rs4l-ocl-regression-polaris22 Radeon Software for Linux OpenCL Installable Client Driver (ICD) regression testing with an Intel Hades Canyon NUC and Radeon RX Vega M GH (Polaris22/VegaM XT).
HTML result view exported from: https://openbenchmarking.org/result/2203094-TAD-2202217T48 .
rs4l-ocl-regression-polaris22 Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server OpenGL OpenCL Vulkan Compiler File-System Screen Resolution 21.40.2 21.50 21.50.2 Intel Core i7-8809G @ 8.30GHz (4 Cores / 8 Threads) Intel NUC8i7HVB (HNKBLi70.86A.0067.2021.0528.1339 BIOS) Intel Xeon E3-1200 v6/7th 32GB Western Digital WD_BLACK SN750 SE 500GB + Samsung SSD 970 PRO 512GB AMD Radeon RX Vega M GH 4GB (1190/800MHz) Realtek ALC700 Intel I219-LM + Intel I210 + Intel 8265 / 8275 Ubuntu 20.04 5.11.0-46-generic (x86_64) GNOME Shell 3.36.9 X Server 1.20.13 4.6 Mesa 21.2.6 (LLVM 12.0.0) OpenCL 2.1 AMD-APP (3354.7) 1.2.182 GCC 9.3.0 + Clang 10.0.0-4ubuntu1 ext4 1920x1080 5.13.0-30-generic (x86_64) OpenCL 2.1 AMD-APP (3380.4) Samsung SSD 970 PRO 512GB + Western Digital WD_BLACK SN750 SE 500GB Intel I219-LM + Intel I210 + Intel Wi-Fi 6 AX200 5.13.0-35-generic (x86_64) GCC 10.3.0 + Clang 10.0.0-4ubuntu1 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - 21.40.2: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - 21.50: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - 21.50.2: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-S4I5Pr/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-S4I5Pr/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xea - Thermald 1.9.1 Graphics Details - GLAMOR - BAR1 / Visible vRAM Size: 4096 MB Security Details - 21.40.2: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Not affected - 21.50: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Not affected - 21.50.2: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Not affected
rs4l-ocl-regression-polaris22 clpeak: Global Memory Bandwidth clpeak: Single-Precision Float clpeak: Double-Precision Double clpeak: Integer Compute INT clpeak: Transfer Bandwidth enqueueWriteBuffer clpeak: Transfer Bandwidth enqueueReadBuffer clpeak: Kernel Latency shoc: OpenCL - Bus Speed Download shoc: OpenCL - Bus Speed Readback shoc: OpenCL - Max SP Flops shoc: OpenCL - Texture Read Bandwidth shoc: OpenCL - FFT SP shoc: OpenCL - GEMM SGEMM_N shoc: OpenCL - MD5 Hash shoc: OpenCL - Reduction shoc: OpenCL - Triad shoc: OpenCL - S3D fahbench: luxmark: GPU - Luxball HDR luxmark: GPU - Microphone luxmark: GPU - Hotel 21.40.2 21.50 21.50.2 152.76 3527.52 225.88 721.92 35.11 13.51 24.88 6.2319 6.3566 3584.78 163.980 397.234 1298.47 4.5235 109.007 2.9173 32.3898 40.4719 9664 6421 1686 152.64 3505.77 225.87 721.88 35.64 13.62 24.66 6.2644 6.3813 3584.02 165.325 396.112 1296.36 4.5249 109.606 2.9409 32.1812 40.8444 9717 6351 1694 152.60 3502.67 225.87 721.92 35.61 13.84 25.16 6.2621 6.3852 3580.85 164.767 396.551 1299.28 4.5254 110.101 2.9373 31.5500 41.1837 9665 6423 1691 OpenBenchmarking.org
clpeak OpenCL Test: Global Memory Bandwidth OpenBenchmarking.org GBPS, More Is Better clpeak OpenCL Test: Global Memory Bandwidth 21.40.2 21.50 21.50.2 30 60 90 120 150 SE +/- 0.09, N = 5 SE +/- 0.05, N = 5 SE +/- 0.02, N = 5 152.76 152.64 152.60 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
clpeak CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 900 2501 4099 21.50 887 2389 4100 21.50.2 801 2356 4100 OpenBenchmarking.org Megahertz, More Is Better clpeak CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
