SPEChpc™ 2021 Medium Result

Copyright 2021-2023 Standard Performance Evaluation Corporation

Lenovo Global Technology

ThinkSystem SR665 V3 (AMD EPYC 9654)

SPEChpc 2021_med_base = 0.482

SPEChpc 2021_med_peak = 0.486

hpc2021 License: 28 Test Date: Jan-2023
Test Sponsor: Lenovo Global Technology Hardware Availability: Nov-2022
Tested by: Lenovo Global Technology Software Availability: Nov-2022

Benchmark result graphs are available in the PDF report.

Results Table

Benchmark Base Peak
Model Ranks Thrds/Rnk Seconds Ratio Seconds Ratio Seconds Ratio Model Ranks Thrds/Rnk Seconds Ratio Seconds Ratio Seconds Ratio
SPEChpc 2021_med_base 0.482
SPEChpc 2021_med_peak 0.486
Results appear in the order in which they were run. Bold underlined text indicates a median measurement.
705.lbm_m OMP 144 8 1144 1.070 1162 1.050 1176 1.040 OMP 144 8 1144 1.070 1162 1.050 1176 1.040
718.tealeaf_m OMP 144 8 4267 0.316 4282 0.315 4167 0.324 OMP 288 4 4116 0.328 4082 0.331 4098 0.329
719.clvleaf_m OMP 144 8 4612 0.401 4603 0.402 4629 0.400 OMP 288 4 4537 0.408 4572 0.405 4582 0.404
728.pot3d_m OMP 144 8 5531 0.334 5500 0.336 5560 0.333 OMP 288 4 5515 0.335 5476 0.338 5477 0.338
734.hpgmgfv_m OMP 144 8 2508 0.399 2441 0.410 2451 0.408 OMP 144 8 2508 0.399 2441 0.410 2451 0.408
735.weather_m OMP 144 8 3530 0.680 3506 0.685 3449 0.696 OMP 144 8 3530 0.680 3506 0.685 3449 0.696
Hardware Summary
Type of System: Homogenous Cluster
Compute Node: ThinkSystem SR665 V3
Interconnect: Nvidia Mellanox ConnectX-6 HDR
Compute Nodes Used: 6
Total Chips: 12
Total Cores: 1152
Total Threads: 2304
Total Memory: 9 TB
Max. Peak Threads: 8
Software Summary
Compiler: Intel oneAPI Compiler 2022.1.0
MPI Library: Intel MPI Library for Linux OS, Build 20220227
Base Parallel Model: OMP
Base Ranks Run: 144
Base Threads Run: 8
Peak Parallel Models: OMP
Minimum Peak Ranks: 144
Maximum Peak Ranks: 288
Max. Peak Threads: 8
Min. Peak Threads: 4

Node Description: ThinkSystem SR665 V3

Hardware
Number of nodes: 6
Uses of the node: Compute
Vendor: Lenovo Global Technology
Model: ThinkSystem SR665 V3
CPU Name: AMD EPYC 9654
CPU(s) orderable: 1,2 chips
Chips enabled: 2
Cores enabled: 192
Cores per chip: 96
Threads per core: 2
CPU Characteristics: Max Boost Clock up to 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: 1536 GB (24 x 64 GB 2Rx4 PC5-4800B-R)
Disk Subsystem: 1x ThinkSystem 2.5" 5300 480GB SSD
Other Hardware: None
Adapter: Nvidia Mellanox ConnectX-6 HDR
Number of Adapters: 1
Slot Type: PCI-Express 4.0 x16
Data Rate: 200 Gb/s
Ports Used: 1
Interconnect Type: ConnectX-6 HDR
Software
Adapter: Nvidia Mellanox ConnectX-6 HDR
Adapter Driver: 5.7-1.0.2
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: xfs
Shared File System: None
System State: Multi-user, run level 3
Other Software: None

