SPEC® MPIM2007 Result

Supermicro

A+ Server 1025CS-TNR (AMD EPYC 9754)

SPECmpiM_peak2007 = 36.4

SPECmpiM_base2007 = 36.4

MPI2007 license:	6569	Test date:	May-2023
Test sponsor:	Supermicro	Hardware Availability:	Jun-2023
Tested by:	Supermicro	Software Availability:	Nov-2022

Results Table

Benchmark	Base							Peak
Benchmark	Ranks	Seconds	Ratio	Seconds	Ratio	Seconds	Ratio	Ranks	Seconds	Ratio	Seconds	Ratio	Seconds	Ratio
Results appear in the order in which they were run. Bold underlined text indicates a median measurement.
104.milc	128	54.9	28.5	55.2	28.4	55.3	28.3	128	54.9	28.5	55.2	28.4	55.3	28.3
107.leslie3d	128	200	26.1	198	26.4	199	26.3	128	200	26.1	198	26.4	199	26.3
113.GemsFDTD	128	173	36.5	171	36.8	171	36.8	128	173	36.5	171	36.8	171	36.8
115.fds4	128	77.3	25.3	77.1	25.3	77.2	25.3	128	77.3	25.3	77.1	25.3	77.2	25.3
121.pop2	128	119	34.5	121	34.0	121	34.2	128	119	34.5	121	34.0	121	34.2
122.tachyon	128	72.9	38.4	75.9	36.8	88.5	31.6	128	72.9	38.4	75.9	36.8	88.5	31.6
126.lammps	128	95.8	30.4	95.1	30.7	98.6	29.6	128	95.8	30.4	95.1	30.7	98.6	29.6
127.wrf2	128	136	57.4	136	57.4	136	57.3	128	136	57.4	136	57.4	136	57.3
128.GAPgeofem	128	53.3	38.8	53.5	38.6	53.5	38.6	128	53.3	38.8	53.5	38.6	53.5	38.6
129.tera_tf	128	97.2	28.5	96.6	28.7	96.4	28.7	128	97.2	28.5	96.6	28.7	96.4	28.7
130.socorro	128	60.4	63.2	60.9	62.6	60.6	63.0	128	60.4	63.2	60.9	62.6	60.6	63.0
132.zeusmp2	128	85.1	36.5	85.1	36.4	85.5	36.3	128	85.1	36.5	85.1	36.4	85.5	36.3
137.lu	128	71.3	51.6	73.6	49.9	72.0	51.1	128	71.3	51.6	73.6	49.9	72.0	51.1

Hardware Summary
Type of System:	Homogeneous
Compute Node:	A+ Server 1025CS-TNR
Total Compute Nodes:	1
Total Chips:	1
Total Cores:	128
Total Threads:	256
Total Memory:	768 GB
Base Ranks Run:	128
Minimum Peak Ranks:	128
Maximum Peak Ranks:	128

Software Summary
C Compiler:	AMD Optimizing C/C++ and Fortran Compilers (AOCC) Version 4.0.0 Build 389 for Linux
C++ Compiler:	AMD Optimizing C/C++ and Fortran Compilers (AOCC) Version 4.0.0 Build 389 for Linux
Fortran Compiler:	AMD Optimizing C/C++ and Fortran Compilers (AOCC) Version 4.0.0 Build 389 for Linux
Base Pointers:	64-bit
Peak Pointers:	64-bit
MPI Library:	Open MPI Library for Linux Version 4.1.5
Other MPI Info:	None
Pre-processors:	No
Other Software:	None

Node Description: A+ Server 1025CS-TNR

Hardware
Number of nodes:	1
Uses of the node:	compute
Vendor:	Supermicro
Model:	A+ Server 1025CS-TNR
CPU Name:	AMD EPYC 9754
CPU(s) orderable:	1 chip
Chips enabled:	1
Cores enabled:	128
Cores per chip:	128
Threads per core:	2
CPU Characteristics:	Max. Boost Clock upto 3.1GHz
CPU MHz:	2250
Primary Cache:	32 KB I + 32 KB D on chip per core
Secondary Cache:	1 MB I+D on chip per core
L3 Cache:	256 MB I+D on chip per chip 16 MB shared / 8 cores
Other Cache:	None
Memory:	768 GB (12 x 64 GB 2Rx4 PC5-4800B-R)
Disk Subsystem:	1 x 480 GB NVMe PCIe Gen4.0
Other Hardware:	None
Adapter:	None
Number of Adapters:	0
Slot Type:	None
Data Rate:	None
Ports Used:	0
Interconnect Type:	None

