SPEC(R) ACCEL_OCL Summary SGI NVIDIA Tesla K40m SGI Rackable C2110G-RP5 (Intel Xeon E5-2697 v2, 2.70 GHz) Thu Feb 27 21:17:16 2014 ACCEL License: 14 Test date: Feb-2014 Test sponsor: SGI Hardware availability: Nov-2013 Tested by: SGI Software availability: Nov-2013 Base Base Base Peak Peak Peak Benchmarks Ref. Run Time Ratio Ref. Run Time Ratio -------------- ------ --------- --------- ------ --------- --------- 101.tpacf 107 70.5 1.52 S 101.tpacf 107 70.1 1.53 * 101.tpacf 107 70.1 1.53 S 103.stencil 125 57.5 2.17 S 103.stencil 125 57.5 2.17 S 103.stencil 125 57.5 2.17 * 104.lbm 112 40.8 2.75 S 104.lbm 112 40.8 2.74 * 104.lbm 112 40.9 2.74 S 110.fft 111 54.3 2.04 S 110.fft 111 54.3 2.04 S 110.fft 111 54.3 2.04 * 112.spmv 147 71.9 2.04 S 112.spmv 147 71.9 2.04 * 112.spmv 147 71.9 2.05 S 114.mriq 109 30.4 3.58 * 114.mriq 109 30.4 3.58 S 114.mriq 109 30.4 3.59 S 116.histo 114 83.9 1.36 S 116.histo 114 83.9 1.36 * 116.histo 114 83.9 1.36 S 117.bfs 117 66.2 1.77 S 117.bfs 117 66.2 1.77 S 117.bfs 117 66.2 1.77 * 118.cutcp 99 34.4 2.88 * 118.cutcp 99 34.4 2.88 S 118.cutcp 99 34.3 2.88 S 120.kmeans 100 89.8 1.11 S 120.kmeans 100 89.9 1.11 * 120.kmeans 100 89.9 1.11 S 121.lavamd 109 65.2 1.67 S 121.lavamd 109 65.7 1.66 * 121.lavamd 109 65.7 1.66 S 122.cfd 126 56.2 2.24 S 122.cfd 126 56.1 2.25 S 122.cfd 126 56.1 2.24 * 123.nw 115 70.2 1.64 S 123.nw 115 70.2 1.64 * 123.nw 115 70.2 1.64 S 124.hotspot 114 39.9 2.85 S 124.hotspot 114 39.9 2.86 * 124.hotspot 114 39.9 2.86 S 125.lud 119 82.8 1.44 S 125.lud 119 83.4 1.43 S 125.lud 119 83.4 1.43 * 126.ge 155 43.4 3.57 S 126.ge 155 43.4 3.57 S 126.ge 155 43.4 3.57 * 127.srad 114 59.8 1.91 S 127.srad 114 59.8 1.91 * 127.srad 114 59.8 1.91 S 128.heartwall 106 100 1.06 S 128.heartwall 106 101 1.05 S 128.heartwall 106 100 1.05 * 140.bplustree 108 86.9 1.24 S 140.bplustree 108 86.9 1.24 * 140.bplustree 108 87.0 1.24 S ============================================================================== 101.tpacf 107 70.1 1.53 * 103.stencil 125 57.5 2.17 * 104.lbm 112 40.8 2.74 * 110.fft 111 54.3 2.04 * 112.spmv 147 71.9 2.04 * 114.mriq 109 30.4 3.58 * 116.histo 114 83.9 1.36 * 117.bfs 117 66.2 1.77 * 118.cutcp 99 34.4 2.88 * 120.kmeans 100 89.9 1.11 * 121.lavamd 109 65.7 1.66 * 122.cfd 126 56.1 2.24 * 123.nw 115 70.2 1.64 * 124.hotspot 114 39.9 2.86 * 125.lud 119 83.4 1.43 * 126.ge 155 43.4 3.57 * 127.srad 114 59.8 1.91 * 128.heartwall 106 100 1.05 * 140.bplustree 108 86.9 1.24 * SPECaccel_ocl_base 1.92 SPECaccel_ocl_peak Not Run 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 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 SPEC is a registered trademark of the Standard Performance Evaluation Corporation. All other brand and product names appearing in this result are trademarks or registered trademarks of their respective holders. ----------------------------------------------------------------------------------- For questions about this result, please contact the tester. For other inquiries, please contact webmaster@spec.org. Copyright 2014-2015 Standard Performance Evaluation Corporation Tested with SPEC ACCEL v39. Report generated on Tue Mar 3 14:21:25 2015 by ACCEL ASCII formatter v1212. Originally published on 17 March 2014.