Interconnect Description: Nvidia Mellanox ConnectX-6 HDR

Hardware
Vendor: Nvidia
Model: Nvidia Mellanox ConnectX-6 HDR
Switch Model: QM8700
Number of Switches: 1
Number of Ports: 40
Data Rate: 200 Gb/s
Firmware: 3.9.0606
Topology: Mesh
Primary Use: MPI Traffic, NFS Access
Software

Submit Notes

The config file option 'submit' was used.
submit = mpiexec -hostfile $[top]/6nodes -np ranks -genv OMP_NUM_THREADS=$threads -ppn %{NRNK} $command

Compiler Version Notes

==============================================================================
 FC  719.clvleaf_m(base, peak) 728.pot3d_m(base, peak) 735.weather_m(base,
      peak)
------------------------------------------------------------------------------
Intel(R) Fortran Compiler for applications running on Intel(R) 64, Version
  2022.1.0 Build 20220316
Copyright (C) 1985-2022 Intel Corporation. All rights reserved.
ifx: command line error: no files specified; for help type "ifx -help"
------------------------------------------------------------------------------

==============================================================================
 CC  705.lbm_m(base, peak) 718.tealeaf_m(base, peak) 734.hpgmgfv_m(base,
      peak)
------------------------------------------------------------------------------
Intel(R) oneAPI DPC++/C++ Compiler for applications running on Intel(R) 64,
  Version 2022.1.0 Build 20220316
Copyright (C) 1985-2022 Intel Corporation. All rights reserved.
clang: warning: -Z-reserved-lib-stdc++: 'linker' input unused
  [-Wunused-command-line-argument]
------------------------------------------------------------------------------

Base Compiler Invocation

C benchmarks:

 mpiicc -cc=icx 

Fortran benchmarks:

 mpiifort -fc=ifx 

Base Portability Flags

705.lbm_m:  -lstdc++ 
718.tealeaf_m:  -lstdc++ 
719.clvleaf_m:  -lstdc++ 
728.pot3d_m:  -lstdc++ 
734.hpgmgfv_m:  -lstdc++ 
735.weather_m:  -lstdc++ 

Base Optimization Flags

C benchmarks:

 -Ofast   -mprefer-vector-width=512   -march=core-avx2   -ipo   -fiopenmp   -ansi-alias 

Fortran benchmarks:

 -Ofast   -mprefer-vector-width=512   -march=core-avx2   -ipo   -fiopenmp   -nostandard-realloc-lhs   -align array64byte 

Base Other Flags

C benchmarks (except as noted below):

 -Ispecmpitime 
734.hpgmgfv_m:  -Ispecmpitime  

Fortran benchmarks:

719.clvleaf_m:  -Ispecmpitime 

Peak Compiler Invocation

C benchmarks:

 mpiicc -cc=icx 

Fortran benchmarks:

 mpiifort -fc=ifx 

Peak Portability Flags

Same as Base Portability Flags

Peak Optimization Flags

C benchmarks:

705.lbm_m:  basepeak = yes 
718.tealeaf_m:  -Ofast   -mprefer-vector-width=512   -march=core-avx2   -ipo   -fiopenmp   -ansi-alias 
734.hpgmgfv_m:  basepeak = yes 

Fortran benchmarks:

719.clvleaf_m:  -Ofast   -mprefer-vector-width=512   -march=core-avx2   -ipo   -fiopenmp   -nostandard-realloc-lhs   -align array64byte 
728.pot3d_m:  Same as 719.clvleaf_m 
735.weather_m:  basepeak = yes 

Peak Other Flags

C benchmarks (except as noted below):

 -Ispecmpitime 
734.hpgmgfv_m:  -Ispecmpitime  

Fortran benchmarks:

719.clvleaf_m:  -Ispecmpitime 

The flags file that was used to format this result can be browsed at
http://www.spec.org/hpc2021/flags/Intel_compiler_flags.2022-11-10.html.

You can also download the XML flags source by saving the following link:
http://www.spec.org/hpc2021/flags/Intel_compiler_flags.2022-11-10.xml.