SPEChpc™ 2021 Tiny Result

Lenovo Global Technology

ThinkSystem SC777 V4(Arm Neoverse V2, Nvidia
GB200)

SPEChpc 2021_tny_base = 69.10

SPEChpc 2021_tny_peak = 69.10

hpc2021 License:	28	Test Date:	May-2026
Test Sponsor:	Lenovo Global Technology	Hardware Availability:	Oct-2026
Tested by:	Lenovo Global Technology	Software Availability:	Oct-2026

Benchmark result graphs are available in the PDF report.

Results Table

Benchmark	Base									Peak
Benchmark	Model	Ranks	Thrds/Rnk	Seconds	Ratio	Seconds	Ratio	Seconds	Ratio	Model	Ranks	Thrds/Rnk	Seconds	Ratio	Seconds	Ratio	Seconds	Ratio
SPEChpc 2021_tny_base					69.10
SPEChpc 2021_tny_peak					69.10
Results appear in the order in which they were run. Bold underlined text indicates a median measurement.
505.lbm_t	ACC	4	2	33.1	68.0	20.5	1100	20.5	1100	ACC	4	2	33.1	68.0	20.5	1100	20.5	1100
513.soma_t	ACC	4	2	43.3	85.4	43.3	85.5	42.8	86.5	ACC	4	2	43.3	85.4	43.3	85.5	42.8	86.5
518.tealeaf_t	ACC	4	2	21.9	75.5	22.0	75.0	22.0	75.1	ACC	4	2	21.9	75.5	22.0	75.0	22.0	75.1
519.clvleaf_t	ACC	4	2	18.6	88.8	18.6	88.9	18.6	88.8	ACC	4	2	18.6	88.8	18.6	88.9	18.6	88.8
521.miniswp_t	ACC	4	2	34.2	46.8	27.4	58.3	27.4	58.4	ACC	4	2	34.2	46.8	27.4	58.3	27.4	58.4
528.pot3d_t	ACC	4	2	22.7	93.8	22.5	94.4	22.5	94.5	ACC	4	2	22.7	93.8	22.5	94.4	22.5	94.5
532.sph_exa_t	ACC	4	2	76.4	25.5	76.4	25.5	76.0	25.7	ACC	4	2	76.4	25.5	76.4	25.5	76.0	25.7
534.hpgmgfv_t	ACC	4	2	47.0	25.0	46.8	25.1	47.0	25.0	ACC	4	2	47.0	25.0	46.8	25.1	47.0	25.0
535.weather_t	ACC	4	2	19.9	1620	19.9	1620	19.9	1620	ACC	4	2	19.9	1620	19.9	1620	19.9	1620

Hardware Summary
Type of System:	Homogeneous Cluster
Compute Node:	ThinkSystem SC777 V4
Compute Nodes Used:	1
Total Chips:	2
Total Cores:	144
Total Threads:	144
Total Memory:	960 GB
Total Accelerators:	4
Max. Peak Threads:	2

Software Summary
Compiler:	NVIDIA HPC SDK 25.11
MPI Library:	Open MPI 4.1.9a1
Other MPI Info:	None
Base Parallel Model:	ACC
Base Ranks Run:	4
Base Threads Run:	2
Peak Parallel Models:	ACC
Minimum Peak Ranks:	4
Maximum Peak Ranks:	4
Max. Peak Threads:	2
Min. Peak Threads:	2

