Graviton4 vs. Graviton3 vs. Graviton2 + AMD EPYC, Intel Xeon AWS

Benchmarks by Michael Larabel for a future article on Phoronix.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2407111-NE-AWS4GRAVI72
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts

Limit displaying results to tests within:

C++ Boost Tests 3 Tests
Timed Code Compilation 4 Tests
C/C++ Compiler Tests 7 Tests
CPU Massive 6 Tests
Creator Workloads 2 Tests
Cryptography 2 Tests
Database Test Suite 3 Tests
HPC - High Performance Computing 4 Tests
Common Kernel Benchmarks 2 Tests
Molecular Dynamics 4 Tests
MPI Benchmarks 3 Tests
Multi-Core 10 Tests
OpenMPI Tests 4 Tests
Programmer / Developer System Benchmarks 4 Tests
Python Tests 4 Tests
Scientific Computing 4 Tests
Software Defined Radio 2 Tests
Server 3 Tests
Server CPU Tests 5 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
EPYC 9R14 r7a.16xlarge
July 10
  5 Hours, 15 Minutes
Graviton2 r6g.16xlarge
July 11
  9 Hours, 4 Minutes
Graviton3 r7g.16xlarge
July 10
  9 Hours, 45 Minutes
Graviton4 r8g.16xlarge
July 10
  9 Hours, 33 Minutes
Xeon 8488C r7i.16xlarge
July 11
  6 Hours, 34 Minutes
Invert Hiding All Results Option
  8 Hours, 2 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


Graviton4 vs. Graviton3 vs. Graviton2 + AMD EPYC, Intel Xeon AWSProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelCompilerFile-SystemScreen ResolutionSystem LayerEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlargeAMD EPYC 9R14 (64 Cores)Amazon EC2 r7a.16xlarge (1.0 BIOS)Intel 440FX 82441FX PMC1 x 512GB DDR5-4800MT/s429GB Amazon Elastic Block StoresimpledrmdrmfbAmazon ElasticUbuntu 24.046.8.0-1009-aws (x86_64)GCC 13.2.0ext4800x600amazonARMv8 Neoverse-N1 (64 Cores)Amazon EC2 r6g.16xlarge (1.0 BIOS)Amazon Device 0200512GB6.8.0-1009-aws (aarch64)ARMv8 Neoverse-V1 (64 Cores)Amazon EC2 r7g.16xlarge (1.0 BIOS)496GBARMv8 Neoverse-V2 (64 Cores)Amazon EC2 r8g.16xlarge (1.0 BIOS)Intel Xeon Platinum 8488C (32 Cores / 64 Threads)Amazon EC2 r7i.16xlarge (1.0 BIOS)Intel 440FX 82441FX PMC1 x 512GB DDR5-4800MT/ssimpledrmdrmfb6.8.0-1009-aws (x86_64)800x600OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- EPYC 9R14 r7a.16xlarge: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Graviton2 r6g.16xlarge: --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 - Graviton3 r7g.16xlarge: --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 - Graviton4 r8g.16xlarge: --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 - Xeon 8488C r7i.16xlarge: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- EPYC 9R14 r7a.16xlarge: CPU Microcode: 0xa101148- Xeon 8488C r7i.16xlarge: CPU Microcode: 0x2b0005d1Python Details- Python 3.12.3Security Details- EPYC 9R14 r7a.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: Vulnerable: Safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: disabled; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - Graviton2 r6g.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 - 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: 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 - Xeon 8488C r7i.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 usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: SW sequence; BHI: BHI_DIS_S + srbds: Not affected + tsx_async_abort: Not affected

EPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlargeResult OverviewPhoronix Test Suite100%171%242%312%383%John The RippersrsRAN ProjectXmrigXcompact3d Incompact3dBlenderGROMACSOpenSSLminiFETimed Node.js CompilationC-RayLiquid-DSPOpenFOAMRocksDBTimed Godot Game Engine CompilationStockfishClickHouseTimed LLVM CompilationTimed Gem5 Compilation7-Zip CompressionPostgreSQL