Software
Adapter:	None
Adapter Driver:	None
Adapter Firmware:	None
Operating System:	Ubuntu 22.04.2 LTS Kernel 5.15.0-71-generic
Local File System:	ext4
Shared File System:	None
System State:	Multi-user, run level 3
Other Software:	None

Submit Notes

The config file option 'submit' was used.
mpirun --allow-run-as-root -np $ranks $command

General Notes

Environment variables set by runspec before the start of the run:
GOMP_CPU_AFFINITY = "0-128"
KMP_BLOCKTIME = "200"
KMP_LIBRARY = "turnaround"
OMP_DYNAMIC = "false"
OMP_NESTED = "FALSE"
OMP_PLACES = "threads"
OMP_SCHEDULE = "static"
OMP_STACKSIZE = "128M"
OMP_THREAD_LIMIT = "128"

 MPI startup command:
   mpirun command was used to start MPI jobs.
 RAM configuration:
   Compute nodes have 1 x 64 GB RDIMM on each memory channel.
 BIOS settings:
   NUMA nodes per socket = NPS4
   L3 Cache as NUMA Domain = Enabled
   Determinism Control = Manual
   Determinism Slider = Power
   TDP Control = Manual
   TDP = 400
   PPT Control = Manual
   PPT = 400


 Yes: The test sponsor attests, as of date of publication,
 that CVE-2017-5754 (Meltdown) is mitigated in the system as tested and documented.
 Yes: The test sponsor attests, as of date of publication,
 that CVE-2017-5753 (Spectre variant 1) is mitigated in the system as tested and documented.
 Yes: The test sponsor attests, as of date of publication,
 that CVE-2017-5715 (Spectre variant 2) is mitigated in the system as tested and documented.

Submitted_by: Henry Lai <henryl@supermicro.com.tw>
Submitted: Tue May 16 23:42:20 EDT 2023
Submission: mpi2007-20230516-00691.sub

Base Compiler Invocation

C benchmarks:

mpicc

C++ benchmarks:

126.lammps:

mpic++

Fortran benchmarks:

mpif90

Benchmarks using both Fortran and C:

mpicc mpif90

Base Portability Flags

104.milc:	-DSPEC_MPI_LP64
115.fds4:	-DSPEC_MPI_LP64
121.pop2:	-DSPEC_MPI_CASE_FLAG -DSPEC_MPI_LP64
122.tachyon:	-DSPEC_MPI_LP64
126.lammps:	-DMPICH_IGNORE_CXX_SEEK
127.wrf2:	-DSPEC_MPI_CASE_FLAG -DSPEC_MPI_LINUX -DSPEC_MPI_LP64
128.GAPgeofem:	-DSPEC_MPI_LP64
130.socorro:	-DSPEC_MPI_LP64
132.zeusmp2:	-DSPEC_MPI_LP64

Base Other Flags

Benchmarks using both Fortran and C:

127.wrf2:

-Wno-return-type

Peak Optimization Flags

C benchmarks:

104.milc:	basepeak = yes
122.tachyon:	basepeak = yes

C++ benchmarks:

126.lammps:

basepeak = yes

Fortran benchmarks:

107.leslie3d:	basepeak = yes
113.GemsFDTD:	basepeak = yes
129.tera_tf:	basepeak = yes
137.lu:	basepeak = yes

Benchmarks using both Fortran and C:

115.fds4:	basepeak = yes
121.pop2:	basepeak = yes
127.wrf2:	basepeak = yes
128.GAPgeofem:	basepeak = yes
130.socorro:	basepeak = yes
132.zeusmp2:	basepeak = yes

The flags file that was used to format this result can be browsed at
http://www.spec.org/mpi2007/flags/amd2021_flags.20230614.html.

You can also download the XML flags source by saving the following link:
http://www.spec.org/mpi2007/flags/amd2021_flags.20230614.xml.