clpeak CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 5.7 15.3 21.50 0.0 6.0 16.8 21.50.2 0.0 5.8 16.0 OpenBenchmarking.org Percent, Fewer Is Better clpeak CPU Usage (Summary) Monitor 5 10 15 20 25
clpeak GPU Frequency Monitor Min Avg Max 21.40.2 225 564 1190 21.50 225 569 1190 21.50.2 225 564 1190 OpenBenchmarking.org Megahertz, More Is Better clpeak GPU Frequency Monitor 400 800 1200 1600 2000
clpeak GPU Memory Usage Monitor Min Avg Max 21.40.2 237 1020 2490 21.50 254 1122 2590 21.50.2 243 1035 2482 OpenBenchmarking.org Megabytes, Fewer Is Better clpeak GPU Memory Usage Monitor 700 1400 2100 2800 3500
clpeak GPU Power Consumption Monitor Min Avg Max 21.40.2 5.1 15.6 38.1 21.50 5.2 16.2 39.1 21.50.2 5.2 16.2 38.2 OpenBenchmarking.org Watts, Fewer Is Better clpeak GPU Power Consumption Monitor 11 22 33 44 55
clpeak GPU Temperature Monitor Min Avg Max 21.40.2 42.0 45.7 53.0 21.50 40.0 44.7 51.0 21.50.2 42.0 45.5 52.0 OpenBenchmarking.org Celsius, Fewer Is Better clpeak GPU Temperature Monitor 15 30 45 60 75
clpeak GPU Usage Monitor Min Avg Max 21.40.2 1.0 95.3 100.0 21.50 100.0 100.0 100.0 21.50.2 100.0 100.0 100.0 OpenBenchmarking.org Percent, Fewer Is Better clpeak GPU Usage Monitor 20 40 60 80 100
clpeak OpenCL Test: Single-Precision Float OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Single-Precision Float 21.40.2 21.50 21.50.2 800 1600 2400 3200 4000 SE +/- 3.63, N = 7 SE +/- 8.55, N = 7 SE +/- 6.07, N = 7 3527.52 3505.77 3502.67 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
clpeak CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 900 2751 4099 21.50 900 2688 4101 21.50.2 900 2663 4100 OpenBenchmarking.org Megahertz, More Is Better clpeak CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
clpeak CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 6.9 16.0 21.50 0.0 6.5 15.8 21.50.2 0.0 6.5 15.3 OpenBenchmarking.org Percent, Fewer Is Better clpeak CPU Usage (Summary) Monitor 5 10 15 20 25
clpeak GPU Frequency Monitor Min Avg Max 21.40.2 225 379 1190 21.50 225 399 1190 21.50.2 225 392 1190 OpenBenchmarking.org Megahertz, More Is Better clpeak GPU Frequency Monitor 400 800 1200 1600 2000
clpeak GPU Memory Usage Monitor Min Avg Max 21.40.2 229.0 253.6 348.0 21.50 245.0 272.2 365.0 21.50.2 243.0 270.3 363.0 OpenBenchmarking.org Megabytes, Fewer Is Better clpeak GPU Memory Usage Monitor 100 200 300 400 500
clpeak GPU Power Consumption Monitor Min Avg Max 21.40.2 5.1 9.7 36.3 21.50 5.2 10.1 38.1 21.50.2 5.2 10.3 37.2 OpenBenchmarking.org Watts, Fewer Is Better clpeak GPU Power Consumption Monitor 11 22 33 44 55
clpeak GPU Temperature Monitor Min Avg Max 21.40.2 39.0 40.3 46.0 21.50 40.0 41.2 47.0 21.50.2 39.0 41.1 47.0 OpenBenchmarking.org Celsius, Fewer Is Better clpeak GPU Temperature Monitor 14 28 42 56 70
clpeak GPU Usage Monitor OpenBenchmarking.org Percent, Fewer Is Better clpeak GPU Usage Monitor 21.50.2 21.50 20 40 60 80 100 100 100
clpeak OpenCL Test: Double-Precision Double OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Double-Precision Double 21.40.2 21.50 21.50.2 50 100 150 200 250 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 225.88 225.87 225.87 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
clpeak CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 805 1809 4099 21.50 900 1670 4100 21.50.2 900 1763 4100 OpenBenchmarking.org Megahertz, More Is Better clpeak CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
clpeak CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 2.8 17.9 21.50 0.0 2.9 15.3 21.50.2 0.0 3.3 16.0 OpenBenchmarking.org Percent, Fewer Is Better clpeak CPU Usage (Summary) Monitor 5 10 15 20 25
