. Graviton2 Amazon EC2 Benchmarks Processor Motherboard Memory Disk Network Chipset OS Kernel Vulkan Compiler File-System System Layer m6g.metal m5.24xlarge m6i.24xlarge m6i.32xlarge m6a.24xlarge ARMv8 Neoverse-N1 (64 Cores) Amazon EC2 m6g.metal v1.0 252GB 107GB Amazon Elastic Block Store Amazon Elastic Ubuntu 20.04 5.4.0-1045-aws (aarch64) 1.0.2 GCC 9.3.0 ext4 2 x Intel Xeon Platinum 8259CL (48 Cores / 96 Threads) Amazon EC2 m5.24xlarge (1.0 BIOS) Intel 440FX 82441FX PMC 374GB 5.4.0-1045-aws (x86_64) KVM 2 x Intel Xeon Platinum 8375C (48 Cores / 96 Threads) Amazon EC2 m6i.24xlarge (1.0 BIOS) 372GB 2 x Intel Xeon Platinum 8375C (64 Cores / 128 Threads) Amazon EC2 m6i.32xlarge (1.0 BIOS) 496GB AMD EPYC 7R13 (48 Cores / 96 Threads) Amazon EC2 m6a.24xlarge (1.0 BIOS) 370GB 5.11.0-1020-aws (x86_64) OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - m6g.metal: --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --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-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto -v - m5.24xlarge: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - m6i.24xlarge: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - m6i.32xlarge: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - m6a.24xlarge: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Java Details - m6g.metal, m5.24xlarge: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.04) Security Details - m6g.metal: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 - m5.24xlarge: itlb_multihit: KVM: Vulnerable + l1tf: Mitigation of PTE Inversion + mds: Vulnerable: Clear buffers attempted no microcode; SMT Host state unknown + meltdown: Mitigation of PTI + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected - m6i.24xlarge: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected - m6i.32xlarge: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected - m6a.24xlarge: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected Processor Details - m5.24xlarge: CPU Microcode: 0x5003005 - m6i.24xlarge: CPU Microcode: 0xd0002b1 - m6i.32xlarge: CPU Microcode: 0xd0002b1 - m6a.24xlarge: CPU Microcode: 0xa001143
Intel M6i Ice Lake vs. Graviton2 Amazon EC2 Benchmarks tnn: CPU - DenseNet asmfish: 1024 Hash Memory, 26 Depth hpcg: povray: Trace Time minife: Small npb: EP.D rocksdb: Rand Read stockfish: Total Time npb: BT.C coremark: CoreMark Size 666 - Iterations Per Second tnn: CPU - MobileNet v2 tnn: CPU - SqueezeNet v1.1 incompact3d: input.i3d 193 Cells Per Direction pennant: sedovbig m-queens: Time To Solve npb: FT.C lulesh: pennant: leblancbig npb: CG.C tnn: CPU - SqueezeNet v2 npb: EP.C n-queens: Elapsed Time incompact3d: input.i3d 129 Cells Per Direction npb: MG.C m6g.metal m5.24xlarge m6i.24xlarge m6i.32xlarge m6a.24xlarge 3288.829 104868482 21.4570 57.439 23848.2 2233.14 270332614 96657449 24464.82 1236555.803752 365.839 341.315 23.2480348 15.41301 19.430 21850.28 16867.370 11.29726 13438.71 105.072 2218.08 3.761 5.18380547 25872.77 3797.589 115160185 26.8884 42.964 14007.1 4875.47 194576074 105658561 104533.15 1451630.519049 426.094 394.508 21.4682878 25.22237 22.341 50800.74 16272.587 10.03026 30206.03 93.266 4777.13 3.892 4.76513163 65732.22 3522.581 136656900 37.2245 10.631 19946.4 6752.38 231109408 136790816 136431.11 1607068.543334 350.378 357.721 14.9058580 17.24513 16.068 70031.71 22519.115 6.413928 33146.76 70.932 6426.32 3.144 3.49298970 88248.73 3524.690 169329043 39.1328 9.015 18797.6 8765.66 298073130 169762583 202455.31 2128843.094210 349.167 357.689 12.5943028 15.14226 12.334 102661.18 35739.821 5.105541 38736.50 70.518 8107.02 2.312 2.95411030 117771.92 2866.455 130814939 17.0281 10.726 11197.8 2780.04 269589717 127232305 92962.40 1850380.040001 312.780 282.809 24.9592756 12.27951 12.334 54008.74 16745.120 7.508991 23714.82 78.819 2759.76 2.382 5.42248488 49638.45 OpenBenchmarking.org
TNN Target: CPU - Model: DenseNet OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 800 1600 2400 3200 4000 SE +/- 2.50, N = 3 SE +/- 1.59, N = 3 SE +/- 4.12, N = 3 SE +/- 3.59, N = 3 SE +/- 0.73, N = 3 3797.59 2866.46 3288.83 3522.58 3524.69 MIN: 3754.49 / MAX: 4081.73 MIN: 2825.11 / MAX: 2989.74 MIN: 3237.1 / MAX: 3327.59 MIN: 3492.16 / MAX: 3621.39 MIN: 3482.31 / MAX: 3882.56 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
