SPEC(R) ACCEL(TM) OCL Summary Asus NVIDIA Tesla K80 ASUS ESC4000 G3 Series Test Sponsor: HZDR Thu Aug 24 07:14:24 2017 ACCEL License: 65A Test date: Aug-2017 Test sponsor: HZDR Hardware availability: Nov-2014 Tested by: HZDR Software availability: Aug-2016 Base Base Base Peak Peak Peak Benchmarks Ref. Run Time Ratio Ref. Run Time Ratio -------------- ------ --------- --------- ------ --------- --------- 101.tpacf 107 39.7 2.69 * 107 38.9 2.75 S 101.tpacf 107 39.8 2.69 S 107 39.0 2.74 * 101.tpacf 107 39.6 2.70 S 107 39.1 2.74 S 103.stencil 125 57.8 2.16 S 125 57.8 2.16 S 103.stencil 125 57.9 2.16 * 125 57.9 2.16 * 103.stencil 125 58.0 2.16 S 125 58.0 2.16 S 104.lbm 112 41.0 2.73 S 112 30.9 3.62 * 104.lbm 112 41.1 2.73 S 112 30.9 3.62 S 104.lbm 112 41.0 2.73 * 112 31.0 3.62 S 110.fft 111 34.8 3.19 * 111 34.8 3.19 * 110.fft 111 34.7 3.20 S 111 34.7 3.20 S 110.fft 111 34.9 3.18 S 111 34.9 3.18 S 112.spmv 147 70.4 2.09 S 147 70.2 2.09 S 112.spmv 147 70.3 2.09 S 147 70.5 2.08 S 112.spmv 147 70.4 2.09 * 147 70.3 2.09 * 114.mriq 109 18.4 5.93 * 109 18.4 5.93 * 114.mriq 109 18.4 5.93 S 109 18.4 5.93 S 114.mriq 109 18.4 5.94 S 109 18.4 5.94 S 116.histo 114 92.6 1.23 S 114 92.6 1.23 S 116.histo 114 65.7 1.74 * 114 65.7 1.74 * 116.histo 114 59.3 1.92 S 114 59.3 1.92 S 117.bfs 117 48.9 2.39 S 117 47.6 2.46 S 117.bfs 117 46.9 2.50 * 117 43.1 2.71 S 117.bfs 117 46.9 2.50 S 117 43.5 2.69 * 118.cutcp 99 29.3 3.38 * 99 29.3 3.38 * 118.cutcp 99 29.3 3.38 S 99 29.3 3.38 S 118.cutcp 99 29.3 3.38 S 99 29.3 3.38 S 120.kmeans 100 60.7 1.65 * 100 56.3 1.78 S 120.kmeans 100 61.0 1.64 S 100 55.8 1.79 S 120.kmeans 100 60.0 1.67 S 100 56.2 1.78 * 121.lavamd 109 14.1 7.73 S 109 14.1 7.73 S 121.lavamd 109 14.1 7.74 * 109 14.1 7.74 * 121.lavamd 109 13.2 8.27 S 109 13.2 8.27 S 122.cfd 126 55.6 2.26 * 126 55.9 2.25 * 122.cfd 126 54.8 2.30 S 126 56.6 2.23 S 122.cfd 126 56.2 2.24 S 126 55.9 2.25 S 123.nw 115 62.8 1.83 S 115 62.8 1.83 S 123.nw 115 62.8 1.83 * 115 62.8 1.83 * 123.nw 115 62.9 1.83 S 115 62.9 1.83 S 124.hotspot 114 38.6 2.95 S 114 38.6 2.95 S 124.hotspot 114 38.5 2.96 * 114 38.5 2.96 * 124.hotspot 114 38.4 2.97 S 114 38.4 2.97 S 125.lud 119 82.1 1.45 S 119 68.4 1.74 S 125.lud 119 83.7 1.42 S 119 68.5 1.74 * 125.lud 119 83.6 1.42 * 119 68.5 1.74 S 126.ge 155 37.4 4.15 S 155 7.34 21.1 S 126.ge 155 37.4 4.15 S 155 7.31 21.2 * 126.ge 155 37.4 4.15 * 155 7.23 21.4 S 127.srad 114 60.6 1.88 S 114 60.6 1.88 S 127.srad 114 60.6 1.88 * 114 60.6 1.88 * 127.srad 114 60.4 1.89 S 114 60.4 1.89 S 128.heartwall 106 127 0.836 * 106 127 0.836 * 128.heartwall 106 127 0.837 S 106 127 0.837 S 128.heartwall 106 127 0.836 S 106 127 0.836 S 140.bplustree 108 91.0 1.19 S 108 91.0 1.19 S 140.bplustree 108 91.0 1.19 * 108 91.0 1.19 * 140.bplustree 108 91.0 1.19 S 108 91.0 1.19 S ============================================================================== 101.tpacf 107 39.7 2.69 * 107 39.0 2.74 * 103.stencil 125 57.9 2.16 * 125 57.9 2.16 * 104.lbm 112 41.0 2.73 * 112 30.9 3.62 * 110.fft 111 34.8 3.19 * 111 34.8 3.19 * 112.spmv 147 70.4 2.09 * 147 70.3 2.09 * 114.mriq 109 18.4 