GPTshop.ai NVIDIA GH200 Linux Benchmarks

Benchmarks by Michael Larabel 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 2402184-NE-GH200THRE73
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

Limit displaying results to tests within:

Chess Test Suite 2 Tests
Timed Code Compilation 5 Tests
C/C++ Compiler Tests 9 Tests
CPU Massive 17 Tests
Creator Workloads 9 Tests
Cryptocurrency Benchmarks, CPU Mining Tests 2 Tests
Cryptography 3 Tests
Fortran Tests 4 Tests
Game Development 2 Tests
HPC - High Performance Computing 14 Tests
Imaging 2 Tests
Common Kernel Benchmarks 2 Tests
Linear Algebra 2 Tests
Machine Learning 2 Tests
Molecular Dynamics 4 Tests
MPI Benchmarks 5 Tests
Multi-Core 25 Tests
NVIDIA GPU Compute 2 Tests
Intel oneAPI 2 Tests
OpenMPI Tests 10 Tests
Programmer / Developer System Benchmarks 7 Tests
Python Tests 6 Tests
Raytracing 2 Tests
Renderers 2 Tests
Scientific Computing 6 Tests
Server 2 Tests
Server CPU Tests 12 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
Show Perf Per Clock 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
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
GPTshop.ai GH200
February 05
  9 Hours, 5 Minutes
HP Z6 G5 A - Threadripper PRO 7995WX
February 17
  12 Hours, 44 Minutes
Invert Hiding All Results Option
  10 Hours, 54 Minutes
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):

GPTshop.ai NVIDIA GH200 Linux Benchmarks Benchmarks by Michael Larabel for a future article. ,,"GPTshop.ai GH200","HP Z6 G5 A - Threadripper PRO 7995WX" Processor,,ARMv8 Neoverse-V2 @ 3.39GHz (72 Cores),AMD Ryzen Threadripper PRO 7995WX 96-Cores @ 6.44GHz (96 Cores / 192 Threads) Motherboard,,Quanta Cloud QuantaGrid S74G-2U 1S7GZ9Z0000 S7G MB (CG1) (3A06 BIOS),HP Z6 G5 A Workstation 8B24 (U65 Ver. 01.01.04 BIOS) Memory,,1 x 480GB DRAM-6400MT/s,8 x 16GB DRAM-5200MT/s Hynix HMCG78AGBRA190N Disk,,960GB SAMSUNG MZ1L2960HCJR-00A07 + 1920GB SAMSUNG MZTL21T9,2 x 1024GB SAMSUNG MZVL21T0HCLR-00BH1 Graphics,,ASPEED,NVIDIA RTX A4000 16GB Network,,2 x Mellanox MT2910 + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE,Realtek RTL8111/8168/8411 Chipset,,,AMD Device 14a4 Audio,,,NVIDIA GA104 HD Audio Monitor,,,ASUS VP28U OS,,Ubuntu 23.10,Ubuntu 23.10 Kernel,,6.5.0-15-generic (aarch64),6.5.0-17-generic (x86_64) Compiler,,GCC 13.2.0,GCC 13.2.0 File-System,,ext4,ext4 Screen Resolution,,1920x1200,3840x2160 Desktop,,,GNOME Shell 45.2 Display Server,,,X Server 1.21.1.7 Display Driver,,,NVIDIA 535.154.05 OpenGL,,,4.6.0 OpenCL,,,OpenCL 3.0 CUDA 12.2.148 ,,"GPTshop.ai GH200","HP Z6 G5 A - Threadripper PRO 7995WX" "Stress-NG - Test: CPU Stress (Bogo Ops/s)",HIB,30484.77,212486.91 "Stress-NG - Test: Matrix Math (Bogo Ops/s)",HIB,512759.08,430429.52 "Stress-NG - Test: Vector Math (Bogo Ops/s)",HIB,359058.52,619071.09 "Stress-NG - Test: AVX-512 VNNI (Bogo