AMD Ryzen 9 9950X DDR5 Memory Performance
AMD Ryzen 9 9950X DDR5 memory module benchmarks by Michael Larabel for a future article.
HTML result view exported from: https://openbenchmarking.org/result/2408225-NE-RYZEN999510&sro&grs.
LeelaChessZero
Backend: BLAS
LeelaChessZero
Backend: Eigen
NAS Parallel Benchmarks
Test / Class: SP.C
Xcompact3d Incompact3d
Input: input.i3d 193 Cells Per Direction
OpenFOAM
Input: drivaerFastback, Medium Mesh Size - Execution Time
NAS Parallel Benchmarks
Test / Class: MG.C
NAS Parallel Benchmarks
Test / Class: FT.C
libxsmm
M N K: 32
libxsmm
M N K: 64
NAS Parallel Benchmarks
Test / Class: SP.B
NAS Parallel Benchmarks
Test / Class: BT.C
NAS Parallel Benchmarks
Test / Class: IS.D
Xcompact3d Incompact3d
Input: input.i3d 129 Cells Per Direction
Llama.cpp
Model: Meta-Llama-3-8B-Instruct-Q8_0.gguf
High Performance Conjugate Gradient
X Y Z: 104 104 104 - RT: 60
libxsmm
M N K: 128
OpenFOAM
Input: drivaerFastback, Small Mesh Size - Execution Time
LULESH
RAMspeed SMP
Type: Copy - Benchmark: Integer
RAMspeed SMP
Type: Triad - Benchmark: Integer
SPECFEM3D
Model: Homogeneous Halfspace
MBW
Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB
MBW
Test: Memory Copy, Fixed Block Size - Array Size: 8192 MiB
NAS Parallel Benchmarks
Test / Class: LU.C
NAS Parallel Benchmarks
Test / Class: CG.C
Y-Cruncher
Pi Digits To Calculate: 1B
RAMspeed SMP
Type: Scale - Benchmark: Integer
RAMspeed SMP
Type: Add - Benchmark: Integer
MBW
Test: Memory Copy - Array Size: 8192 MiB
RAMspeed SMP
Type: Average - Benchmark: Integer
PyTorch
Device: CPU - Batch Size: 1 - Model: ResNet-50
NAMD
Input: ATPase with 327,506 Atoms
TensorFlow
Device: CPU - Batch Size: 64 - Model: ResNet-50
simdjson
Throughput Test: TopTweet
Build2
Time To Compile
OpenFOAM
Input: motorBike - Execution Time
SPECFEM3D
Model: Layered Halfspace
GROMACS
Implementation: MPI CPU - Input: water_GMX50_bare
XNNPACK
Model: FP32MobileNetV3Large
Y-Cruncher
Pi Digits To Calculate: 500M
PyTorch
Device: CPU - Batch Size: 256 - Model: ResNet-50
SPECFEM3D
Model: Water-layered Halfspace
Stockfish
Chess Benchmark
NAMD
Input: STMV with 1,066,628 Atoms
OpenFOAM
Input: drivaerFastback, Medium Mesh Size - Mesh Time
GROMACS
Input: water_GMX50_bare
Embree
Binary: Pathtracer ISPC - Model: Asian Dragon
Memcached
Set To Get Ratio: 1:100
XNNPACK
Model: QU8MobileNetV3Small
Embree
Binary: Pathtracer ISPC - Model: Crown
Memcached
Set To Get Ratio: 1:10
LuxCoreRender
Scene: Rainbow Colors and Prism - Acceleration: CPU
7-Zip Compression
Test: Compression Rating
OpenRadioss
Model: Cell Phone Drop Test
SPECFEM3D
Model: Tomographic Model
OpenFOAM
Input: motorBike - Mesh Time
XNNPACK
Model: FP16MobileNetV3Small
XNNPACK
Model: QU8MobileNetV3Large
Java JMH
Throughput
XNNPACK
Model: FP16MobileNetV2
XNNPACK
Model: FP16MobileNetV3Large
OpenRadioss
Model: INIVOL and Fluid Structure Interaction Drop Container
x265
Video Input: Bosphorus 4K
Blender
Blend File: Junkshop - Compute: CPU-Only
XNNPACK
Model: QU8MobileNetV2
TensorFlow
Device: CPU - Batch Size: 1 - Model: ResNet-50
MBW
Test: Memory Copy - Array Size: 4096 MiB
NAS Parallel Benchmarks
Test / Class: EP.D
XNNPACK
Model: FP32MobileNetV3Small
SPECFEM3D
Model: Mount St. Helens
Blender
Blend File: BMW27 - Compute: CPU-Only
simdjson
Throughput Test: Kostya
OpenFOAM
Input: drivaerFastback, Small Mesh Size - Mesh Time
x265
Video Input: Bosphorus 1080p
BRL-CAD
VGR Performance Metric
Xmrig
Variant: GhostRider - Hash Count: 1M
Blender
Blend File: Barbershop - Compute: CPU-Only
Numpy Benchmark
Timed LLVM Compilation
Build System: Ninja
LuxCoreRender
Scene: LuxCore Benchmark - Acceleration: CPU
Quicksilver
Input: CORAL2 P1
LuxCoreRender
Scene: Orange Juice - Acceleration: CPU
OpenRadioss
Model: Rubber O-Ring Seal Installation
LuxCoreRender
Scene: Danish Mood - Acceleration: CPU
miniBUDE
Implementation: OpenMP - Input Deck: BM2
miniBUDE
Implementation: OpenMP - Input Deck: BM2
POV-Ray
Trace Time
NAS Parallel Benchmarks
Test / Class: EP.C
XNNPACK
Model: FP32MobileNetV2
LuxCoreRender
Scene: DLSC - Acceleration: CPU
Etcpak
Benchmark: Multi-Threaded - Configuration: ETC2
miniBUDE
Implementation: OpenMP - Input Deck: BM1
miniBUDE
Implementation: OpenMP - Input Deck: BM1
Stress-NG
Test: Memory Copying
OpenRadioss
Model: Bumper Beam
Timed Linux Kernel Compilation
Build: defconfig
Timed Node.js Compilation
Time To Compile
simdjson
Throughput Test: LargeRandom
Timed Gem5 Compilation
Time To Compile
7-Zip Compression
Test: Decompression Rating
Timed Linux Kernel Compilation
Build: allmodconfig
Llamafile
Test: Meta-Llama-3-8B-Instruct.F16 - Acceleration: CPU
OpenRadioss
Model: Bird Strike on Windshield
OpenRadioss
Model: Chrysler Neon 1M
Phoronix Test Suite v10.8.5