asmFish 1024 Hash Memory, 26 Depth OpenBenchmarking.org Nodes/second, More Is Better asmFish 2018-07-23 1024 Hash Memory, 26 Depth m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 40M 80M 120M 160M 200M SE +/- 806502.14, N = 12 SE +/- 280698.15, N = 3 SE +/- 1056350.97, N = 3 SE +/- 1425879.59, N = 3 SE +/- 870392.07, N = 3 115160185 130814939 104868482 136656900 169329043
High Performance Conjugate Gradient OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 9 18 27 36 45 SE +/- 0.17, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.13, N = 3 26.89 17.03 21.46 37.22 39.13 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi
POV-Ray Trace Time OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray 3.7.0.7 Trace Time m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 13 26 39 52 65 SE +/- 4.195, N = 15 SE +/- 0.016, N = 3 SE +/- 0.915, N = 15 SE +/- 0.059, N = 3 SE +/- 0.105, N = 3 42.964 10.726 57.439 10.631 9.015 -march=native -lSM -lICE -lX11 -march=native -lSM -lICE -lX11 -march=native -lSM -lICE -lX11 -march=native 1. (CXX) g++ options: -pipe -O3 -ffast-math -pthread -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
miniFE Problem Size: Small OpenBenchmarking.org CG Mflops, More Is Better miniFE 2.2 Problem Size: Small m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 5K 10K 15K 20K 25K SE +/- 284.82, N = 15 SE +/- 149.74, N = 15 SE +/- 5.77, N = 3 SE +/- 817.97, N = 15 SE +/- 590.35, N = 15 14007.1 11197.8 23848.2 19946.4 18797.6 1. (CXX) g++ options: -O3 -fopenmp -pthread -lmpi_cxx -lmpi
NAS Parallel Benchmarks Test / Class: EP.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 2K 4K 6K 8K 10K SE +/- 257.35, N = 12 SE +/- 4.54, N = 3 SE +/- 1.71, N = 3 SE +/- 78.27, N = 15 SE +/- 77.50, N = 15 4875.47 2780.04 2233.14 6752.38 8765.66 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Read m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 60M 120M 180M 240M 300M SE +/- 128495.22, N = 3 SE +/- 749179.54, N = 3 SE +/- 1242136.86, N = 3 SE +/- 1027109.62, N = 3 SE +/- 2848830.44, N = 3 194576074 269589717 270332614 231109408 298073130 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 13 Total Time m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 40M 80M 120M 160M 200M SE +/- 1176206.14, N = 15 SE +/- 1261758.38, N = 6 SE +/- 692846.14, N = 3 SE +/- 185784.28, N = 3 SE +/- 554216.71, N = 3 105658561 127232305 96657449 136790816 169762583 -m64 -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -msse4.1 -mssse3 -msse2 -mbmi2 -m64 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -m64 -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -m64 -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 1. (CXX) g++ options: -lgcov -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -flto -flto=jobserver
NAS Parallel Benchmarks Test / Class: BT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 40K 80K 120K 160K 200K SE +/- 119.93, N = 3 SE +/- 140.47, N = 3 SE +/- 12.96, N = 3 SE +/- 147.64, N = 3 SE +/- 156.09, N = 3 104533.15 92962.40 24464.82 136431.11 202455.31 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 500K 1000K 1500K 2000K 2500K SE +/- 5103.90, N = 3 SE +/- 16150.98, N = 3 SE +/- 279.74, N = 3 SE +/- 8144.03, N = 3 SE +/- 2056.46, N = 3 1451630.52 1850380.04 1236555.80 1607068.54 2128843.09 1. (CC) gcc options: -O2 -lrt" -lrt
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 90 180 270 360 450 SE +/- 0.52, N = 3 SE +/- 1.81, N = 3 SE +/- 0.26, N = 3 SE +/- 0.24, N = 3 SE +/- 0.19, N = 3 426.09 312.78 365.84 350.38 349.17 MIN: 422.84 / MAX: 477.54 MIN: 309.33 / MAX: 382.03 MIN: 364.34 / MAX: 367.32 MIN: 348.46 / MAX: 395.91 MIN: 346.78 / MAX: 378.54 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 90 180 270 360 450 SE +/- 0.14, N = 3 SE +/- 0.32, N = 3 SE +/- 0.83, N = 3 SE +/- 0.23, N = 3 SE +/- 0.00, N = 3 394.51 282.81 341.32 357.72 357.69 MIN: 393.65 / MAX: 397.65 MIN: 281.46 / MAX: 315.41 MIN: 338.67 / MAX: 344.11 MIN: 356.98 / MAX: 361.71 MIN: 357.05 / MAX: 360.09 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