Node Description: ThinkSystem SC777 V4

Hardware
Number of nodes:	1
Uses of the node:	compute
Vendor:	Lenovo Global Technology
Model:	ThinkSystem SC777 V4
CPU Name:	NVIDIA Grace Neoverse V2 CPU
CPU(s) orderable:	2 chips
Chips enabled:	2
Cores enabled:	144
Cores per chip:	72
Threads per core:	1
CPU Characteristics:	Grace CPU @3.3GHz
CPU MHz:	3300
Primary Cache:	64 KB I + 64 KB D on chip per core
Secondary Cache:	1 MB I+D on chip per core
L3 Cache:	117 MB I+D on chip per chip
Other Cache:	None
Memory:	960 GB (2x 480 GB LPDDR5X)
Disk Subsystem:	1x ThinkSystem 2.5" 5300 480GB SSD
Other Hardware:	None
Accel Count:	4
Accel Model:	NVIDIA GB200
Accel Vendor:	NVIDIA Corporation
Accel Type:	GPU
Accel Connection:	NVLink-C2C
Accel ECC enabled:	Yes
Accel Description:	NVIDIA Grace Blackwell GB200
Adapter:	N/A
Number of Adapters:	1
Slot Type:	N/A
Data Rate:	N/A
Ports Used:	0
Interconnect Type:	N/A

Software
Accelerator Driver:	610.43.02
Adapter:	N/A
Adapter Driver:	N/A
Adapter Firmware:	N/A
Operating System:	Ubuntu 24.04.4 LTS, Kernel 6.17.0-1018-nvidia-64k
Local File System:	xfs
Shared File System:	XFS
System State:	Multi-user, run level 3
Other Software:	None

Submit Notes

The config file option 'submit' was used.

General Notes

Environment variables set by runhpc before the start of the run:
UCX_MEMTYPE_CACHE = "n"
UCX_NET_DEVICES = "all"
UCX_TLS = "self,sm,cuda_copy,tcp"

Compiler Version Notes

==============================================================================
 CC  505.lbm_t(base) 513.soma_t(base) 518.tealeaf_t(base) 521.miniswp_t(base)
      534.hpgmgfv_t(base)
------------------------------------------------------------------------------
nvc 25.11-0 linuxarm64 target on aarch64 Linux -tp neoverse-v2 
NVIDIA Compilers and Tools
Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES.  All rights reserved.
------------------------------------------------------------------------------

==============================================================================
 CXXC 532.sph_exa_t(base)
------------------------------------------------------------------------------
nvc++ 25.11-0 linuxarm64 target on aarch64 Linux -tp neoverse-v2 
NVIDIA Compilers and Tools
Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES.  All rights reserved.
------------------------------------------------------------------------------

==============================================================================
 FC  519.clvleaf_t(base) 528.pot3d_t(base) 535.weather_t(base)
------------------------------------------------------------------------------
nvfortran 25.11-0 linuxarm64 target on aarch64 Linux -tp neoverse-v2 
NVIDIA Compilers and Tools
Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES.  All rights reserved.
------------------------------------------------------------------------------

Base Compiler Invocation

C benchmarks:

mpicc

C++ benchmarks:

mpicxx

Fortran benchmarks:

mpif90

Base Portability Flags

505.lbm_t:	-DSPEC_OPENACC_NO_SELF
532.sph_exa_t:	--c++17

Base Other Flags

C benchmarks (except as noted below):

	-Ispecmpitime -w
521.miniswp_t:	-Ispecmpitime/ -w
534.hpgmgfv_t:	-Ispecmpitime -w

C++ benchmarks:

-Ispecmpitime -w

Fortran benchmarks (except as noted below):

	-w
519.clvleaf_t:	-Ispecmpitime -w

Peak Optimization Flags

C benchmarks:

505.lbm_t:	basepeak = yes
513.soma_t:	basepeak = yes
518.tealeaf_t:	basepeak = yes
521.miniswp_t:	basepeak = yes
534.hpgmgfv_t:	basepeak = yes

C++ benchmarks:

532.sph_exa_t:

basepeak = yes

Fortran benchmarks:

519.clvleaf_t:	basepeak = yes
528.pot3d_t:	basepeak = yes
535.weather_t:	basepeak = yes

The flags file that was used to format this result can be browsed at
http://www.spec.org/hpc2021/flags/nv2021_flags_v1.0.3.2026-09-16.html.

You can also download the XML flags source by saving the following link:
http://www.spec.org/hpc2021/flags/nv2021_flags_v1.0.3.2026-09-16.xml.