SPEC® ACCEL™ OCL Result

Copyright 2015-2019 Standard Performance Evaluation Corporation

Lenovo Global Technology

NVIDIA Tesla V100-PCIE-16GB

ThinkSystem SR650

SPECaccel_ocl_base = 10.9 

SPECaccel_ocl_peak = Not Run

ACCEL license: 28 Test date: Mar-2019
Test sponsor: Lenovo Global Technology Hardware Availability: Apr-2019
Tested by: Lenovo Global Technology Software Availability: Apr-2019
Benchmark results graph
Hardware
CPU Name: Intel Xeon Gold 6240
CPU Characteristics:
CPU MHz: 2600
CPU MHz Maximum: 3700
FPU: Integrated
CPU(s) enabled: 32 cores, 2 chips, 16 cores/chip
CPU(s) orderable: 2 chip
Primary Cache: 32 KB I + 32 KB D on chip per core
Secondary Cache: 1 MB I+D on chip per core
L3 Cache: 22 MB I+D on chip per chip
Other Cache: None
Memory: 768 GB (24 x 32 GB 2Rx4 PC4-2933Y-R)
Disk Subsystem: 1 X Lenovo 1 TB SAS 2.5" HDD (JBOD)
Other Hardware: None
Accelerator
Accel Model Name: Tesla V100
Accel Vendor: NVIDIA
Accel Name: NVIDIA Tesla V100-PCIE-16GB
Type of Accel: GPU
Accel Connection: PCIe 3.0 16x
Does Accel Use ECC: Yes
Accel Description: NVIDIA V100-PCIE-16GB
Accel Driver: NVIDIA UNIX x86_64 Kernel Module 396.26
Software
Operating System: Red Hat Enterprise Linux Server release 7.6
(Maipo)
3.10.0-957.el7.x86_64
Compiler: PGI Accelerator Server Complete, Release 18.7
File System: xfs
System State: Run level 3 (Multi User)
Other Software: CUDA 9.2 SDK

Results Table

Benchmark Base Peak
Seconds Ratio Seconds Ratio Seconds Ratio Seconds Ratio Seconds Ratio Seconds Ratio
Results appear in the order in which they were run. Bold underlined text indicates a median measurement.
101.tpacf 6.85  15.6   6.84  15.6   6.88  15.6  
103.stencil 8.03  15.6   8.00  15.6   8.00  15.6  
104.lbm 6.77  16.5   6.76  16.6   6.76  16.6  
110.fft 8.48  13.1   8.48  13.1   8.41  13.2  
112.spmv 18.3   8.01  18.3   8.02  18.3   8.03 
114.mriq 3.79  28.7   3.80  28.7   3.80  28.7  
116.histo 54.8   2.08  56.2   2.03  52.7   2.16 
117.bfs 20.9   5.60  21.0   5.58  18.6   6.31 
118.cutcp 4.71  21.0   4.69  21.1   4.68  21.2  
120.kmeans 38.3   2.61  40.0   2.50  39.3   2.54 
121.lavamd 5.84  18.7   5.79  18.8   5.85  18.6  
122.cfd 12.0   10.5   12.0   10.5   11.9   10.6  
123.nw 14.9   7.73  14.9   7.72  14.9   7.72 
124.hotspot 8.05  14.2   8.01  14.2   8.05  14.2  
125.lud 12.6   9.45  12.3   9.64  12.6   9.43 
126.ge 6.14  25.2   6.18  25.1   6.17  25.1  
127.srad 12.1   9.46  12.1   9.44  12.0   9.46 
128.heartwall 12.1   8.76  12.2   8.72  12.1   8.74 
140.bplustree 7.32  14.8   7.32  14.8   7.33  14.7  

Platform Notes

 Sysinfo program /home/ACCEL1.2/Docs/sysinfo
 $Rev: 6965 $ $Date:: 2015-04-21 #$ c05a7f14b1b1765e3fe1df68447e8a35
 running on slave5 Wed Mar 09 13:46:49 2019

 This section contains SUT (System Under Test) info as seen by
 some common utilities.  To remove or add to this section, see:
   http://www.spec.org/accel/Docs/config.html#sysinfo

 From /proc/cpuinfo
    model name : Intel(R) Xeon(R) Gold 6240 CPU @ 2.60GHz
       2 "physical id"s (chips)
       36 "processors"
    cores, siblings (Caution: counting these is hw and system dependent.  The
    following excerpts from /proc/cpuinfo might not be reliable.  Use with
    caution.)
       cpu cores : 18
       siblings  : 18
       physical 0: cores 0 1 2 3 4 8 9 10 11 16 17 18 19 20 24 25 26 27
       physical 1: cores 0 1 2 3 4 8 9 10 11 16 17 18 19 20 24 25 26 27
    cache size : 25344 KB

