GPTshop.ai GH200 Linux Benchmarks

Benchmarks by Michael Larabel for a future article looking at the NVIDIA GH200 CPU performance. Other benchmarks of the NVIDIA GH200 forthcoming by Michael Larabel.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2402073-NE-2402063NE88
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 4 Tests
C/C++ Compiler Tests 6 Tests
CPU Massive 11 Tests
Creator Workloads 3 Tests
Cryptography 2 Tests
Fortran Tests 3 Tests
HPC - High Performance Computing 8 Tests
Imaging 2 Tests
Common Kernel Benchmarks 2 Tests
Linear Algebra 2 Tests
Molecular Dynamics 3 Tests
MPI Benchmarks 2 Tests
Multi-Core 14 Tests
OpenMPI Tests 7 Tests
Programmer / Developer System Benchmarks 6 Tests
Python Tests 4 Tests
Scientific Computing 5 Tests
Server 2 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

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
Performance Per
Dollar
Date
Run
  Test
  Duration
EPYC 8534P
December 01 2023
  4 Hours, 28 Minutes
EPYC 8534PN
December 06 2023
  4 Hours, 55 Minutes
EPYC 9554
November 13 2023
  4 Hours, 45 Minutes
EPYC 9554 2P
November 14 2023
  3 Hours, 38 Minutes
EPYC 9654
November 15 2023
  4 Hours, 22 Minutes
EPYC 9654 2P
November 16 2023
  4 Hours, 16 Minutes
EPYC 9684X
November 08 2023
  6 Hours, 1 Minute
EPYC 9684X 2P
November 07 2023
  4 Hours, 14 Minutes
EPYC 9754
November 09 2023
  4 Hours, 33 Minutes
EPYC 9754 2P
November 11 2023
  5 Hours, 8 Minutes
Xeon Platinum 8380
December 03 2023
  6 Hours, 16 Minutes
Xeon Platinum 8380 2P
December 03 2023
  4 Hours, 17 Minutes
Xeon Platinum 8490H
October 31 2023
  4 Hours, 6 Minutes
Xeon Platinum 8490H 2P
October 30 2023
  3 Hours, 41 Minutes
Xeon Platinum 8592+
December 08 2023
  3 Hours, 50 Minutes
Xeon Platinum 8592+ 2P
December 07 2023
  3 Hours, 9 Minutes
GPTshop.ai GH200
February 05
  4 Hours, 24 Minutes
Ampere Altra Max M128-30
February 06
  6 Hours, 48 Minutes
Invert Hiding All Results Option
  4 Hours, 36 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):

GPTshop.ai GH200 Linux Benchmarks Benchmarks by Michael Larabel for a future article looking at the NVIDIA GH200 CPU performance. Other benchmarks of the NVIDIA GH200 forthcoming by Michael Larabel. ,,"EPYC 8534P","EPYC 8534PN","EPYC 9554","EPYC 9554 2P","EPYC 9654","EPYC 9654 2P","EPYC 9684X","EPYC 9684X 2P","EPYC 9754","EPYC 9754 2P","Xeon Platinum 8380","Xeon Platinum 8380 2P","Xeon Platinum 8490H","Xeon Platinum 8490H 2P","Xeon Platinum 8592+","Xeon Platinum 8592+ 2P","GPTshop.ai GH200","Ampere Altra Max M128-30" Processor,,AMD EPYC 8534P 64-Core @ 2.30GHz (64 Cores / 128 Threads),AMD EPYC 8534PN 64-Core @ 2.00GHz (64 Cores / 128 Threads),AMD EPYC 9554 64-Core @ 3.10GHz (64 Cores / 128 Threads),2 x AMD EPYC 9554 64-Core @ 3.10GHz (128 Cores / 256 Threads),AMD EPYC 9654 96-Core @ 2.40GHz (96 Cores / 192 Threads),2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads),AMD EPYC 9684X 96-Core @ 2.55GHz (96 Cores / 192 