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 m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 6 12 18 24 30 SE +/- 0.11, N = 3 SE +/- 0.25, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 21.47 24.96 23.25 14.91 12.59 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
Pennant Test: sedovbig OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: sedovbig m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 25.22 12.28 15.41 17.25 15.14 1. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi
m-queens Time To Solve OpenBenchmarking.org Seconds, Fewer Is Better m-queens 1.2 Time To Solve m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 5 10 15 20 25 SE +/- 0.13, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.19, N = 3 SE +/- 0.14, N = 4 22.34 12.33 19.43 16.07 12.33 1. (CXX) g++ options: -fopenmp -O2 -march=native
NAS Parallel Benchmarks Test / Class: FT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 20K 40K 60K 80K 100K SE +/- 441.43, N = 15 SE +/- 84.37, N = 3 SE +/- 2.47, N = 3 SE +/- 54.84, N = 3 SE +/- 1220.06, N = 4 50800.74 54008.74 21850.28 70031.71 102661.18 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
LULESH OpenBenchmarking.org z/s, More Is Better LULESH 2.0.3 m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 8K 16K 24K 32K 40K SE +/- 6.88, N = 3 SE +/- 110.64, N = 3 SE +/- 6.43, N = 3 SE +/- 64.35, N = 3 SE +/- 50.85, N = 3 16272.59 16745.12 16867.37 22519.12 35739.82 1. (CXX) g++ options: -O3 -fopenmp -lm -pthread -lmpi_cxx -lmpi
Pennant Test: leblancbig OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: leblancbig m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 3 6 9 12 15 SE +/- 0.019405, N = 3 SE +/- 0.005942, N = 3 SE +/- 0.003475, N = 3 SE +/- 0.016794, N = 3 SE +/- 0.014585, N = 3 10.030260 7.508991 11.297260 6.413928 5.105541 1. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi
NAS Parallel Benchmarks Test / Class: CG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 8K 16K 24K 32K 40K SE +/- 40.34, N = 3 SE +/- 167.20, N = 3 SE +/- 27.23, N = 3 SE +/- 54.87, N = 3 SE +/- 259.41, N = 3 30206.03 23714.82 13438.71 33146.76 38736.50 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
TNN Target: CPU - Model: SqueezeNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 20 40 60 80 100 SE +/- 0.01, N = 3 SE +/- 0.09, N = 3 SE +/- 0.14, N = 3 SE +/- 0.53, N = 3 SE +/- 0.10, N = 3 93.27 78.82 105.07 70.93 70.52 MIN: 93.03 / MAX: 93.7 MIN: 78.48 / MAX: 84.22 MIN: 104.55 / MAX: 105.78 MIN: 70.08 / MAX: 72.98 MIN: 70.09 / MAX: 71.46 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
NAS Parallel Benchmarks Test / Class: EP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.C m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 2K 4K 6K 8K 10K SE +/- 188.76, N = 15 SE +/- 6.49, N = 3 SE +/- 9.83, N = 3 SE +/- 82.22, N = 3 SE +/- 60.61, N = 11 4777.13 2759.76 2218.08 6426.32 8107.02 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
N-Queens Elapsed Time OpenBenchmarking.org Seconds, Fewer Is Better N-Queens 1.0 Elapsed Time m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 0.8757 1.7514 2.6271 3.5028 4.3785 SE +/- 0.028, N = 3 SE +/- 0.007, N = 3 SE +/- 0.001, N = 3 SE +/- 0.041, N = 3 SE +/- 0.052, N = 15 3.892 2.382 3.761 3.144 2.312 1. (CC) gcc options: -static -fopenmp -O3 -march=native
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 m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 1.2201 2.4402 3.6603 4.8804 6.1005 SE +/- 0.01271715, N = 3 SE +/- 0.01191253, N = 3 SE +/- 0.00359720, N = 3 SE +/- 0.02606307, N = 3 SE +/- 0.01051693, N = 3 4.76513163 5.42248488 5.18380547 3.49298970 2.95411030 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
NAS Parallel Benchmarks Test / Class: MG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C m5.24xlarge m6a.24xlarge m6g.metal m6i.24xlarge m6i.32xlarge 30K 60K 90K 120K 150K SE +/- 462.23, N = 3 SE +/- 36.70, N = 3 SE +/- 37.90, N = 3 SE +/- 6.50, N = 3 SE +/- 270.09, N = 3 65732.22 49638.45 25872.77 88248.73 117771.92 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
Phoronix Test Suite v10.8.4