AMD EPYC 9965 Turin Dense vs. AmpereOne ARM 192-Core CPU Benchmarks
Benchmarks by Michael Larabel for a future article review on Phoronix.
HTML result view exported from: https://openbenchmarking.org/result/2410103-NE-AMPEREONE62&sgm=1&scalar=1&ppd_QW1wZXJlT25lIEExOTItMzJY=5555&ppd_RVBZQyA5OTY1=14813&ppt=D&sor&grw.
ASTC Encoder
Preset: Thorough
ASTC Encoder
Preset: Very Thorough
ASTC Encoder
Preset: Exhaustive
Xmrig
Variant: GhostRider - Hash Count: 1M
QuantLib
Configuration: Multi-Threaded
WRF
Input: conus 2.5km
GROMACS
Implementation: MPI CPU - Input: water_GMX50_bare
LAMMPS Molecular Dynamics Simulator
Model: Rhodopsin Protein
LAMMPS Molecular Dynamics Simulator
Model: 20k Atoms
High Performance Conjugate Gradient
X Y Z: 144 144 144 - RT: 60
NAS Parallel Benchmarks
Test / Class: EP.D
NAS Parallel Benchmarks
Test / Class: SP.C
NAS Parallel Benchmarks
Test / Class: IS.D
oneDNN
Harness: Deconvolution Batch shapes_3d - Engine: CPU
ASKAP
Test: tConvolve MPI - Degridding
ASKAP
Test: tConvolve MPI - Gridding
Pennant
Test: leblancbig
Pennant
Test: sedovbig
Algebraic Multi-Grid Benchmark
LULESH
OpenFOAM
Input: drivaerFastback, Small Mesh Size - Execution Time
OpenFOAM
Input: drivaerFastback, Medium Mesh Size - Execution Time
QMCPACK
Input: Li2_STO_ae
miniFE
Problem Size: Small
Xcompact3d Incompact3d
Input: input.i3d 193 Cells Per Direction
Xcompact3d Incompact3d
Input: X3D-benchmarking input.i3d
GPAW
Input: Carbon Nanotube
Coremark
CoreMark Size 666 - Iterations Per Second
Primesieve
Length: 1e13
Stockfish
Chess Benchmark
7-Zip Compression
Test: Compression Rating
7-Zip Compression
Test: Decompression Rating
John The Ripper
Test: Blowfish
John The Ripper
Test: bcrypt
Timed LLVM Compilation
Build System: Ninja
Parallel BZIP2 Compression
FreeBSD-13.0-RELEASE-amd64-memstick.img Compression
m-queens
Time To Solve
GraphicsMagick
Operation: Noise-Gaussian
GraphicsMagick
Operation: Enhanced
GraphicsMagick
Operation: Sharpen
GraphicsMagick
Operation: Swirl
Timed Gem5 Compilation
Time To Compile
Timed Mesa Compilation
Time To Compile
Timed Node.js Compilation
Time To Compile
srsRAN Project
Test: PUSCH Processor Benchmark, Throughput Total
Speedb
Test: Random Read
Helsing
Digit Range: 14 digit
RocksDB
Test: Random Read
RocksDB
Test: Read While Writing
Timed Node.js Compilation
CPU Power Consumption Monitor
Timed Gem5 Compilation
CPU Power Consumption Monitor
Timed LLVM Compilation
CPU Power Consumption Monitor
Timed Mesa Compilation
CPU Power Consumption Monitor
John The Ripper
Test: Blowfish
John The Ripper
CPU Power Consumption Monitor
John The Ripper
Test: bcrypt
RocksDB
Test: Random Read
RocksDB
CPU Power Consumption Monitor
RocksDB
Test: Read While Writing
RocksDB
CPU Power Consumption Monitor
Speedb
Test: Random Read
Speedb
CPU Power Consumption Monitor
Coremark
CoreMark Size 666 - Iterations Per Second
Coremark
CPU Power Consumption Monitor
Algebraic Multi-Grid Benchmark
Algebraic Multi-Grid Benchmark
CPU Power Consumption Monitor
WRF
CPU Power Consumption Monitor
LULESH
LULESH
CPU Power Consumption Monitor
LAMMPS Molecular Dynamics Simulator
Model: Rhodopsin Protein
LAMMPS Molecular Dynamics Simulator
CPU Power Consumption Monitor
LAMMPS Molecular Dynamics Simulator
Model: 20k Atoms
LAMMPS Molecular Dynamics Simulator
CPU Power Consumption Monitor
m-queens
CPU Power Consumption Monitor
miniFE
Problem Size: Small
miniFE
CPU Power Consumption Monitor
ASKAP
Test: tConvolve MPI - Gridding
ASKAP
CPU Power Consumption Monitor
GROMACS
Implementation: MPI CPU - Input: water_GMX50_bare
GROMACS
CPU Power Consumption Monitor
QuantLib
Configuration: Multi-Threaded
QuantLib
CPU Power Consumption Monitor
QMCPACK
CPU Power Consumption Monitor
GPAW
CPU Power Consumption Monitor
High Performance Conjugate Gradient
X Y Z: 144 144 144 - RT: 60
High Performance Conjugate Gradient
CPU Power Consumption Monitor
Pennant
CPU Power Consumption Monitor
Pennant
CPU Power Consumption Monitor
NAS Parallel Benchmarks
Test / Class: EP.D
NAS Parallel Benchmarks
CPU Power Consumption Monitor
NAS Parallel Benchmarks
Test / Class: SP.C
NAS Parallel Benchmarks
CPU Power Consumption Monitor
NAS Parallel Benchmarks
Test / Class: IS.D
NAS Parallel Benchmarks
CPU Power Consumption Monitor
Xcompact3d Incompact3d
CPU Power Consumption Monitor
Xcompact3d Incompact3d
CPU Power Consumption Monitor
OpenFOAM