Graviton4 vs. Graviton3 vs. Graviton2 + AMD EPYC, Intel Xeon AWSjohn-the-ripper: WPA PSKjohn-the-ripper: MD5liquid-dsp: 64 - 256 - 512openssl: ChaCha20-Poly1305openssl: ChaCha20john-the-ripper: HMAC-SHA512rocksdb: Update Randblender: Pabellon Barcelona - CPU-Onlyblender: Fishy Cat - CPU-Onlysrsran: PDSCH Processor Benchmark, Throughput Totalsrsran: PUSCH Processor Benchmark, Throughput Totalxmrig: GhostRider - 1Mopenssl: AES-256-GCMincompact3d: input.i3d 193 Cells Per Directionopenssl: AES-128-GCMgromacs: MPI CPU - water_GMX50_bareblender: Classroom - CPU-Onlyblender: Barbershop - CPU-Onlyminife: Smallblender: BMW27 - CPU-Onlybuild-nodejs: Time To Compilec-ray: 5K - 16c-ray: 4K - 16openfoam: drivaerFastback, Medium Mesh Size - Execution Timeopenfoam: drivaerFastback, Small Mesh Size - Execution Timepgbench: 100 - 1000 - Read Onlypgbench: 100 - 1000 - Read Only - Average Latencyliquid-dsp: 64 - 256 - 57build-godot: Time To Compileopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timerocksdb: Rand Readopenfoam: drivaerFastback, Small Mesh Size - Mesh Timejohn-the-ripper: bcryptjohn-the-ripper: Blowfishclickhouse: 100M Rows Hits Dataset, First Run / Cold Cacherocksdb: Read Rand Write Randbuild-llvm: Ninjaclickhouse: 100M Rows Hits Dataset, Second Runclickhouse: 100M Rows Hits Dataset, Third Runcompress-7zip: Decompression Ratingbuild-gem5: Time To Compileliquid-dsp: 64 - 256 - 32compress-7zip: Compression Ratingrocksdb: Read While Writingpgbench: 100 - 1000 - Read Writepgbench: 100 - 1000 - Read Write - Average Latencystockfish: Chess BenchmarkEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge371747864700075970000021749109673730861139039325638400074289884.5239.1628256.82400.26899.823648294821310.91576612561017954078.51957.11284.6341274.230.19250.42988.89149.691374.6966443.16970920927100.4782529533333127.448123.9971732470366924.7882369140991221488.883756585198.500508.87514.29288408213.288226153333332093363041924458224.32385180777498541332667150236667464792765336704593394761258333305604321.20147.778104.1705.92067.512651093551725.52030051569572631872.709169.86832.2722674.083.01678.013113.14663.698872.07907102.648359167861.0911173933333274.041194.7898616581693937.2915144521645204252.632912791344.432269.15274.07232070334.808185120000022984459558454483223.17143501453526311451333166313333694307045409414750207786689000817470247.60115.4712612.61053.82108.524909550059713.95584842875915247634.163129.48644.9836361.762.77571.01168.69938.668552.565768.29461510874880.9201654733333195.497121.2786124316677124.7844655070950679348.414254497257.853375.29382.14284576251.402257380000029673168723894541220.27355548662574441579667185000000751905487071018987203231080663331274616202.2695.0114402.51332.55958.72661251505277.875020662997971021374.831105.39499.6365410.450.64365.02450.24728.323344.167641.41307519475250.5141929666667147.87091.97452734653258618.3847685703857032449.445584014182.063479.94495.03331505186.768325873333338346085225974420226.244814408012385615780000619730000134022346887183018463593182244000779301115.1453.7416787.81610.33659.341937137145320.89203015031745257475.73378.96414.2429012.739.74354.093135.59876.254653.5816863.45039519956180.5012093933333164.602135.9669517062480726.5992415879658815377.023243486263.369404.64404.38177209244.881195220000024571256851674437225.37259224620OpenBenchmarking.org