clpeak GPU Frequency Monitor Min Avg Max 21.40.2 225 954 1190 21.50 225 960 1190 21.50.2 225 956 1190 OpenBenchmarking.org Megahertz, More Is Better clpeak GPU Frequency Monitor 400 800 1200 1600 2000
clpeak GPU Memory Usage Monitor Min Avg Max 21.40.2 217.0 354.9 406.0 21.50 245.0 372.0 416.0 21.50.2 243.0 368.0 413.0 OpenBenchmarking.org Megabytes, Fewer Is Better clpeak GPU Memory Usage Monitor 110 220 330 440 550
clpeak GPU Power Consumption Monitor Min Avg Max 21.40.2 5.1 24.2 36.0 21.50 5.2 25.2 36.2 21.50.2 5.2 25.1 36.1 OpenBenchmarking.org Watts, Fewer Is Better clpeak GPU Power Consumption Monitor 10 20 30 40 50
clpeak GPU Temperature Monitor Min Avg Max 21.40.2 38.0 46.9 50.0 21.50 39.0 48.3 51.0 21.50.2 38.0 47.4 51.0 OpenBenchmarking.org Celsius, Fewer Is Better clpeak GPU Temperature Monitor 15 30 45 60 75
clpeak GPU Usage Monitor OpenBenchmarking.org Percent, Fewer Is Better clpeak GPU Usage Monitor 21.50.2 21.50 20 40 60 80 100 100 100
clpeak OpenCL Test: Integer Compute INT OpenBenchmarking.org GIOPS, More Is Better clpeak OpenCL Test: Integer Compute INT 21.40.2 21.50 21.50.2 160 320 480 640 800 SE +/- 0.01, N = 4 SE +/- 0.01, N = 4 SE +/- 0.01, N = 4 721.92 721.88 721.92 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
clpeak CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 900 2174 4099 21.50 900 2272 4100 21.50.2 900 2115 4099 OpenBenchmarking.org Megahertz, More Is Better clpeak CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
clpeak CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 4.3 19.9 21.50 0.0 4.5 15.8 21.50.2 0.0 4.9 15.5 OpenBenchmarking.org Percent, Fewer Is Better clpeak CPU Usage (Summary) Monitor 6 12 18 24 30
clpeak GPU Frequency Monitor Min Avg Max 21.40.2 225 688 1190 21.50 225 693 1190 21.50.2 225 701 1190 OpenBenchmarking.org Megahertz, More Is Better clpeak GPU Frequency Monitor 400 800 1200 1600 2000
clpeak GPU Memory Usage Monitor Min Avg Max 21.40.2 227.0 287.7 347.0 21.50 254.0 307.8 365.0 21.50.2 252.0 306.9 363.0 OpenBenchmarking.org Megabytes, Fewer Is Better clpeak GPU Memory Usage Monitor 100 200 300 400 500
clpeak GPU Power Consumption Monitor Min Avg Max 21.40.2 5.1 20.8 39.1 21.50 5.2 21.5 40.0 21.50.2 5.2 22.0 40.0 OpenBenchmarking.org Watts, Fewer Is Better clpeak GPU Power Consumption Monitor 11 22 33 44 55
clpeak GPU Temperature Monitor Min Avg Max 21.40.2 40.0 45.5 51.0 21.50 42.0 46.7 51.0 21.50.2 43.0 47.2 51.0 OpenBenchmarking.org Celsius, Fewer Is Better clpeak GPU Temperature Monitor 15 30 45 60 75
clpeak GPU Usage Monitor Min Avg Max 21.40.2 2.0 93.4 100.0 21.50 100.0 100.0 100.0 21.50.2 100.0 100.0 100.0 OpenBenchmarking.org Percent, Fewer Is Better clpeak GPU Usage Monitor 20 40 60 80 100
clpeak OpenCL Test: Transfer Bandwidth enqueueWriteBuffer OpenBenchmarking.org GBPS, More Is Better clpeak OpenCL Test: Transfer Bandwidth enqueueWriteBuffer 21.40.2 21.50 21.50.2 8 16 24 32 40 SE +/- 0.15, N = 5 SE +/- 0.03, N = 5 SE +/- 0.01, N = 5 35.11 35.64 35.61 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
clpeak CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 900 3473 4100 21.50 900 3442 4101 21.50.2 900 3333 4100 OpenBenchmarking.org Megahertz, More Is Better clpeak CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
clpeak CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.3 9.2 14.5 21.50 0.0 10.4 15.8 21.50.2 0.0 10.2 15.8 OpenBenchmarking.org Percent, Fewer Is Better clpeak CPU Usage (Summary) Monitor 5 10 15 20 25