Threads),2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads),AMD EPYC 9754 128-Core @ 2.25GHz (128 Cores / 256 Threads),2 x AMD EPYC 9754 128-Core @ 2.25GHz (256 Cores / 512 Threads),Intel Xeon Platinum 8380 @ 3.40GHz (40 Cores / 80 Threads),2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads),Intel Xeon Platinum 8490H @ 3.50GHz (60 Cores / 120 Threads),2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads),INTEL XEON PLATINUM 8592+ @ 3.90GHz (64 Cores / 128 Threads),2 x INTEL XEON PLATINUM 8592+ @ 3.90GHz (128 Cores / 256 Threads),ARMv8 Neoverse-V2 @ 3.39GHz (72 Cores),ARMv8 Neoverse-N1 @ 3.00GHz (128 Cores) Motherboard,,AMD Cinnabar (RCB1009C BIOS),AMD Cinnabar (RCB1009C BIOS),AMD Titanite_4G (RTI1007B BIOS),AMD Titanite_4G (RTI1007B BIOS),AMD Titanite_4G (RTI1007B BIOS),AMD Titanite_4G (RTI1007B BIOS),AMD Titanite_4G (RTI1007B BIOS),AMD Titanite_4G (RTI1007B BIOS),AMD Titanite_4G (RTI1007B BIOS),AMD Titanite_4G (RTI1007B BIOS),Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS),Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS),Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS),Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS),Quanta Cloud S6Q-MB-MPS (3B05.TEL4P1 BIOS),Quanta Cloud S6Q-MB-MPS (3B05.TEL4P1 BIOS),Quanta Cloud QuantaGrid S74G-2U 1S7GZ9Z0000 S7G MB (CG1) (3A06 BIOS),GIGABYTE G242-P36-00 MP32-AR2-00 v01000100 (F31k SCP: 2.10.20220531 BIOS) Chipset,,AMD Device 14a4,AMD Device 14a4,AMD Device 14a4,AMD Device 14a4,AMD Device 14a4,AMD Device 14a4,AMD Device 14a4,AMD Device 14a4,AMD Device 14a4,AMD Device 14a4,Intel Ice Lake IEH,Intel Ice Lake IEH,Intel Device 1bce,Intel Device 1bce,Intel Device 1bce,Intel Device 1bce,,Ampere Computing LLC Altra PCI Root Complex A Memory,,192GB,192GB,768GB,1520GB,768GB,1520GB,768GB,1520GB,768GB,1520GB,256GB,512GB,512GB,1008GB,512GB,1008GB,1 x 480GB DRAM-6400MT/s,16 x 32GB DDR4-3200MT/s Samsung M393A4K40DB3-CWE Disk,,3201GB Micron_7450_MTFDKCC3T2TFS,3201GB Micron_7450_MTFDKCC3T2TFS,3201GB Micron_7450_MTFDKCC3T2TFS,3201GB Micron_7450_MTFDKCC3T2TFS,3201GB Micron_7450_MTFDKCC3T2TFS,3201GB Micron_7450_MTFDKCC3T2TFS,3201GB Micron_7450_MTFDKCC3T2TFS,3201GB Micron_7450_MTFDKCC3T2TFS,3201GB Micron_7450_MTFDKCC3T2TFS,3201GB Micron_7450_MTFDKCC3T2TFS,3201GB Micron_7450_MTFDKCC3T2TFS,3201GB Micron_7450_MTFDKCC3T2TFS,3201GB Micron_7450_MTFDKCC3T2TFS,3201GB Micron_7450_MTFDKCC3T2TFS,3201GB Micron_7450_MTFDKCC3T2TFS,3201GB Micron_7450_MTFDKCC3T2TFS + 0GB Virtual HDisk0 + 0GB Virtual HDisk1 + 0GB Virtual HDisk2 + 0GB Virtual HDisk3,960GB SAMSUNG MZ1L2960HCJR-00A07 + 1920GB SAMSUNG MZTL21T9,800GB Micron_7450_MTFDKBA800TFS Graphics,,ASPEED,ASPEED,ASPEED,ASPEED,ASPEED,ASPEED,ASPEED,ASPEED,ASPEED,ASPEED,ASPEED,ASPEED,ASPEED,ASPEED,ASPEED,ASPEED,ASPEED,ASPEED Network,,2 x Broadcom NetXtreme BCM5720 PCIe,2 x Broadcom NetXtreme BCM5720 PCIe,Broadcom NetXtreme BCM5720 PCIe,Broadcom NetXtreme BCM5720 PCIe,Broadcom NetXtreme BCM5720 PCIe,Broadcom NetXtreme BCM5720 PCIe,Broadcom