CPU Power Consumption Monitor
OpenFOAM
CPU Power Consumption Monitor
7-Zip Compression
Test: Decompression Rating
7-Zip Compression
CPU Power Consumption Monitor
Parallel BZIP2 Compression
CPU Power Consumption Monitor
ASTC Encoder
Preset: Thorough
ASTC Encoder
CPU Power Consumption Monitor
ASTC Encoder
Preset: Very Thorough
ASTC Encoder
CPU Power Consumption Monitor
ASTC Encoder
Preset: Exhaustive
ASTC Encoder
CPU Power Consumption Monitor
GraphicsMagick
Operation: Noise-Gaussian
GraphicsMagick
CPU Power Consumption Monitor
GraphicsMagick
Operation: Enhanced
GraphicsMagick
CPU Power Consumption Monitor
GraphicsMagick
Operation: Sharpen
GraphicsMagick
CPU Power Consumption Monitor
GraphicsMagick
Operation: Swirl
GraphicsMagick
CPU Power Consumption Monitor
srsRAN Project
Test: PUSCH Processor Benchmark, Throughput Total
srsRAN Project
CPU Power Consumption Monitor
oneDNN
CPU Power Consumption Monitor
Xmrig
Variant: GhostRider - Hash Count: 1M
Xmrig
CPU Power Consumption Monitor
Helsing
CPU Power Consumption Monitor
Stockfish
Chess Benchmark
Stockfish
CPU Power Consumption Monitor
Primesieve
CPU Power Consumption Monitor
CPU Power Consumption Monitor
Phoronix Test Suite System Monitoring
Geometric Mean Of All Test Results
Result Composite - AMD EPYC 9965 Turin Dense vs. AmpereOne ARM 192-Core CPU Benchmarks
ASTC Encoder
Performance / Cost - Preset: Thorough
ASTC Encoder
Performance / Cost - Preset: Very Thorough
ASTC Encoder
Performance / Cost - Preset: Exhaustive
Xmrig
Performance / Cost - Variant: GhostRider - Hash Count: 1M
QuantLib
Performance / Cost - Configuration: Multi-Threaded
WRF
Performance / Cost - Input: conus 2.5km
GROMACS
Performance / Cost - Implementation: MPI CPU - Input: water_GMX50_bare
LAMMPS Molecular Dynamics Simulator
Performance / Cost - Model: Rhodopsin Protein
LAMMPS Molecular Dynamics Simulator
Performance / Cost - Model: 20k Atoms
High Performance Conjugate Gradient
Performance / Cost - X Y Z: 144 144 144 - RT: 60
NAS Parallel Benchmarks
Performance / Cost - Test / Class: EP.D
NAS Parallel Benchmarks
Performance / Cost - Test / Class: SP.C
NAS Parallel Benchmarks
Performance / Cost - Test / Class: IS.D
oneDNN
Performance / Cost - Harness: Deconvolution Batch shapes_3d - Engine: CPU
ASKAP
Performance / Cost - Test: tConvolve MPI - Degridding
ASKAP
Performance / Cost - Test: tConvolve MPI - Gridding
Pennant
Performance / Cost - Test: leblancbig
Pennant
Performance / Cost - Test: sedovbig
Algebraic Multi-Grid Benchmark
Performance / Cost
LULESH
Performance / Cost
OpenFOAM
Performance / Cost - Input: drivaerFastback, Small Mesh Size - Execution Time
OpenFOAM
Performance / Cost - Input: drivaerFastback, Medium Mesh Size - Execution Time
QMCPACK
Performance / Cost - Input: Li2_STO_ae
miniFE
Performance / Cost - Problem Size: Small
Xcompact3d Incompact3d
Performance / Cost - Input: input.i3d 193 Cells Per Direction
Xcompact3d Incompact3d
Performance / Cost - Input: X3D-benchmarking input.i3d
GPAW
Performance / Cost - Input: Carbon Nanotube
Coremark
Performance / Cost - CoreMark Size 666 - Iterations Per Second
Primesieve
Performance / Cost - Length: 1e13
Stockfish
Performance / Cost - Chess Benchmark
7-Zip Compression
Performance / Cost - Test: Compression Rating
7-Zip Compression
Performance / Cost - Test: Decompression Rating
John The Ripper
Performance / Cost - Test: Blowfish
John The Ripper
Performance / Cost - Test: bcrypt
Timed LLVM Compilation
Performance / Cost - Build System: Ninja
Parallel BZIP2 Compression
Performance / Cost - FreeBSD-13.0-RELEASE-amd64-memstick.img Compression
m-queens
Performance / Cost - Time To Solve
GraphicsMagick
Performance / Cost - Operation: Noise-Gaussian
GraphicsMagick
Performance / Cost - Operation: Enhanced
GraphicsMagick
Performance / Cost - Operation: Sharpen
GraphicsMagick
Performance / Cost - Operation: Swirl
Timed Gem5 Compilation
Performance / Cost - Time To Compile
Timed Mesa Compilation
Performance / Cost - Time To Compile
Timed Node.js Compilation
Performance / Cost - Time To Compile
srsRAN Project
Performance / Cost - Test: PUSCH Processor Benchmark, Throughput Total
Speedb
Performance / Cost - Test: Random Read
Helsing
Performance / Cost - Digit Range: 14 digit
RocksDB
Performance / Cost - Test: Random Read
RocksDB
Performance / Cost - Test: Read While Writing
Phoronix Test Suite v10.8.5