5.93 * 109 18.4 5.93 * 116.histo 114 65.7 1.74 * 114 65.7 1.74 * 117.bfs 117 46.9 2.50 * 117 43.5 2.69 * 118.cutcp 99 29.3 3.38 * 99 29.3 3.38 * 120.kmeans 100 60.7 1.65 * 100 56.2 1.78 * 121.lavamd 109 14.1 7.74 * 109 14.1 7.74 * 122.cfd 126 55.6 2.26 * 126 55.9 2.25 * 123.nw 115 62.8 1.83 * 115 62.8 1.83 * 124.hotspot 114 38.5 2.96 * 114 38.5 2.96 * 125.lud 119 83.6 1.42 * 119 68.5 1.74 * 126.ge 155 37.4 4.15 * 155 7.31 21.2 * 127.srad 114 60.6 1.88 * 114 60.6 1.88 * 128.heartwall 106 127 0.836 * 106 127 0.836 * 140.bplustree 108 91.0 1.19 * 108 91.0 1.19 * SPECaccel_ocl_base 2.39 SPECaccel_ocl_peak 2.70 HARDWARE -------- CPU Name: Intel Xeon E5-2630 v3 CPU Characteristics: Intel Turbo Boost Technology up to 3.20 GHz AVX clock: 2100 MHz CPU MHz: 2400 CPU MHz Maximum: 3200 FPU: Integrated CPU(s) enabled: 16 cores, 2 chips, 8 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: 20 MB I+D on chip per chip Other Cache: None Memory: 256 GB (16 x 16 GB 2Rx4 PC4-2133P-E, running at 1866 MHz) Disk Subsystem: 128 GB Samsung SSD 850 PRO Other Hardware: None ACCELERATOR ----------- Accel Model Name: Tesla K80 Accel Vendor: NVIDIA Accel Name: NVIDIA Tesla K80 Type of Accel: GPU Accel Connection: PCIe 3.0 x16 Does Accel Use ECC: yes Accel Description: NVIDIA Tesla K80, 2496 CUDA cores, 875 MHz 12 GB GDDR5 RAM (Kepler Generation) Accel Driver: NVIDIA UNIX x86_64 Kernel Module 367.48 SOFTWARE -------- Operating System: Ubuntu 14.04.5 LTS 4.4.0-38-generic Compiler: GNU Compiler C/C++ Version 6.2.0 File System: ext3 System State: Run level 5 (user-level) Other Software: NVIDIA Cuda SDK 7.0, driver version 367.48 Platform Notes -------------- Sysinfo program /tmp/spec/1.2/Docs/sysinfo $Rev: 6965 $ $Date:: 2015-04-21 #$ c05a7f14b1b1765e3fe1df68447e8a35 running on kepler020 Thu Aug 24 13:14:25 2017 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 E5-2630 v3 @ 2.40GHz 2 "physical id"s (chips) 32 "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 : 8 siblings : 16 physical 0: cores 0 1 2 3 4 5 6 7 physical 1: cores 0 1 2 3 4 5 6 7 cache size : 20480 KB From /proc/meminfo MemTotal: 264058968 kB HugePages_Total: 0 Hugepagesize: 2048 kB /usr/bin/lsb_release -d Ubuntu 14.04.5 LTS From /etc/*release* /etc/*version* debian_version: jessie/sid os-release: NAME="Ubuntu" VERSION="14.04.5 LTS, Trusty Tahr" ID=ubuntu ID_LIKE=debian PRETTY_NAME="Ubuntu 14.04.5 LTS" VERSION_ID="14.04" HOME_URL="http://www.ubuntu.com/" SUPPORT_URL="http://help.ubuntu.com/" rh-release: Red Hat Enterprise Linux Server release 7.2 (Maipo) uname -a: Linux kepler020 4.4.0-38-generic #57~14.04.1-Ubuntu SMP Tue Sep 6 17:20:43 UTC 2016 x86_64 x86_64 x86_64 GNU/Linux run-level 5 Apr 10 07:27 SPEC is set to: /tmp/spec/1.2 Filesystem Type Size Used Avail Use% Mounted on /dev/sda1 ext3 44G 14G 28G 34% / 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 1.2 CUDA 8.0.44 OpenCL Device #0: Tesla K80, v 367.48 C++ benchmarks: OpenCL Platform: NVIDIA CUDA, OpenCL 1.2 CUDA 8.0.44 OpenCL Device #0: Tesla K80, v 367.48 Base Compiler Invocation ------------------------ C benchmarks: gcc