SPEC® MPIM2007 Result

Lenovo

ThinkSystem SR665 V3 (AMD EPYC 9654)

SPECmpiM_peak2007 = 81.8

SPECmpiM_base2007 = 81.8

MPI2007 license:	28	Test date:	Jan-2023
Test sponsor:	Lenovo	Hardware Availability:	Feb-2023
Tested by:	Lenovo	Software Availability:	Feb-2023

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	384	14.2	110	14.1	111	14.1	111	384	14.2	110	14.1	111	14.1	111
107.leslie3d	384	47.7	109	46.6	112	47.1	111	384	47.7	109	46.6	112	47.1	111
113.GemsFDTD	384	168	37.6	168	37.7	170	37.2	384	168	37.6	168	37.7	170	37.2
115.fds4	384	21.0	93.0	19.7	98.9	19.6	99.6	384	21.0	93.0	19.7	98.9	19.6	99.6
121.pop2	384	59.7	69.1	59.8	69.0	59.4	69.5	384	59.7	69.1	59.8	69.0	59.4	69.5
122.tachyon	384	27.6	101	27.5	102	27.8	101	384	27.6	101	27.5	102	27.8	101
126.lammps	384	81.7	35.7	77.9	37.4	75.4	38.6	384	81.7	35.7	77.9	37.4	75.4	38.6
127.wrf2	384	34.6	225	53.3	146	35.0	223	384	34.6	225	53.3	146	35.0	223
128.GAPgeofem	384	15.5	134	15.1	137	15.6	132	384	15.5	134	15.1	137	15.6	132
129.tera_tf	384	42.1	65.7	42.4	65.3	41.9	66.0	384	42.1	65.7	42.4	65.3	41.9	66.0
130.socorro	384	250	15.3	248	15.4	247	15.4	384	250	15.3	248	15.4	247	15.4
132.zeusmp2	384	24.6	126	24.0	129	24.1	129	384	24.6	126	24.0	129	24.1	129
137.lu	384	23.2	158	23.2	159	24.9	147	384	23.2	158	23.2	159	24.9	147

Hardware Summary
Type of System:	Homogeneous
Compute Node:	ThinkSystem SR665 V3
Total Compute Nodes:	2
Total Chips:	4
Total Cores:	192
Total Threads:	384
Total Memory:	1536 GB
Base Ranks Run:	384
Minimum Peak Ranks:	384
Maximum Peak Ranks:	384

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 4.1.1
Other MPI Info:	None
Pre-processors:	No
Other Software:	None

Node Description: ThinkSystem SR665 V3

Hardware
Number of nodes:	2
Uses of the node:	compute
Vendor:	Lenovo
Model:	ThinkSystem SR665 V3
CPU Name:	AMD EPYC 9654
CPU(s) orderable:	1, 2 chip
Chips enabled:	2
Cores enabled:	96
Cores per chip:	96
Threads per core:	2
CPU Characteristics:	Max. Boost Clock upto 3.7 GHz
CPU MHz:	2400
Primary Cache:	32 KB I + 32 KB D on chip per core
Secondary Cache:	1 MB I+D on chip per core
L3 Cache:	384 MB I+D on chip per chip 32 MB shared / 8 cores
Other Cache:	None
Memory:	768 GB (24 x 32 GB 2Rx8 PC5-4800B-R)
Disk Subsystem:	1x ThinkSystem 2.5" 5300 480GB SSD
Other Hardware:	None
Adapter:	Mellanox ConnectX-6 HDR
Number of Adapters:	1
Slot Type:	PCIe Gen5 x16
Data Rate:	200Gb
Ports Used:	1
Interconnect Type:	Mellanox ConnectX-6 HDR

Software
Adapter:	Mellanox ConnectX-6 HDR
Adapter Driver:	Mellanox
Adapter Firmware:	20.28.1002
Operating System:	Red Hat Enterprise Linux Server release 8.6, Kernel 4.18.0-372.9.1.el8.x86_64
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.

General Notes

 MPI startup command:
   mpiexec command was used to start MPI jobs.
 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.

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
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 Optimization Flags

C benchmarks:

-Ofast -flto -ffast-math -march=znver4 -lamdlibm

C++ benchmarks:

126.lammps:

-Ofast -flto -ffast-math -march=znver4 -DMPICH_IGNORE_CXX_SEEK

Fortran benchmarks:

-Ofast -flto -ffast-math -march=znver4 -funroll-loops

Benchmarks using both Fortran and C:

115.fds4:	-Ofast -flto -ffast-math -march=znver4 -funroll-loops
121.pop2:	Same as 115.fds4
127.wrf2:	Same as 115.fds4
128.GAPgeofem:	-Ofast -flto -ffast-math -march=znver4 -funroll-loops -lamdlibm
130.socorro:	Same as 115.fds4
132.zeusmp2:	Same as 115.fds4

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.html.

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