 From /proc/meminfo
    MemTotal:       792031348 kB
    HugePages_Total:       0
    Hugepagesize:       2048 kB

 From /etc/*release* /etc/*version*
    os-release:
       NAME="Red Hat Enterprise Linux Server"
       VERSION="7.6 (Maipo)"
       ID="rhel"
       ID_LIKE="fedora"
       VARIANT="Server"
       VARIANT_ID="server"
       VERSION_ID="7.6"
       PRETTY_NAME="Red Hat Enterprise Linux Server 7.6 (Maipo)"
    redhat-release: Red Hat Enterprise Linux Server release 7.6 (Maipo)
    system-release: Red Hat Enterprise Linux Server release 7.6 (Maipo)
    system-release-cpe: cpe:/o:redhat:enterprise_linux:7.6:ga:server

 uname -a:
    Linux slave5 3.10.0-957.el7.x86_64 #1 SMP Thu Oct 4 20:48:51 UTC 2018 x86_64
    x86_64 x86_64 GNU/Linux

 run-level 3 Mar 09 11:52

 SPEC is set to: /home/ACCEL1.2
    Filesystem     Type  Size  Used Avail Use% Mounted on
    /dev/sda3      xfs   221G   41G  180G  19% /home
 Additional information from dmidecode:

    Warning: Use caution when you interpret this section. The 'dmidecode' program
    reads system data which is "intended to allow hardware to be accurately
    determined", but the intent may not be met, as there are frequent changes to
    hardware, firmware, and the "DMTF SMBIOS" standard.

   BIOS Lenovo -[IVE135S-2.10]- 03/08/2019
   Memory:
    24x Samsung M393A4K40CB2-CVF 32 GB 2 rank 2933 MT/s

 (End of data from sysinfo program)

General Notes

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.
Run nvidia-smi -pm 1 to enable persistence mode.
-DSPEC_LOCAL_MEMORY_HEADROOM works as a portability flag for 116.histo,
but misplaced under optimization flag. The flag does not affect performance of the benchmark.

Base Runtime Environment

C benchmarks:

 OpenCL Platform: NVIDIA CUDA, OpenCL 1.2 CUDA 9.2.106   OpenCL Device #0: Tesla V100-PCIE-16GB, v 396.26 

C++ benchmarks:

 OpenCL Platform: NVIDIA CUDA, OpenCL 1.2 CUDA 9.2.106   OpenCL Device #0: Tesla V100-PCIE-16GB, v 396.26 

Base Compiler Invocation

C benchmarks:

 pgcc 

C++ benchmarks:

 pgc++ 

Base Portability Flags

116.histo:  -DSPEC_LOCAL_MEMORY_HEADROOM=2(*) 
118.cutcp:  -D__GNUC__ 

(*) Indicates a portability flag that was found in a non-portability variable.

Base Optimization Flags

C benchmarks:

110.fft:  -fast   -Mfprelaxed   -DSPEC_LOCAL_MEMORY_HEADROOM=2 
114.mriq:  Same as 110.fft 
116.histo:  -fast   -Mfprelaxed 
117.bfs:  Same as 110.fft 
118.cutcp:  Same as 110.fft 
121.lavamd:  Same as 110.fft 
124.hotspot:  Same as 110.fft 
127.srad:  Same as 110.fft 
128.heartwall:  Same as 110.fft 
140.bplustree:  Same as 110.fft 

C++ benchmarks:

 -fast   -Mfprelaxed   -DSPEC_LOCAL_MEMORY_HEADROOM=2 

Base Other Flags

C benchmarks:

 -I/usr/local/cuda-9.2/targets/x86_64-linux/include/    -L/usr/local/cuda-9.2/targets/x86_64-linux/lib   -lOpenCL 

C++ benchmarks:

 -I/usr/local/cuda-9.2/targets/x86_64-linux/include/    -L/usr/local/cuda-9.2/targets/x86_64-linux/lib   -lOpenCL 

The flags files that were used to format this result can be browsed at
https://www.spec.org/accel/flags/Lenovo-SPECACCEL1.2_Platform_Flags.html,
https://www.spec.org/accel/flags/pgi2014_flags.20190321.html.

You can also download the XML flags sources by saving the following links:
https://www.spec.org/accel/flags/Lenovo-SPECACCEL1.2_Platform_Flags.xml,
https://www.spec.org/accel/flags/pgi2014_flags.20190321.xml.