clpeak GPU Frequency Monitor Min Avg Max 21.40.2 225.0 235.5 535.0 21.50 225.0 241.3 535.0 21.50.2 225.0 233.3 400.0 OpenBenchmarking.org Megahertz, More Is Better clpeak GPU Frequency Monitor 140 280 420 560 700
clpeak GPU Memory Usage Monitor Min Avg Max 21.40.2 227.0 266.7 315.0 21.50 245.0 288.3 334.0 21.50.2 243.0 288.7 396.0 OpenBenchmarking.org Megabytes, Fewer Is Better clpeak GPU Memory Usage Monitor 110 220 330 440 550
clpeak GPU Power Consumption Monitor Min Avg Max 21.40.2 5.1 5.1 7.2 21.50 5.2 5.3 8.1 21.50.2 5.2 5.2 6.0 OpenBenchmarking.org Watts, Fewer Is Better clpeak GPU Power Consumption Monitor 3 6 9 12 15
clpeak GPU Temperature Monitor Min Avg Max 21.40.2 38.0 38.7 40.0 21.50 40.0 40.3 42.0 21.50.2 39.0 40.0 42.0 OpenBenchmarking.org Celsius, Fewer Is Better clpeak GPU Temperature Monitor 12 24 36 48 60
clpeak OpenCL Test: Transfer Bandwidth enqueueReadBuffer OpenBenchmarking.org GBPS, More Is Better clpeak OpenCL Test: Transfer Bandwidth enqueueReadBuffer 21.40.2 21.50 21.50.2 4 8 12 16 20 SE +/- 0.02, N = 5 SE +/- 0.05, N = 5 SE +/- 0.06, N = 5 13.51 13.62 13.84 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
clpeak CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 900 3284 4101 21.50 900 3421 4099 21.50.2 900 3533 4101 OpenBenchmarking.org Megahertz, More Is Better clpeak CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
clpeak CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 9.2 14.5 21.50 0.0 10.3 17.3 21.50.2 0.0 10.4 15.2 OpenBenchmarking.org Percent, Fewer Is Better clpeak CPU Usage (Summary) Monitor 5 10 15 20 25
clpeak GPU Frequency Monitor Min Avg Max 21.40.2 225.0 235.5 535.0 21.50 225.0 232.7 535.0 21.50.2 225.0 233.5 400.0 OpenBenchmarking.org Megahertz, More Is Better clpeak GPU Frequency Monitor 140 280 420 560 700
clpeak GPU Memory Usage Monitor Min Avg Max 21.40.2 227.0 269.9 315.0 21.50 245.0 288.5 334.0 21.50.2 243.0 287.1 331.0 OpenBenchmarking.org Megabytes, Fewer Is Better clpeak GPU Memory Usage Monitor 80 160 240 320 400
clpeak GPU Power Consumption Monitor Min Avg Max 21.40.2 5.1 5.2 9.0 21.50 5.2 5.2 8.1 21.50.2 5.2 5.2 5.2 OpenBenchmarking.org Watts, Fewer Is Better clpeak GPU Power Consumption Monitor 4.42 8.84 13.26 17.68 22.1
clpeak GPU Temperature Monitor Min Avg Max 21.40.2 37.0 38.0 39.0 21.50 38.0 39.3 40.0 21.50.2 38.0 38.9 39.0 OpenBenchmarking.org Celsius, Fewer Is Better clpeak GPU Temperature Monitor 11 22 33 44 55
clpeak OpenCL Test: Kernel Latency OpenBenchmarking.org us, Fewer Is Better clpeak OpenCL Test: Kernel Latency 21.40.2 21.50 21.50.2 6 12 18 24 30 SE +/- 0.26, N = 15 SE +/- 0.18, N = 8 SE +/- 0.31, N = 15 24.88 24.66 25.16 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
clpeak CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 900 2989 4100 21.50 900 2936 4099 21.50.2 900 2988 4100 OpenBenchmarking.org Megahertz, More Is Better clpeak CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
clpeak CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 7.6 17.6 21.50 0.0 8.8 20.0 21.50.2 0.0 8.1 19.8 OpenBenchmarking.org Percent, Fewer Is Better clpeak CPU Usage (Summary) Monitor 6 12 18 24 30
clpeak GPU Frequency Monitor Min Avg Max 21.40.2 225 309 1190 21.50 225 314 1190 21.50.2 225 312 1190 OpenBenchmarking.org Megahertz, More Is Better clpeak GPU Frequency Monitor 400 800 1200 1600 2000
clpeak GPU Memory Usage Monitor Min Avg Max 21.40.2 227.0 241.1 313.0 21.50 245.0 260.2 332.0 21.50.2 243.0 258.0 330.0 OpenBenchmarking.org Megabytes, Fewer Is Better clpeak GPU Memory Usage Monitor 80 160 240 320 400