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: WPA PSKEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge80K160K240K320K400KSE +/- 164.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 10.97, N = 3SE +/- 741.52, N = 3371747498545263157444238561-m64-m641. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: MD5EPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge2M4M6M8M10MSE +/- 7571.88, N = 3SE +/- 666.67, N = 3SE +/- 333.33, N = 3SE +/- 1201.85, N = 3SE +/- 6245.00, N = 386470001332667145133315796675780000-m64-m641. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

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.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 512EPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge160M320M480M640M800MSE +/- 1140935.29, N = 3SE +/- 1503344.42, N = 3SE +/- 3333.33, N = 3SE +/- 0.00, N = 3SE +/- 1206523.93, N = 37597000001502366671663133331850000006197300001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenSSL

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSLAlgorithm: ChaCha20-Poly1305EPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge50000M100000M150000M200000M250000MSE +/- 197460025.45, N = 3SE +/- 36473958.31, N = 3SE +/- 6321669.59, N = 3SE +/- 558939.35, N = 3SE +/- 5879540.90, N = 32174910967374647927653369430704540751905487071340223468871. EPYC 9R14 r7a.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8 2. Graviton2 r6g.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)3. Graviton3 r7g.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)4. Graviton4 r8g.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)5. Xeon 8488C r7i.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSLAlgorithm: ChaCha20EPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge70000M140000M210000M280000M350000MSE +/- 350599170.76, N = 3SE +/- 10580063.28, N = 3SE +/- 4627810.23, N = 3SE +/- 66408.09, N = 3SE +/- 95540656.21, N = 330861139039367045933947941475020771018987203231830184635931. EPYC 9R14 r7a.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8 2. Graviton2 r6g.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)3. Graviton3 r7g.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)4. Graviton4 r8g.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)5. Xeon 8488C r7i.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: HMAC-SHA512EPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge50M100M150M200M250MSE +/- 730794.32, N = 3SE +/- 126483.64, N = 3SE +/- 76622.45, N = 3SE +/- 640028.21, N = 3SE +/- 396706.86, N = 32563840006125833386689000108066333182244000-m64-m641. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

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.orgOp/s, More Is BetterRocksDB 9.0Test: Update RandomEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge300K600K900K1200K1500KSE +/- 4861.01, N = 3SE +/- 1081.97, N = 3SE +/- 7555.40, N = 15SE +/- 11457.12, N = 3SE +/- 4510.79, N = 374289830560481747012746167793011. (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.orgSeconds, Fewer Is BetterBlender 4.0.2Blend File: Pabellon Barcelona - Compute: CPU-OnlyEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge70140210280350SE +/- 0.11, N = 3SE +/- 0.45, N = 3SE +/- 0.13, N = 3SE +/- 0.34, N = 3SE +/- 0.65, N = 384.52321.20247.60202.26115.14

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0.2Blend File: Fishy Cat - Compute: CPU-OnlyEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge306090120150SE +/- 0.06, N = 3SE +/- 0.44, N = 3SE +/- 0.23, N = 3SE +/- 0.26, N = 3SE +/- 0.35, N = 339.16147.77115.4795.0153.74

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.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PDSCH Processor Benchmark, Throughput TotalEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge6K12K18K24K30KSE +/- 148.22, N = 3SE +/- 19.11, N = 3SE +/- 20.13, N = 3SE +/- 34.15, N = 3SE +/- 135.70, N = 1528256.88104.112612.614402.516787.8-march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq-march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq1. (CXX) g++ options: -O3 -fno-trapping-math -fno-math-errno -ldl

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PUSCH Processor Benchmark, Throughput TotalEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge5001000150020002500SE +/- 0.07, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.13, N = 32400.2705.91053.81332.51610.3-march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 1696.6 / MAX: 2400.3MIN: 415.8MIN: 599.4 / MAX: 1053.9MIN: 784 / MAX: 1332.6-march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 1018.4 / MAX: 1610.61. (CXX) g++ options: -O3 -fno-trapping-math -fno-math-errno -ldl

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.orgH/s, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge15003000450060007500SE +/- 2.15, N = 3SE +/- 1.60, N = 3SE +/- 4.85, N = 3SE +/- 47.30, N = 12SE +/- 2.70, N = 26899.82067.52108.55958.73659.3-maes-maes1. (CXX) g++ options: -fexceptions -fno-rtti -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenSSL

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSLAlgorithm: AES-256-GCMEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge90000M180000M270000M360000M450000MSE +/- 338102973.44, N = 3SE +/- 14487293.04, N = 3SE +/- 4988409.71, N = 3SE +/- 6417811.59, N = 3SE +/- 1133918988.52, N = 32364829482131265109355172490955005972661251505274193713714531. EPYC 9R14 r7a.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8 2. Graviton2 r6g.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)3. Graviton3 r7g.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)4. Graviton4 r8g.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)5. Xeon 8488C r7i.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8

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.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per DirectionEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge612182430SE +/- 0.01638008, N = 3SE +/- 0.02637428, N = 3SE +/- 0.01649632, N = 3SE +/- 0.01884341, N = 3SE +/- 0.11253050, N = 310.9157661025.5203005013.955848407.8750206620.892030101. (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

OpenSSL

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSLAlgorithm: AES-128-GCMEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge110000M220000M330000M440000M550000MSE +/- 358257182.84, N = 3SE +/- 11278788.96, N = 3SE +/- 3618954.21, N = 3SE +/- 7802917.99, N = 3SE +/- 252375791.78, N = 32561017954071569572631872875915247632997971021375031745257471. EPYC 9R14 r7a.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8 2. Graviton2 r6g.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)3. Graviton3 r7g.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)4. Graviton4 r8g.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024)5. Xeon 8488C r7i.16xlarge: OpenSSL 3.0.13 30 Jan 2024 (Library: OpenSSL 3.0.13 30 Jan 2024) - Additional Parameters: -engine qatengine -async_jobs 8

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.orgNs Per Day, More Is BetterGROMACS 2024Implementation: MPI CPU - Input: water_GMX50_bareEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge246810SE +/- 0.041, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.004, N = 3SE +/- 0.012, N = 38.5192.7094.1634.8315.7331. (CXX) g++ options: -O3 -lm

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.orgSeconds, Fewer Is BetterBlender 4.0.2Blend File: Classroom - Compute: CPU-OnlyEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge4080120160200SE +/- 0.14, N = 3SE +/- 0.42, N = 3SE +/- 0.06, N = 3SE +/- 0.11, N = 3SE +/- 0.20, N = 357.11169.86129.48105.3978.96

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0.2Blend File: Barbershop - Compute: CPU-OnlyEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge2004006008001000SE +/- 0.03, N = 3SE +/- 2.45, N = 3SE +/- 0.24, N = 3SE +/- 0.76, N = 3SE +/- 1.03, N = 3284.63832.27644.98499.63414.24

miniFE

MiniFE Finite Element is an application for unstructured implicit finite element codes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgCG Mflops, More Is BetterminiFE 2.2Problem Size: SmallEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge14K28K42K56K70KSE +/- 136.71, N = 3SE +/- 53.93, N = 3SE +/- 21.14, N = 3SE +/- 28.12, N = 3SE +/- 80.98, N = 341274.222674.036361.765410.429012.71. (CXX) g++ options: -O3 -fopenmp -lmpi_cxx -lmpi

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.orgSeconds, Fewer Is BetterBlender 4.0.2Blend File: BMW27 - Compute: CPU-OnlyEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge20406080100SE +/- 0.08, N = 3SE +/- 0.30, N = 3SE +/- 0.02, N = 3SE +/- 0.10, N = 3SE +/- 0.15, N = 330.1983.0162.7750.6439.74

Timed Node.js Compilation

This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 21.7.2Time To CompileEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge150300450600750SE +/- 0.19, N = 3SE +/- 0.88, N = 3SE +/- 0.62, N = 3SE +/- 0.19, N = 3SE +/- 0.26, N = 3250.43678.01571.01365.02354.09

C-Ray

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 2.0Resolution: 5K - Rays Per Pixel: 16EPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge306090120150SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 388.89113.1568.7050.25135.601. (CC) gcc options: -lpthread -lm

