GPTshop.ai NVIDIA GH200 Linux Benchmarks
Benchmarks by Michael Larabel for a future article.
HTML result view exported from: https://openbenchmarking.org/result/2402184-NE-GH200THRE73&grs.
OpenVINO
Model: Face Detection FP16-INT8 - Device: CPU
John The Ripper
Test: WPA PSK
SVT-AV1
Encoder Mode: Preset 8 - Input: Bosphorus 4K
SVT-AV1
Encoder Mode: Preset 4 - Input: Bosphorus 4K
John The Ripper
Test: MD5
OpenVINO
Model: Face Detection FP16 - Device: CPU
OpenVINO
Model: Face Detection Retail FP16-INT8 - Device: CPU
OpenVINO
Model: Face Detection Retail FP16 - Device: CPU
OpenVINO
Model: Road Segmentation ADAS FP16-INT8 - Device: CPU
Stress-NG
Test: CPU Stress
OpenVINO
Model: Face Detection Retail FP16-INT8 - Device: CPU
SVT-AV1
Encoder Mode: Preset 12 - Input: Bosphorus 4K
Liquid-DSP
Threads: 240 - Buffer Length: 256 - Filter Length: 512
OpenVINO
Model: Face Detection FP16 - Device: CPU
SVT-AV1
Encoder Mode: Preset 13 - Input: Bosphorus 4K
NAS Parallel Benchmarks
Test / Class: LU.C
OpenVINO
Model: Handwritten English Recognition FP16 - Device: CPU
OpenVINO
Model: Handwritten English Recognition FP16 - Device: CPU
OpenVINO
Model: Vehicle Detection FP16-INT8 - Device: CPU
OpenVINO
Model: Handwritten English Recognition FP16-INT8 - Device: CPU
OpenVINO
Model: Weld Porosity Detection FP16 - Device: CPU
Liquid-DSP
Threads: 128 - Buffer Length: 256 - Filter Length: 512
ASKAP
Test: tConvolve MPI - Gridding
NAS Parallel Benchmarks
Test / Class: BT.C
OpenVINO
Model: Person Vehicle Bike Detection FP16 - Device: CPU
NAS Parallel Benchmarks
Test / Class: SP.C
OpenVINO
Model: Road Segmentation ADAS FP16 - Device: CPU
miniBUDE
Implementation: OpenMP - Input Deck: BM2
miniBUDE
Implementation: OpenMP - Input Deck: BM2
PostgreSQL
Scaling Factor: 100 - Clients: 1000 - Mode: Read Write
PostgreSQL
Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency
ASKAP
Test: tConvolve MPI - Degridding
Xmrig
Variant: Monero - Hash Count: 1M
Xmrig
Variant: Wownero - Hash Count: 1M
OpenVINO
Model: Vehicle Detection FP16 - Device: CPU
OpenVINO
Model: Machine Translation EN To DE FP16 - Device: CPU
OpenVINO
Model: Person Vehicle Bike Detection FP16 - Device: CPU
OpenVINO
Model: Person Detection FP32 - Device: CPU
OpenVINO
Model: Person Detection FP16 - Device: CPU
OpenVINO
Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU
John The Ripper
Test: bcrypt
NAS Parallel Benchmarks
Test / Class: IS.D
John The Ripper
Test: Blowfish
ACES DGEMM
Sustained Floating-Point Rate
Stress-NG
Test: AVX-512 VNNI
Timed Linux Kernel Compilation
Build: defconfig
Stress-NG
Test: Vector Floating Point
NAS Parallel Benchmarks
Test / Class: CG.C
NAS Parallel Benchmarks
Test / Class: FT.C
OpenVINO
Model: Machine Translation EN To DE FP16 - Device: CPU
Graph500
Scale: 26
OpenVINO
Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU
OpenVINO
Model: Person Detection FP16 - Device: CPU
OpenVINO
Model: Person Detection FP32 - Device: CPU
OpenVINO
Model: Weld Porosity Detection FP16 - Device: CPU
OpenVINO
Model: Road Segmentation ADAS FP16-INT8 - Device: CPU
OpenVINO
Model: Weld Porosity Detection FP16-INT8 - Device: CPU
OpenVINO
Model: Vehicle Detection FP16-INT8 - Device: CPU
OpenVINO
Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU
OpenVINO
Model: Face Detection FP16-INT8 - Device: CPU
Graph500
Scale: 26
Stress-NG
Test: Matrix 3D Math
OpenVINO
Model: Vehicle Detection FP16 - Device: CPU
Coremark
CoreMark Size 666 - Iterations Per Second
Stress-NG
Test: Vector Math
7-Zip Compression
Test: Decompression Rating
GraphicsMagick
Operation: Sharpen
asmFish
1024 Hash Memory, 26 Depth
NAS Parallel Benchmarks
Test / Class: MG.C
Timed LLVM Compilation
Build System: Ninja
Timed Godot Game Engine Compilation
Time To Compile
Timed Node.js Compilation
Time To Compile
7-Zip Compression
Test: Compression Rating
Primesieve
Length: 1e13
Stress-NG
Test: Floating Point
Xcompact3d Incompact3d
Input: X3D-benchmarking input.i3d
Stress-NG
Test: Fused Multiply-Add
OpenVINO
Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU
Stress-NG
Test: Wide Vector Math
OpenVINO
Model: Face Detection Retail FP16 - Device: CPU
OpenVINO
Model: Weld Porosity Detection FP16-INT8 - Device: CPU
GraphicsMagick
Operation: Enhanced
OpenVINO
Model: Road Segmentation ADAS FP16 - Device: CPU
RawTherapee
Total Benchmark Time
DuckDB
Benchmark: TPC-H Parquet
Helsing
Digit Range: 14 digit
Algebraic Multi-Grid Benchmark
Stress-NG
Test: Matrix Math
Graph500
Scale: 26
Timed Gem5 Compilation
Time To Compile
NWChem
Input: C240 Buckyball
DuckDB
Benchmark: IMDB
Rodinia
Test: OpenMP LavaMD
Xcompact3d Incompact3d
Input: input.i3d 193 Cells Per Direction
Timed Linux Kernel Compilation
Build: allmodconfig
Graph500
Scale: 26
LULESH
Stress-NG
Test: Memory Copying
ASTC Encoder
Preset: Exhaustive
ASTC Encoder
Preset: Thorough
ASTC Encoder
Preset: Medium
Cpuminer-Opt
Algorithm: Triple SHA-256, Onecoin
Cpuminer-Opt
Algorithm: Myriad-Groestl
Cpuminer-Opt
Algorithm: Blake-2 S
Cpuminer-Opt
Algorithm: Deepcoin
Tachyon
Total Time
oneDNN
Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU
oneDNN
Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU
rays1bench
Large Scene
libxsmm
M N K: 256
libxsmm
M N K: 128
High Performance Conjugate Gradient
X Y Z: 144 144 144 - RT: 60
OpenVINO
Model: Handwritten English Recognition FP16-INT8 - Device: CPU
GROMACS
Implementation: MPI CPU - Input: water_GMX50_bare
Stockfish
Total Time
Phoronix Test Suite v10.8.4