Ops/s)",HIB,4173580.13,9099613.65 "Stress-NG - Test: Floating Point (Bogo Ops/s)",HIB,20137.35,30460.61 "Stress-NG - Test: Matrix 3D Math (Bogo Ops/s)",HIB,17483.02,9100.74 "Stress-NG - Test: Memory Copying (Bogo Ops/s)",HIB,27182.72,27883.51 "Stress-NG - Test: Wide Vector Math (Bogo Ops/s)",HIB,2002466.67,2721964.70 "Stress-NG - Test: Fused Multiply-Add (Bogo Ops/s)",HIB,139525267.41,206576021.93 "Stress-NG - Test: Vector Floating Point (Bogo Ops/s)",HIB,103967.93,219092.94 "ASTC Encoder - Preset: Medium (MT/s)",HIB,,443.4589 "libxsmm - M N K: 256 (GFLOPS/s)",HIB,,2582.5 "libxsmm - M N K: 128 (GFLOPS/s)",HIB,,2039.8 "ASTC Encoder - Preset: Thorough (MT/s)",HIB,,62.6393 "ASTC Encoder - Preset: Exhaustive (MT/s)",HIB,,6.6196 "RawTherapee - Total Benchmark Time (sec)",LIB,46.718,57.892 "Xmrig - Variant: Monero - Hash Count: 1M (H/s)",HIB,17253.0,56612.2 "Xmrig - Variant: Wownero - Hash Count: 1M (H/s)",HIB,21924.1,71115.4 "Graph500 - Scale: 26 (bfs median_TEPS)",HIB,1249790000,634702000 "Graph500 - Scale: 26 (bfs max_TEPS)",HIB,1315650000,647711000 "Graph500 - Scale: 26 (sssp median_TEPS)",HIB,299027000,317931000 "Graph500 - Scale: 26 (sssp max_TEPS)",HIB,467012000,399994000 "miniBUDE - Implementation: OpenMP - Input Deck: BM2 (GFInst/s)",HIB,1193.124,4472.175 "miniBUDE - Implementation: OpenMP - Input Deck: BM2 (Billion Interactions/s)",HIB,47.725,178.887 "GROMACS - Implementation: MPI CPU - Input: water_GMX50_bare (Ns/Day)",HIB,5.194,10.314 "High Performance Conjugate Gradient - X Y Z: 144 144 144 - RT: 60 (GFLOP/s)",HIB,41.6941, "NAS Parallel Benchmarks - Test / Class: BT.C (Mop/s)",HIB,49381.68,213489.54 "NAS Parallel Benchmarks - Test / Class: CG.C (Mop/s)",HIB,24046.25,50606.21 "NAS Parallel Benchmarks - Test / Class: FT.C (Mop/s)",HIB,48109.28,100501.03 "NAS Parallel Benchmarks - Test / Class: IS.D (Mop/s)",HIB,1748.55,4351.68 "NAS Parallel Benchmarks - Test / Class: LU.C (Mop/s)",HIB,39739.62,251214.23 "NAS Parallel Benchmarks - Test / Class: MG.C (Mop/s)",HIB,58334.53,94796.95 "NAS Parallel Benchmarks - Test / Class: SP.C (Mop/s)",HIB,21268.70,88821.77 "Rodinia - Test: OpenMP LavaMD (sec)",LIB,30.308,26.814 "oneDNN - Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,,0.358902 "oneDNN - Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,,1.25835 "OpenVINO - Model: Face Detection FP16 - Device: CPU (FPS)",HIB,7.46,48.01 "OpenVINO - Model: Face Detection FP16 - Device: CPU (ms)",LIB,134.06,993.05 "OpenVINO - Model: Person Detection FP16 - Device: CPU (FPS)",HIB,19.06,340.49 "OpenVINO - Model: Person Detection FP16 - Device: CPU (ms)",LIB,52.51,140.80 "OpenVINO - Model: Person Detection FP32 - Device: CPU (FPS)",HIB,19.16,341.45 "OpenVINO - Model: Person Detection FP32 - Device: CPU (ms)",LIB,52.20,140.45 "OpenVINO - Model: Vehicle Detection FP16 - Device: CPU (FPS)",HIB,124.47,3237.40 "Helsing - Digit Range: 14 digit (sec)",LIB,67.612,55.902 "OpenVINO - Model: Vehicle Detection FP16 - Device: CPU (ms)",LIB,8.02,14.81 "OpenVINO - Model: Face Detection FP16-INT8 - Device: CPU (FPS)",HIB,1.01,94.94 "OpenVINO - Model: Face Detection FP16-INT8 - Device: CPU (ms)",LIB,993.52,503.91 "OpenVINO - Model: Face Detection Retail FP16 - Device: CPU (FPS)",HIB,184.36,11647.89 "OpenVINO - Model: Face Detection Retail FP16 - Device: CPU (ms)",LIB,5.41,4.11 "OpenVINO - Model: Road Segmentation ADAS FP16 - Device: CPU (FPS)",HIB,44.58,1712.72 "OpenVINO - Model: Road Segmentation ADAS FP16 - Device: CPU (ms)",LIB,22.44,28.00 "OpenVINO - Model: Vehicle Detection FP16-INT8 - Device: CPU (FPS)",HIB,9.94,5727.47 "OpenVINO - Model: Vehicle Detection FP16-INT8 - Device: CPU (ms)",LIB,100.62,8.37 "OpenVINO - Model: Weld Porosity Detection FP16 - Device: CPU (FPS)",HIB,285.00,4793.80 "OpenVINO - Model: Weld Porosity Detection FP16 - Device: CPU (ms)",LIB,3.50,20.01 "OpenVINO - Model: Face Detection Retail FP16-INT8 - Device: CPU (FPS)",HIB,26.53,16968.10 "OpenVINO - Model: Face Detection Retail FP16-INT8 - Device: CPU (ms)",LIB,37.70,5.64 "OpenVINO - Model: Road Segmentation ADAS FP16-INT8 - Device: CPU (FPS)",HIB,3.24,2039.24 "OpenVINO - Model: Road Segmentation ADAS FP16-INT8 - Device: CPU (ms)",LIB,308.42,23.52 "OpenVINO - Model: Machine Translation EN To DE FP16 - Device: CPU (FPS)",HIB,23.78,555.21 "OpenVINO - Model: Machine Translation EN To DE FP16 - Device: CPU (ms)",LIB,42.05,86.38 "OpenVINO - Model: Weld Porosity Detection FP16-INT8 - Device: CPU (FPS)",HIB,76.44,9585.34 "OpenVINO - Model: Weld Porosity Detection FP16-INT8 - Device: CPU (ms)",LIB,13.07,10.00 "OpenVINO - Model: Person Vehicle Bike Detection FP16 - Device: CPU (FPS)",HIB,26.68,5467.67 "OpenVINO - Model: Person Vehicle Bike Detection FP16 - Device: CPU (ms)",LIB,37.48,8.76 "OpenVINO - Model: Handwritten English Recognition FP16 - Device: CPU (FPS)",HIB,4.33,2541.51 "OpenVINO - Model: Handwritten English Recognition FP16 - Device: CPU (ms)",LIB,231.18,37.75 "OpenVINO - Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU (FPS)",HIB,781.77,83726.28 "OpenVINO - Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU (ms)",LIB,1.27,0.90 "OpenVINO - Model: Handwritten English Recognition FP16-INT8 - Device: CPU (FPS)",HIB,4.16,2141.63 "OpenVINO - Model: Handwritten English Recognition FP16-INT8 - Device: CPU (ms)",LIB,240.51,44.96 "OpenVINO - Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU (FPS)",HIB,595.73,107003.12 "OpenVINO - Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU (ms)",LIB,1.67,0.65 "ASKAP - Test: tConvolve MPI - Degridding (Mpix/sec)",HIB,12407.6,40906.5 "ASKAP - Test: tConvolve MPI - Gridding (Mpix/sec)",HIB,9652.19,43543.9 "ACES DGEMM - Sustained Floating-Point Rate (GFLOP/s)",HIB,17.936778,43.456885 "Algebraic Multi-Grid Benchmark - (Figure Of Merit)",HIB,1997929111,1669939667 "LULESH - (z/s)",HIB,23185.177,23830.867 "NWChem - Input: C240 Buckyball (sec)",LIB,1403.5,1601.1 "Xcompact3d Incompact3d - Input: X3D-benchmarking input.i3d (sec)",LIB,254.490031,383.985718 "Xcompact3d Incompact3d - Input: input.i3d 193 Cells Per Direction (sec)",LIB,9.81172053,10.7605492 "Coremark - CoreMark Size 666 - Iterations Per Second (Iterations/Sec)",HIB,2263279.939802,3998440.414024 "Primesieve - Length: 1e13 (sec)",LIB,35.490,23.288 "Stockfish - Total Time (Nodes/s)",HIB,153826682,285651359 "7-Zip Compression - Test: Compression Rating (MIPS)",HIB,345295,547165 "7-Zip Compression - Test: Decompression Rating (MIPS)",HIB,389055,658991 "John The Ripper - Test: bcrypt (Real C/S)",HIB,68817,172723 "John The Ripper - Test: WPA PSK (Real C/S)",HIB,70310,612830 "John The Ripper - Test: Blowfish (Real C/S)",HIB,69811,172819 "John The Ripper - Test: MD5 (Real C/S)",HIB,1900667,14692667 "Timed LLVM Compilation - Build System: Ninja (sec)",LIB,195.982,122.388 "asmFish - 1024 Hash Memory, 26 Depth (Nodes/s)",HIB,150936379,248304686 "Cpuminer-Opt - Algorithm: Deepcoin (kH/s)",HIB,,33632 "Cpuminer-Opt - Algorithm: Blake-2 S (kH/s)",HIB,,560763 "Cpuminer-Opt - Algorithm: Myriad-Groestl (kH/s)",HIB,,44940 "Cpuminer-Opt - Algorithm: Triple SHA-256, Onecoin (kH/s)",HIB,,401393 "Timed Linux Kernel Compilation - Build: defconfig (sec)",LIB,66.894,30.978 "Timed Linux Kernel Compilation - Build: allmodconfig (sec)",LIB,282.286,261.438 "GraphicsMagick - Operation: Sharpen (Iterations/min)",HIB,1363,824 "GraphicsMagick - Operation: Enhanced (Iterations/min)",HIB,1761,1380 "Tachyon - Total Time (sec)",LIB,,16.0529 "SVT-AV1 - Encoder Mode: Preset 4 - Input: Bosphorus 4K (FPS)",HIB,0.826,7.016 "SVT-AV1 - Encoder Mode: Preset 8 - Input: Bosphorus 4K (FPS)",HIB,13.908,119.984 "SVT-AV1 - Encoder Mode: Preset 12 - Input: Bosphorus 4K (FPS)",HIB,31.468,206.132 "SVT-AV1 - Encoder Mode: Preset 13 - Input: Bosphorus 4K (FPS)",HIB,31.496,202.283 "Timed Godot Game Engine Compilation - Time To Compile (sec)",LIB,139.099,86.962 "rays1bench - Large Scene (mrays/s)",HIB,,582.32 "Timed Gem5 Compilation - Time To Compile (sec)",LIB,180.622,156.374 "Timed Node.js Compilation - Time To Compile (sec)",LIB,173.877,109.232 "Liquid-DSP - Threads: 128 - Buffer Length: 256 - Filter Length: 512 (samples/s)",HIB,229866667,1306966667 "Liquid-DSP - Threads: 240 - Buffer Length: 256 - Filter Length: 512 (samples/s)",HIB,237746667,1530466667 "DuckDB - Benchmark: IMDB (sec)",LIB,92.081,104.275 "DuckDB - Benchmark: TPC-H Parquet (sec)",LIB,148.759,120.764 "PostgreSQL - Scaling Factor: 100 - Clients: 1000 - Mode: Read Write (TPS)",HIB,54975,16124 "PostgreSQL - Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency (ms)",LIB,18.230,62.032