SPEC® ACCEL_OCL Result

Copyright 2014-2015 Standard Performance Evaluation Corporation

SGI

NVIDIA Tesla K40m

SGI Rackable C2110G-RP5 (Intel Xeon E5-2697
v2, 2.70 GHz)

SPECaccel_ocl_base = 1.92

SPECaccel_ocl_peak = Not Run

ACCEL license: 14 Test date: Feb-2014
Test sponsor: SGI Hardware Availability: Nov-2013
Tested by: SGI Software Availability: Nov-2013
Benchmark results graph
Hardware
CPU Name: Intel Xeon E5-2697 v2
CPU Characteristics: Twelve Core, 2.7 GHz, 8.0 GT/s QPI
CPU MHz: 2700
CPU MHz Maximum: 3500
FPU: Integrated
CPU(s) enabled: 24 cores, 2 chips, 12 cores/chip, 2 threads/core
CPU(s) orderable: 1-2 chips
Primary Cache: 32 KB I + 32 KB D on chip per core
Secondary Cache: 256 KB I+D on chip per core
L3 Cache: 30 MB I+D on chip per chip, 30 MB shared / 12
cores
Other Cache: None
Memory: 128 GB (8 x 16 GB 2Rx4 PC3-14900R-13, ECC)
Disk Subsystem: 15 TB 3x 6+2 RAID6, 24 x 900 GB SAS (Western
Digital WD9001BKHG02D22, 10K RPM)
Other Hardware: None
Accelerator
Accel Model Name: Tesla K40m
Accel Vendor: NVIDIA
Accel Name: NVIDIA Tesla K40m
Type of Accel: GPU
Accel Connection: PCIe 3.0 16x
Does Accel Use ECC: Yes
Accel Description: Nvidia Tesla K40m, 12GB GDDR5 RAM, 745MHz, 2880
CUDA Cores.
Accel Driver: NVIDIA UNIX x86_64 Kernel Module 331.20
Software
Operating System: Red Hat Enterprise Linux Server release 6.4
(Santiago)
Kernel 2.6.32-358.el6.x86_64
Compiler: Intel c/c++/Fortran Compiler XE, Version
14.0.1.106
File System: NFSv3 IPoIB
System State: Run level 5 (Multi-users)
Other Software: CUDA 5.5

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 70.5  1.52  70.1  1.53  70.1  1.53 
103.stencil 57.5  2.17  57.5  2.17  57.5  2.17 
104.lbm 40.8  2.75  40.8  2.74  40.9  2.74 
110.fft 54.3  2.04  54.3  2.04  54.3  2.04 
112.spmv 71.9  2.04  71.9  2.04  71.9  2.05 
114.mriq 30.4  3.58  30.4  3.58  30.4  3.59 
116.histo 83.9  1.36  83.9  1.36  83.9  1.36 
117.bfs 66.2  1.77  66.2  1.77  66.2  1.77 
118.cutcp 34.4  2.88  34.4  2.88  34.3  2.88 
120.kmeans 89.8  1.11  89.9  1.11  89.9  1.11 
121.lavamd 65.2  1.67  65.7  1.66  65.7  1.66 
122.cfd 56.2  2.24  56.1  2.25  56.1  2.24 
123.nw 70.2  1.64  70.2  1.64  70.2  1.64 
124.hotspot 39.9  2.85  39.9  2.86  39.9  2.86 
125.lud 82.8  1.44  83.4  1.43  83.4  1.43 
126.ge 43.4  3.57  43.4  3.57  43.4  3.57 
127.srad 59.8  1.91  59.8  1.91  59.8  1.91 
128.heartwall 100    1.06  101    1.05  100    1.05 
140.bplustree 86.9  1.24  86.9  1.24  87.0  1.24 

Operating System Notes

Transparent Hugepage: disabled
  Transparent Hugepage is disabled by
  echo never > /sys/kernel/mm/redhat_transparent_hugepage/enabled

Platform Notes

 Sysinfo program /store/hfeng/Accel/kit-39/Docs/sysinfo
 $Rev: 6874 $ $Date:: 2013-11-20 #$ 0953404ef7e75a5f9bbb534c6de3f831
 running on n009 Thu Feb 27 20:17:18 2014

 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) CPU E5-2697 v2 @ 2.70GHz
       2 "physical id"s (chips)
       48 "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 : 12
       siblings  : 24
       physical 0: cores 0 1 2 3 4 5 8 9 10 11 12 13
       physical 1: cores 0 1 2 3 4 5 8 9 10 11 12 13
    cache size : 30720 KB

 From /proc/meminfo
    MemTotal:       132131352 kB
    HugePages_Total:       0
    Hugepagesize:       2048 kB

 /usr/bin/lsb_release -d
    Red Hat Enterprise Linux Server release 6.4 (Santiago)

 From /etc/*release* /etc/*version*
    redhat-release: Red Hat Enterprise Linux Server release 6.4 (Santiago)
    sgi-accelerate-release: SGI Accelerate 1.6, Build 708r13.rhel6-1304102350
    sgi-foundation-release: SGI Foundation Software 2.8, Build
    708r13.rhel6-1304102350
    sgi-mpi-release: SGI MPI 1.6, Build 708r13.rhel6-1304102350
    sgi-release: SGI Performance Suite 1.6, Build 708r13.rhel6-1304102350
    sgi-upc-release: SGI UPC 1.6, Build 708r13.rhel6-1304102350
    sgi-xfs_xvm-release: SGI XFS-XVM 3.0, Build 707rp29.rhel6-1306102001
    system-release: Red Hat Enterprise Linux Server release 6.4 (Santiago)
    system-release-cpe: cpe:/o:redhat:enterprise_linux:6server:ga:server

 uname -a:
    Linux n009 2.6.32-358.el6.x86_64 #1 SMP Tue Jan 29 11:47:41 EST 2013 x86_64
    x86_64 x86_64 GNU/Linux

 run-level 5 Feb 18 14:36

 SPEC is set to: /store/hfeng/Accel/kit-39
    Filesystem    Type    Size  Used Avail Use% Mounted on
    service1-ib:/nas
                   nfs     15T  1.3T   14T   9% /nas

 Cannot run dmidecode; consider saying 'chmod +s /usr/sbin/dmidecode'

 (End of data from sysinfo program)

Base Runtime Environment

C benchmarks:

 OpenCL Platform: NVIDIA CUDA, OpenCL 1.1 CUDA 6.0.1   OpenCL Device #0: Tesla K40m, v 331.20 

C++ benchmarks:

 OpenCL Platform: NVIDIA CUDA, OpenCL 1.1 CUDA 6.0.1   OpenCL Device #0: Tesla K40m, v 331.20 

Base Compiler Invocation

C benchmarks:

 icc 

C++ benchmarks:

 icpc 

Base Optimization Flags

C benchmarks:

 -O3 

C++ benchmarks:

 -O3 

Base Other Flags

C benchmarks:

 -I/usr/local/cuda/include   -L/usr/local/cuda/lib64   -lOpenCL 

C++ benchmarks:

 -I/usr/local/cuda/include   -L/usr/local/cuda/lib64   -lOpenCL 

The flags file that was used to format this result can be browsed at
http://www.spec.org/accel/flags/SGI-Accel-OpenCL.html.

You can also download the XML flags source by saving the following link:
http://www.spec.org/accel/flags/SGI-Accel-OpenCL.xml.