clpeak GPU Power Consumption Monitor Min Avg Max 21.40.2 5.1 6.3 21.2 21.50 5.2 6.6 22.2 21.50.2 5.2 6.6 23.0 OpenBenchmarking.org Watts, Fewer Is Better clpeak GPU Power Consumption Monitor 8 16 24 32 40
clpeak GPU Temperature Monitor Min Avg Max 21.40.2 37.0 38.3 42.0 21.50 38.0 39.5 44.0 21.50.2 38.0 39.0 43.0 OpenBenchmarking.org Celsius, Fewer Is Better clpeak GPU Temperature Monitor 12 24 36 48 60
clpeak GPU Usage Monitor Min Avg Max 21.40.2 47.0 53.2 74.0 21.50.2 4.0 44.9 52.0 OpenBenchmarking.org Percent, Fewer Is Better clpeak GPU Usage Monitor 20 40 60 80 100
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Bus Speed Download OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Download 21.40.2 21.50 21.50.2 2 4 6 8 10 SE +/- 0.0155, N = 9 SE +/- 0.0209, N = 10 SE +/- 0.0226, N = 10 6.2319 6.2644 6.2621 -lSHOCCommonMPI -pthread -lmpi_cxx -lmpi 1. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt
SHOC Scalable HeterOgeneous Computing CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 900 2042 4093 21.50 860 2086 4099 21.50.2 843 2103 4097 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
SHOC Scalable HeterOgeneous Computing CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 2.1 9.8 21.50 0.0 3.2 13.0 21.50.2 0.0 2.1 7.5 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Usage (Summary) Monitor 4 8 12 16 20
SHOC Scalable HeterOgeneous Computing GPU Frequency Monitor Min Avg Max 21.40.2 225 458 1080 21.50 225 482 1140 21.50.2 225 465 1140 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Frequency Monitor 200 400 600 800 1000
SHOC Scalable HeterOgeneous Computing GPU Memory Usage Monitor Min Avg Max 21.40.2 227 440 851 21.50 245 462 870 21.50.2 243 444 868 OpenBenchmarking.org Megabytes, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Memory Usage Monitor 200 400 600 800 1000
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max 21.40.2 5.1 7.9 16.2 21.50 5.2 8.4 20.0 21.50.2 5.2 8.4 20.1 OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Power Consumption Monitor 6 12 18 24 30
SHOC Scalable HeterOgeneous Computing GPU Temperature Monitor Min Avg Max 21.40.2 37.0 38.5 41.0 21.50 39.0 40.3 43.0 21.50.2 38.0 40.3 44.0 OpenBenchmarking.org Celsius, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Temperature Monitor 12 24 36 48 60
SHOC Scalable HeterOgeneous Computing GPU Usage Monitor Min Avg Max 21.40.2 1.0 86.4 100.0 21.50 1.0 75.1 100.0 21.50.2 1.0 83.9 100.0 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Usage Monitor 20 40 60 80 100
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Bus Speed Readback OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Readback 21.40.2 21.50 21.50.2 2 4 6 8 10 SE +/- 0.0090, N = 9 SE +/- 0.0132, N = 9 SE +/- 0.0160, N = 10 6.3566 6.3813 6.3852 -lSHOCCommonMPI -pthread -lmpi_cxx -lmpi 1. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt
SHOC Scalable HeterOgeneous Computing CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 890 2402 4098 21.50 900 1928 4095 21.50.2 897 2119 4098 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
SHOC Scalable HeterOgeneous Computing CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 2.1 9.3 21.50 0.0 3.7 12.8 21.50.2 0.0 2.2 11.0 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Usage (Summary) Monitor 4 8 12 16 20
SHOC Scalable HeterOgeneous Computing GPU Frequency Monitor Min Avg Max 21.40.2 225 456 1080 21.50 225 457 1140 21.50.2 225 462 1140 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Frequency Monitor 200 400 600 800 1000
