NVIDIA GH200 Benchmarks Smoke Run Comparison

Benchmarks by Michael Larabel for a future article. Just some initial smoke run benchmarks looking at the NVIDIA GH200 CPU performance versus other server CPUs. More interesting benchmarks to come.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2401256-NE-NVIDIAGH254
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:

Timed Code Compilation 5 Tests
C/C++ Compiler Tests 4 Tests
CPU Massive 11 Tests
Creator Workloads 3 Tests
Cryptography 2 Tests
Database Test Suite 2 Tests
Fortran Tests 4 Tests
HPC - High Performance Computing 11 Tests
Imaging 2 Tests
Common Kernel Benchmarks 3 Tests
Linear Algebra 2 Tests
Molecular Dynamics 4 Tests
MPI Benchmarks 5 Tests
Multi-Core 14 Tests
OpenMPI Tests 10 Tests
Programmer / Developer System Benchmarks 7 Tests
Python Tests 4 Tests
Scientific Computing 6 Tests
Server 4 Tests
Server CPU Tests 7 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
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

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
Condense Test Profiles With Multiple Version Results 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 9554
November 13 2023
  5 Hours, 29 Minutes
EPYC 9654
November 15 2023
  5 Hours, 37 Minutes
EPYC 9684X
November 08 2023
  7 Hours, 10 Minutes
EPYC 9754
November 09 2023
  6 Hours, 20 Minutes
Xeon Platinum 8490H
October 31 2023
  4 Hours, 9 Minutes
Ampere Altra Max 128c
November 27 2023
  7 Hours, 48 Minutes
GPTshop GH200
January 25
  4 Hours, 28 Minutes
Invert Hiding All Results Option
  5 Hours, 52 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):


NVIDIA GH200 Benchmarks Smoke Run Comparison Suite 1.0.0 System Test suite extracted from NVIDIA GH200 Benchmarks Smoke Run Comparison. pts/compress-7zip-1.10.0 Test: Compression Rating pts/mt-dgemm-1.2.0 Sustained Floating-Point Rate pts/amg-1.1.0 pts/cassandra-1.2.0 WRITE Test: Writes pts/askap-2.1.0 tConvolveMT Test: tConvolve MT - Gridding pts/askap-2.1.0 tConvolveMPI Test: tConvolve MPI - Degridding pts/askap-2.1.0 tConvolveMPI Test: tConvolve MPI - Gridding pts/cloverleaf-1.2.0 clover_bm16 Input: clover_bm16 pts/cloverleaf-1.2.0 clover_bm64_short Input: clover_bm64_short pts/duckdb-1.0.0 benchmark/imdb Benchmark: IMDB pts/duckdb-1.0.0 benchmark/tpch/parquet Benchmark: TPC-H Parquet pts/easywave-1.0.0 -grid examples/e2Asean.grd -source examples/BengkuluSept2007.flt -time 1200 Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200 pts/easywave-1.0.0 -grid examples/e2Asean.grd -source examples/BengkuluSept2007.flt -time 2400 Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400 pts/graph500-1.0.1 26 Scale: 26 pts/graphics-magick-2.1.0 -sharpen 0x2.0 Operation: Sharpen pts/graphics-magick-2.1.0 -enhance Operation: Enhanced pts/hpcg-1.3.0 --nx=144 --ny=144 --nz=144 --rt=60 X Y Z: 144 144 144 - RT: 60 pts/lulesh-1.1.1 pts/minife-1.0.0 -‐nx 264 --ny 256 -‐nz 256 Problem Size: Small pts/npb-1.4.5 cg.C Test / Class: CG.C pts/npb-1.4.5 ft.C Test / Class: FT.C pts/npb-1.4.5 is.D Test / Class: IS.D pts/npb-1.4.5 mg.C Test / Class: MG.C pts/openssl-3.1.0 sha512 Algorithm: SHA512 pts/primesieve-1.9.0 1e13 Length: 1e13 system/rawtherapee-1.0.1 Total Benchmark Time pts/rocksdb-1.5.0 --benchmarks="readrandom" Test: Random Read pts/rodinia-1.3.2 OMP_LAVAMD Test: OpenMP LavaMD pts/stress-ng-1.11.0 --numa -1 --no-rand-seed Test: NUMA pts/stress-ng-1.11.0 --memcpy -1 --no-rand-seed Test: Memory Copying pts/build-gem5-1.1.0 Time To Compile pts/build-godot-4.0.0 Time To Compile pts/build-linux-kernel-1.15.0 allmodconfig Build: allmodconfig pts/build-llvm-1.5.0 Ninja Build System: Ninja pts/build-nodejs-1.3.0 Time To Compile pts/incompact3d-2.0.2 input.i3d Input: X3D-benchmarking input.i3d pts/incompact3d-2.0.2 input_193_nodes.i3d Input: input.i3d 193 Cells Per Direction pts/xmrig-1.1.0 --bench=1M Variant: Monero - Hash Count: 1M pts/xmrig-1.1.0 -a rx/wow --bench=1M Variant: Wownero - Hash Count: 1M