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 2.0Resolution: 4K - Rays Per Pixel: 16EPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge20406080100SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 349.6963.7038.6728.3276.251. (CC) gcc options: -lpthread -lm

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.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Execution TimeEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge2004006008001000374.70872.08552.57344.17653.58-m64-mcpu=native-mcpu=native-mcpu=native-m641. (CXX) g++ options: -std=c++14 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Execution TimeEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge2040608010043.17102.6568.2941.4163.45-m64-mcpu=native-mcpu=native-mcpu=native-m641. (CXX) g++ options: -std=c++14 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -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.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read OnlyEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge400K800K1200K1600K2000KSE +/- 7113.73, N = 3SE +/- 5859.87, N = 3SE +/- 5453.81, N = 3SE +/- 6233.51, N = 3SE +/- 13816.25, N = 320927109167861087488194752519956181. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average LatencyEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge0.24550.4910.73650.9821.2275SE +/- 0.002, N = 3SE +/- 0.007, N = 3SE +/- 0.005, N = 3SE +/- 0.002, N = 3SE +/- 0.004, N = 30.4781.0910.9200.5140.5011. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -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.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 57EPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge500M1000M1500M2000M2500MSE +/- 6691619.97, N = 3SE +/- 88191.71, N = 3SE +/- 133333.33, N = 3SE +/- 33333.33, N = 3SE +/- 3955727.21, N = 3252953333311739333331654733333192966666720939333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Timed Godot Game Engine Compilation

This test times how long it takes to compile the Godot Game Engine. Godot is a popular, open-source, cross-platform 2D/3D game engine and is built using the SCons build system and targeting the X11 platform. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 4.0Time To CompileEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge60120180240300SE +/- 0.19, N = 3SE +/- 0.76, N = 3SE +/- 0.85, N = 3SE +/- 0.35, N = 3SE +/- 0.48, N = 3127.45274.04195.50147.87164.60

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.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Mesh TimeEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge4080120160200124.00194.79121.2891.97135.97-m64-mcpu=native-mcpu=native-mcpu=native-m641. (CXX) g++ options: -std=c++14 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -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.orgOp/s, More Is BetterRocksDB 9.0Test: Random ReadEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge70M140M210M280M350MSE +/- 827628.35, N = 3SE +/- 2004027.04, N = 3SE +/- 36358.69, N = 3SE +/- 1371022.17, N = 3SE +/- 44880.70, N = 33247036691658169392431667713465325861706248071. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

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.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Mesh TimeEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge91827364524.7937.2924.7818.3826.60-m64-mcpu=native-mcpu=native-mcpu=native-m641. (CXX) g++ options: -std=c++14 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: bcryptEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge20K40K60K80K100KSE +/- 75.52, N = 3SE +/- 4.70, N = 3SE +/- 8.67, N = 3SE +/- 2.33, N = 3SE +/- 32.00, N = 39140945216507095703858796-m64-m641. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge20K40K60K80K100KSE +/- 117.95, N = 3SE +/- 30.67, N = 3SE +/- 15.39, N = 3SE +/- 9.29, N = 3SE +/- 12.67, N = 39122145204506795703258815-m64-m641. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

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.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, First Run / Cold CacheEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge110220330440550SE +/- 6.79, N = 3SE +/- 3.33, N = 3SE +/- 5.68, N = 9SE +/- 4.96, N = 9SE +/- 3.99, N = 4488.88252.63348.41449.44377.02MIN: 40.21 / MAX: 5000MIN: 20.56 / MAX: 3157.89MIN: 33.19 / MAX: 5000MIN: 42.7 / MAX: 6666.67MIN: 26.25 / MAX: 5000

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.orgOp/s, More Is BetterRocksDB 9.0Test: Read Random Write RandomEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge1.2M2.4M3.6M4.8M6MSE +/- 17358.30, N = 3SE +/- 47713.48, N = 12SE +/- 1357.98, N = 3SE +/- 11170.68, N = 3SE +/- 7177.88, N = 3375658529127914254497558401432434861. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