SHOC Scalable HeterOgeneous Computing GPU Memory Usage Monitor Min Avg Max 21.40.2 227 445 852 21.50 245 459 871 21.50.2 243 461 869 OpenBenchmarking.org Megabytes, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Memory Usage Monitor 200 400 600 800 1000
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max 21.40.2 5.1 8.1 18.1 21.50 5.2 8.7 19.1 21.50.2 5.2 8.5 20.2 OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Power Consumption Monitor 6 12 18 24 30
SHOC Scalable HeterOgeneous Computing GPU Temperature Monitor Min Avg Max 21.40.2 39.0 42.0 46.0 21.50 40.0 43.3 47.0 21.50.2 41.0 42.9 46.0 OpenBenchmarking.org Celsius, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Temperature Monitor 14 28 42 56 70
SHOC Scalable HeterOgeneous Computing GPU Usage Monitor Min Avg Max 21.40.2 2.0 86.8 100.0 21.50 3.0 82.1 100.0 21.50.2 5.0 81.8 100.0 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Usage Monitor 20 40 60 80 100
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Max SP Flops OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Max SP Flops 21.40.2 21.50 21.50.2 800 1600 2400 3200 4000 SE +/- 1.14, N = 3 SE +/- 1.11, N = 3 SE +/- 0.55, N = 3 3584.78 3584.02 3580.85 -lSHOCCommonMPI -pthread -lmpi_cxx -lmpi 1. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt
SHOC Scalable HeterOgeneous Computing CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 900 2718 4097 21.50 900 2912 4100 21.50.2 900 3048 4101 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
SHOC Scalable HeterOgeneous Computing CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 2.8 7.8 21.50 0.0 3.3 8.5 21.50.2 0.0 3.1 9.6 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Usage (Summary) Monitor 4.42 8.84 13.26 17.68 22.1
SHOC Scalable HeterOgeneous Computing GPU Frequency Monitor Min Avg Max 21.40.2 225 895 1190 21.50 225 729 1190 21.50.2 225 739 1190 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Frequency Monitor 400 800 1200 1600 2000
SHOC Scalable HeterOgeneous Computing GPU Memory Usage Monitor Min Avg Max 21.40.2 227.0 333.8 373.0 21.50 254.0 356.0 392.0 21.50.2 243.0 349.8 390.0 OpenBenchmarking.org Megabytes, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Memory Usage Monitor 110 220 330 440 550
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max 21.40.2 5.2 20.3 34.2 21.50 5.2 16.7 39.1 21.50.2 5.2 16.8 35.1 OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Power Consumption Monitor 11 22 33 44 55
SHOC Scalable HeterOgeneous Computing GPU Temperature Monitor Min Avg Max 21.40.2 44.0 52.4 58.0 21.50 43.0 50.7 57.0 21.50.2 42.0 50.0 57.0 OpenBenchmarking.org Celsius, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Temperature Monitor 16 32 48 64 80
SHOC Scalable HeterOgeneous Computing GPU Usage Monitor Min Avg Max 21.40.2 1.0 89.8 100.0 21.50 7.0 88.9 100.0 21.50.2 2.0 84.4 100.0 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Usage Monitor 20 40 60 80 100
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Texture Read Bandwidth OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Texture Read Bandwidth 21.40.2 21.50 21.50.2 40 80 120 160 200 SE +/- 0.88, N = 3 SE +/- 0.73, N = 3 SE +/- 1.25, N = 10 163.98 165.33 164.77 -lSHOCCommonMPI -pthread -lmpi_cxx -lmpi 1. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt
SHOC Scalable HeterOgeneous Computing CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 900 2570 4097 21.50 900 2061 4100 21.50.2 900 1878 4099 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