C++ benchmarks: g++ Base Portability Flags ---------------------- 116.histo: -DSPEC_LOCAL_MEMORY_HEADROOM=2 122.cfd: -std=gnu++98 Base Optimization Flags ----------------------- C benchmarks: -O2 -march=haswell -I/opt/pkg/devel/cuda/7.0/include -L/opt/pkg/devel/cuda/7.0/libb64 -lcuda -lOpenCL C++ benchmarks: -O2 -march=haswell -I/opt/pkg/devel/cuda/7.0/include -L/opt/pkg/devel/cuda/7.0/libb64 -lcuda -lOpenCL Peak Runtime Environment ------------------------ C benchmarks: OpenCL Platform: NVIDIA CUDA, OpenCL 1.2 CUDA 8.0.44 OpenCL Device #0: Tesla K80, v 367.48 C++ benchmarks: OpenCL Platform: NVIDIA CUDA, OpenCL 1.2 CUDA 8.0.44 OpenCL Device #0: Tesla K80, v 367.48 Peak Compiler Invocation ------------------------ C benchmarks: gcc C++ benchmarks: g++ Peak Portability Flags ---------------------- 116.histo: -DSPEC_LOCAL_MEMORY_HEADROOM=2 122.cfd: -std=gnu++98 Peak Optimization Flags ----------------------- C benchmarks: 110.fft: basepeak = yes 114.mriq: basepeak = yes 116.histo: basepeak = yes 117.bfs: -O2 -march=haswell -DSPEC_ACCEL_WG_SIZE_0_0=64 -DSPEC_ACCEL_WG_SIZE_1_0=64 -I/opt/pkg/devel/cuda/7.0/include -L/opt/pkg/devel/cuda/7.0/libb64 -lcuda -lOpenCL 118.cutcp: basepeak = yes 121.lavamd: basepeak = yes 124.hotspot: basepeak = yes 127.srad: basepeak = yes 128.heartwall: basepeak = yes 140.bplustree: basepeak = yes C++ benchmarks: 101.tpacf: -O2 -march=haswell -DSPEC_ACCEL_WG_SIZE_0_0=1024 -I/opt/pkg/devel/cuda/7.0/include -L/opt/pkg/devel/cuda/7.0/libb64 -lcuda -lOpenCL 103.stencil: basepeak = yes 104.lbm: -O2 -march=haswell -DSPEC_ACCEL_WG_SIZE_0_0=32 -DSPEC_ACCEL_WG_SIZE_0_1=1 -DSPEC_ACCEL_WG_SIZE_0_2=1 -I/opt/pkg/devel/cuda/7.0/include -L/opt/pkg/devel/cuda/7.0/libb64 -lcuda -lOpenCL 112.spmv: -O2 -march=haswell -DSPEC_ACCEL_WG_SIZE_0_0=96 -I/opt/pkg/devel/cuda/7.0/include -L/opt/pkg/devel/cuda/7.0/libb64 -lcuda -lOpenCL 120.kmeans: -O2 -march=haswell -DSPEC_ACCEL_WG_SIZE_0_0=288 -I/opt/pkg/devel/cuda/7.0/include -L/opt/pkg/devel/cuda/7.0/libb64 -lcuda -lOpenCL 122.cfd: -O2 -march=haswell -DSPEC_ACCEL_WG_SIZE_3_0=288 -I/opt/pkg/devel/cuda/7.0/include -L/opt/pkg/devel/cuda/7.0/libb64 -lcuda -lOpenCL 123.nw: basepeak = yes 125.lud: -O2 -march=haswell -DSPEC_ACCEL_WG_SIZE_0_0=32 -I/opt/pkg/devel/cuda/7.0/include -L/opt/pkg/devel/cuda/7.0/libb64 -lcuda -lOpenCL 126.ge: -O2 -march=haswell -DSPEC_ACCEL_WG_SIZE_0_0=512 -DSPEC_ACCEL_WG_SIZE_1_0=1 -DSPEC_ACCEL_WG_SIZE_1_1=512 -I/opt/pkg/devel/cuda/7.0/include -L/opt/pkg/devel/cuda/7.0/libb64 -lcuda -lOpenCL The flags file that was used to format this result can be browsed at https://www.spec.org/accel/flags/flags-advanced.20170929.html You can also download the XML flags source by saving the following link: https://www.spec.org/accel/flags/flags-advanced.20170929.xml SPEC and SPEC ACCEL are registered trademarks or trademarks 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 2015-2017 Standard Performance Evaluation Corporation Tested with SPEC ACCEL v1.2. Report generated on Fri Sep 29 13:32:03 2017 by ACCEL ASCII formatter v1290. Originally published on 28 September 2017.