Timed LLVM Compilation

This test times how long it takes to compile/build the LLVM compiler stack. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: NinjaEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge70140210280350SE +/- 0.91, N = 3SE +/- 0.93, N = 3SE +/- 0.38, N = 3SE +/- 0.20, N = 3SE +/- 0.60, N = 3198.50344.43257.85182.06263.37

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.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second RunEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge110220330440550SE +/- 2.24, N = 3SE +/- 5.29, N = 3SE +/- 3.03, N = 9SE +/- 5.05, N = 9SE +/- 1.87, N = 4508.87269.15375.29479.94404.64MIN: 40.57 / MAX: 6000MIN: 20.53 / MAX: 4000MIN: 33.15 / MAX: 5000MIN: 43.1 / MAX: 6000MIN: 26.56 / MAX: 5000

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third RunEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge110220330440550SE +/- 9.86, N = 3SE +/- 6.12, N = 3SE +/- 2.76, N = 9SE +/- 6.71, N = 9SE +/- 3.42, N = 4514.29274.07382.14495.03404.38MIN: 40.51 / MAX: 6000MIN: 20.67 / MAX: 3750MIN: 33.22 / MAX: 4615.38MIN: 43.07 / MAX: 6666.67MIN: 26.32 / MAX: 5454.55

7-Zip Compression

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 24.05Test: Decompression RatingEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge70K140K210K280K350KSE +/- 148.35, N = 3SE +/- 14.19, N = 3SE +/- 70.02, N = 3SE +/- 107.45, N = 3SE +/- 78.29, N = 32884082320702845763315051772091. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Timed Gem5 Compilation

This test times how long it takes to compile Gem5. Gem5 is a simulator for computer system architecture research. Gem5 is widely used for computer architecture research within the industry, academia, and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 23.0.1Time To CompileEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge70140210280350SE +/- 2.25, N = 3SE +/- 4.90, N = 9SE +/- 2.33, N = 3SE +/- 1.43, N = 12SE +/- 1.80, N = 3213.29334.81251.40186.77244.88

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.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 32EPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge700M1400M2100M2800M3500MSE +/- 3199131.83, N = 3SE +/- 300000.00, N = 3SE +/- 404145.19, N = 3SE +/- 533333.33, N = 3SE +/- 808290.38, N = 3226153333318512000002573800000325873333319522000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

7-Zip Compression

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 24.05Test: Compression RatingEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge80K160K240K320K400KSE +/- 1508.30, N = 3SE +/- 252.67, N = 3SE +/- 546.41, N = 3SE +/- 397.84, N = 3SE +/- 69.57, N = 33209332298442967313834602457121. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

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.orgOp/s, More Is BetterRocksDB 9.0Test: Read While WritingEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge2M4M6M8M10MSE +/- 43017.34, N = 13SE +/- 15757.89, N = 3SE +/- 6592.32, N = 3SE +/- 26974.32, N = 3SE +/- 80361.43, N = 3630419259558456872389852259756851671. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

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.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read WriteEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge10002000300040005000SE +/- 34.82, N = 3SE +/- 33.26, N = 11SE +/- 45.23, N = 3SE +/- 14.53, N = 3SE +/- 13.89, N = 3445844834541442044371. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average LatencyEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge50100150200250SE +/- 1.74, N = 3SE +/- 1.59, N = 11SE +/- 2.18, N = 3SE +/- 0.74, N = 3SE +/- 0.70, N = 3224.32223.17220.27226.24225.371. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

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.orgNodes Per Second, More Is BetterStockfish 16.1Chess BenchmarkEPYC 9R14 r7a.16xlargeGraviton2 r6g.16xlargeGraviton3 r7g.16xlargeGraviton4 r8g.16xlargeXeon 8488C r7i.16xlarge20M40M60M80M100MSE +/- 927253.56, N = 12SE +/- 1062798.48, N = 12SE +/- 1152869.30, N = 12SE +/- 2235406.92, N = 15SE +/- 1357414.60, N = 158518077743501453555486628144080159224620-m64 -msse -msse3 -mpopcnt -mavx2 -mbmi -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2-m64 -msse -msse3 -mpopcnt -mavx2 -mbmi -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi21. (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