NetXtreme BCM5720 PCIe,Broadcom NetXtreme BCM5720 PCIe,Broadcom NetXtreme BCM5720 PCIe,Broadcom NetXtreme BCM5720 PCIe,2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP,2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP,,2 x Intel X710 for 10GBASE-T,,2 x Intel X710 for 10GBASE-T,2 x Mellanox MT2910 + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE,2 x Intel I350 Monitor,,,,,,,,,,,,VE228,VE228,,,,,,VGA HDMI OS,,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10 Kernel,,6.6.0-rc5-phx (x86_64),6.6.0-rc5-phx (x86_64),6.6.0-rc5-phx (x86_64),6.6.0-rc5-phx (x86_64),6.6.0-rc5-phx (x86_64),6.6.0-rc5-phx (x86_64),6.6.0-rc5-phx (x86_64),6.6.0-rc5-phx (x86_64),6.6.0-rc5-phx (x86_64),6.6.0-rc5-phx (x86_64),6.6.0-rc5-phx (x86_64),6.6.0-rc5-phx (x86_64),6.6.0-rc5-phx (x86_64),6.6.0-rc5-phx (x86_64),6.6.0-rc5-phx (x86_64),6.6.0-rc5-phx (x86_64),6.5.0-15-generic (aarch64),6.5.0-13-generic (aarch64) Desktop,,GNOME Shell 45.0,GNOME Shell 45.0,GNOME Shell 45.0,GNOME Shell 45.0,GNOME Shell 45.0,GNOME Shell 45.0,GNOME Shell 45.0,GNOME Shell 45.0,GNOME Shell 45.0,GNOME Shell 45.0,GNOME Shell 45.0,GNOME Shell 45.0,GNOME Shell 45.0,GNOME Shell 45.0,GNOME Shell 45.0,GNOME Shell 45.0,, Display Server,,X Server 1.21.1.7,X Server 1.21.1.7,X Server 1.21.1.7,X Server 1.21.1.7,X Server 1.21.1.7,X Server 1.21.1.7,X Server 1.21.1.7,X Server 1.21.1.7,X Server 1.21.1.7,X Server 1.21.1.7,X Server 1.21.1.7,X Server 1.21.1.7,X Server 1.21.1.7,X Server 1.21.1.7,X Server 1.21.1.7,X Server 1.21.1.7,, Compiler,,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0 File-System,,ext4,ext4,ext4,ext4,ext4,ext4,ext4,ext4,ext4,ext4,ext4,ext4,ext4,ext4,ext4,ext4,ext4,ext4 Screen Resolution,,1920x1200,1920x1200,1920x1200,1920x1200,1920x1200,1920x1200,1920x1200,1920x1200,1920x1200,1920x1200,1920x1080,1920x1080,1920x1200,1920x1200,1920x1200,1920x1200,1920x1200,1920x1080 ,,"EPYC 8534P","EPYC 8534PN","EPYC 9554","EPYC 9554 2P","EPYC 9654","EPYC 9654 2P","EPYC 9684X","EPYC 9684X 2P","EPYC 9754","EPYC 9754 2P","Xeon Platinum 8380","Xeon Platinum 8380 2P","Xeon Platinum 8490H","Xeon Platinum 8490H 2P","Xeon Platinum 8592+","Xeon Platinum 8592+ 2P","GPTshop.ai GH200","Ampere Altra Max M128-30" "High Performance Conjugate Gradient - X Y Z: 144 144 144 - RT: 60 (GFLOP/s)",HIB,22.2406,22.2492,22.4511,49.0062,32.1283,43.9701,23.7784,44.1122,25.8918,47.0053,20.6544,40.3123,31.2432,60.4224,35.4214,70.9524,41.6941,21.2379 "Rodinia - Test: OpenMP LavaMD (sec)",LIB,45.380,52.115,34.014,20.545,30.240,18.239,30.317,18.318,25.150,16.455,77.083,44.552,42.713,26.661,39.886,24.778,30.308,31.671 "Algebraic Multi-Grid Benchmark - (Figure Of Merit)",HIB,1152783333,1150663000,2321156000,4545229333,2296730667,4514770333,2374853333,4659305667,2291049667,4531752333,1079277000,2119944667,1611826000,3174538667,1839912667,3739485333,1997929111,1059875333 "NWChem - Input: C240 Buckyball (sec)",LIB,1955.4,2189.1,1452.1,1322.7,1568.4,1559.5,1641.6,1614.6,1700.8,1721.4,3505.4,2198.3,2056.6,1879.7,1850.8,1738.6,1403.5,2707.9 "Xcompact3d Incompact3d - Input: X3D-benchmarking input.i3d (sec)",LIB,560.360494,561.969991,515.792758,235.749586,430.080329,247.178482,440.548584,194.743902,493.502452,249.071167,551.260030,289.896668,353.557595,193.573130,323.527415,167.085159,254.490031,607.675171 "Xcompact3d Incompact3d - Input: input.i3d 193 Cells Per Direction (sec)",LIB,20.9124565,20.8184172,9.74551621,4.87686817,8.45212936,4.29390898,7.30814419,4.02365785,9.02806168,4.41382325,24.0121949,11.0611921,12.7983420,6.17124205,10.1814694,5.24690800,9.81172053,23.7940191 "LULESH - (z/s)",HIB,16684.800,16431.062,24037.442,46784.684,23701.442,45810.905,24712.884,47999.677,22356.746,43781.190,18008.014,33249.861,23997.715,45133.446,39468.910,72625.296,23185.177,16161.786 "Xmrig - Variant: Monero - Hash Count: 1M (H/s)",HIB,20536.7,20394.0,47926.4,82864.5,59047.7,103949.6,69205.6,112646.9,29356.1,85822.0,14453.8,25209.0,27608.5,45484.3,40381.2,70136.2,17253.0,4298.5 "John The Ripper - Test: bcrypt (Real C/S)",HIB,105831,94229,138035,247115,166850,308207,166119,309091,204828,421977,56989,113216,93877,178108,104067,196398,68817,109117 "GraphicsMagick - Operation: Sharpen (Iterations/min)",HIB,530,484,669,1038,809,1122,775,1089,924,1242,351,639,691,1173,749,1302,1363,1281 "GraphicsMagick - Operation: Enhanced (Iterations/min)",HIB,902,834,1142,1600,1319,1660,1277,1646,1451,1805,612,1077,1124,1763,1192,1936,1761,1233 "ACES DGEMM - Sustained Floating-Point Rate (GFLOP/s)",HIB,22.822067,21.146791,30.174904,54.738943,39.282158,69.671333,40.320062,69.398619,43.681923,86.331170,13.622806,24.966772,23.257388,45.786798,29.136787,58.642849,17.936778,18.206802 "7-Zip Compression - Test: Compression Rating (MIPS)",HIB,354386,332890,489736,734093,564950,809868,554411,802007,586571,827103,248249,411957,389690,604131,448786,670551,345295,334516 "7-Zip Compression - Test: Decompression Rating (MIPS)",HIB,385839,343521,521569,947599,648630,1229686,623489,1203430,774122,1462016,193509,331094,299902,547633,308961,627606,389055,541268 "Stockfish - Total Time (Nodes/s)",HIB,176962395,153597574,241774328,412586511,289066909,511362452,281982711,479462631,363329642,581155326,90465243,172510998,153469265,275371601,167594290,297535072,153826682,189937895 "asmFish - 1024 Hash Memory, 26 Depth (Nodes/s)",HIB,157920638,144229352,210167054,370493283,250209020,372335155,233926631,362859456,290260505,375753268,88111984,163860413,130818594,235032608,154003409,272155356,150936379,214150509 "Timed Godot Game Engine Compilation - Time To Compile (sec)",LIB,137.467,142.989,103.500,92.979,101.563,92.427,98.555,89.617,118.247,110.070,169.295,131.143,128.467,109.561,111.960,93.302,139.099,229.970 "Timed LLVM Compilation - Build System: Ninja (sec)",LIB,179.541,191.733,131.203,90.327,133.070,91.010,131.990,91.745,146.386,98.898,264.126,159.177,169.528,110.861,148.735,96.469,195.982,267.099 "Timed Node.js Compilation - Time To Compile (sec)",LIB,165.101,174.552,121.928,93.413,120.156,93.051,119.203,92.355,130.460,104.590,229.912,149.180,151.567,108.095,134.093,98.328,173.877,268.430 "Primesieve - Length: 1e13 (sec)",LIB,42.839,54.283,28.136,14.677,24.164,12.528,25.969,13.294,21.756,11.173,80.291,40.808,52.375,27.422,49.062,25.131,35.490,41.914 "Helsing - Digit Range: 14 digit (sec)",LIB,94.422,113.139,71.268,38.193,61.529,31.660,64.349,32.673,48.947,28.083,161.892,84.516,86.758,50.484,84.948,49.317,67.612,57.044 "Graph500 - Scale: 26 (bfs median_TEPS)",HIB,723332000,656629000,836159000,1258070000,816172000,1456580000,854029000,1406670000,1147090000,1865120000,787545000,874430000,1073860000,1051290000,1238670000,1199830000,1249790000,976326000 "Graph500 - Scale: 26 (bfs max_TEPS)",HIB,756590000,693945000,865152000,1305120000,839917000,1543990000,882181000,1484490000,1184510000,2040450000,802659000,904141000,1113120000,1094220000,1304200000,1248330000,1315650000,985207000 "Graph500 - Scale: 26 (sssp median_TEPS)",HIB,267945000,249463000,368016000,496492000,391167000,581965000,383754000,589785000,377033000,732799000,221437000,293299000,333129000,379655000,419138000,476274000,299027000,222683000 "Graph500 - Scale: 26 (sssp max_TEPS)",HIB,336877000,318668000,467453000,670675000,499347000,857107000,501222000,825625000,502151000,1074790000,300411000,390893000,454483000,521570000,547915000,653964000,467012000,332248000 "DuckDB - Benchmark: IMDB (sec)",LIB,123.605,126.955,103.720,132.292,115.805,154.971,116.050,154.192,147.601,202.191,110.729,124.308,99.249,123.833,96.870,124.713,92.081,142.913 "DuckDB - Benchmark: TPC-H Parquet (sec)",LIB,171.659,172.196,143.306,148.515,146.276,156.696,147.489,158.484,177.134,191.652,167.223,169.567,148.099,156.790,134.732,149.980,148.759,238.828 "PostgreSQL - Scaling Factor: 100 - Clients: 1000 - Mode: Read Write (TPS)",HIB,61916,57178,72860,60352,78212,57174,67606,54657,71483,57557,64769,71624,70604,67565,75232,63852,54975,58226 "PostgreSQL - Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency (ms)",LIB,16.153,17.491,13.726,16.570,12.786,17.492,14.792,18.296,13.989,17.391,15.448,13.962,14.164,14.801,13.293,15.663,18.230,17.176 "RawTherapee - Total Benchmark Time (sec)",LIB,59.455,60.315,49.943,58.333,52.051,64.678,52.991,65.000,66.132,81.019,53.384,55.527,46.578,53.671,45.530,57.793,46.718,66.765 "Stress-NG - Test: Matrix Math (Bogo Ops/s)",HIB,266664.84,233716.23,346518.02,688593.49,421053.02,816181.03,417406.39,817035.07,552067.04,1062616.62,181695.08,353381.32,304345.30,535739.58,301894.53,536146.58,512759.08,682631.37 "Stress-NG - Test: Matrix 3D Math (Bogo Ops/s)",HIB,6004.42,5986.41,13521.34,19439.89,13448.20,18432.29,16634.44,22460.19,8009.21,17903.58,6436.61,12793.84,9894.20,18308.84,13854.38,25487.42,17483.02,5116.05 "Timed Gem5 Compilation - Time To Compile (sec)",LIB,222.757,231.494,179.743,156.205,180.857,162.867,180.061,159.582,208.576,185.753,251.631,193.021,197.759,161.439,174.175,146.623,180.622,265.149