SHOC Scalable HeterOgeneous Computing CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 2.2 12.5 21.50 0.0 1.8 12.8 21.50.2 0.0 1.6 12.7 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Usage (Summary) Monitor 4 8 12 16 20
SHOC Scalable HeterOgeneous Computing GPU Frequency Monitor Min Avg Max 21.40.2 225 1029 1190 21.50 225 957 1190 21.50.2 225 982 1190 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Frequency Monitor 400 800 1200 1600 2000
SHOC Scalable HeterOgeneous Computing GPU Memory Usage Monitor Min Avg Max 21.40.2 226.0 406.8 443.0 21.50 254.0 423.0 471.0 21.50.2 243.0 427.0 469.0 OpenBenchmarking.org Megabytes, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Memory Usage Monitor 120 240 360 480 600
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max 21.40.2 5.2 21.7 33.2 21.50 5.2 20.7 34.1 21.50.2 5.2 21.3 33.2 OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Power Consumption Monitor 10 20 30 40 50
SHOC Scalable HeterOgeneous Computing GPU Temperature Monitor Min Avg Max 21.40.2 45.0 50.7 54.0 21.50 45.0 50.8 54.0 21.50.2 44.0 49.5 54.0 OpenBenchmarking.org Celsius, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Temperature Monitor 15 30 45 60 75
SHOC Scalable HeterOgeneous Computing GPU Usage Monitor Min Avg Max 21.40.2 19.0 97.5 100.0 21.50 3.0 94.8 100.0 21.50.2 1.0 95.6 100.0 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Usage Monitor 20 40 60 80 100
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: FFT SP OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: FFT SP 21.40.2 21.50 21.50.2 90 180 270 360 450 SE +/- 2.27, N = 10 SE +/- 1.30, N = 10 SE +/- 1.59, N = 10 397.23 396.11 396.55 -lSHOCCommonMPI -pthread -lmpi_cxx -lmpi 1. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt
SHOC Scalable HeterOgeneous Computing CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 900 2391 4099 21.50 900 2332 4099 21.50.2 900 2325 4099 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
SHOC Scalable HeterOgeneous Computing CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 3.9 12.5 21.50 0.0 3.6 12.5 21.50.2 0.0 3.7 12.8 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Usage (Summary) Monitor 4 8 12 16 20
SHOC Scalable HeterOgeneous Computing GPU Frequency Monitor Min Avg Max 21.40.2 225 379 1190 21.50 225 417 1190 21.50.2 225 390 1190 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Frequency Monitor 400 800 1200 1600 2000
SHOC Scalable HeterOgeneous Computing GPU Memory Usage Monitor Min Avg Max 21.40.2 217.0 308.0 573.0 21.50 245.0 336.2 602.0 21.50.2 243.0 328.3 600.0 OpenBenchmarking.org Megabytes, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Memory Usage Monitor 160 320 480 640 800
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max 21.40.2 5.1 7.7 34.2 21.50 5.2 9.3 35.2 21.50.2 5.2 9.2 34.2 OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Power Consumption Monitor 10 20 30 40 50
SHOC Scalable HeterOgeneous Computing GPU Temperature Monitor Min Avg Max 21.40.2 42.0 43.3 47.0 21.50 42.0 42.9 47.0 21.50.2 42.0 43.2 47.0 OpenBenchmarking.org Celsius, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Temperature Monitor 14 28 42 56 70
SHOC Scalable HeterOgeneous Computing GPU Usage Monitor Min Avg Max 21.40.2 1.0 84.9 100.0 21.50 4.0 64.3 100.0 21.50.2 1.0 86.4 100.0 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Usage Monitor 20 40 60 80 100
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: GEMM SGEMM_N OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: GEMM SGEMM_N 21.40.2 21.50 21.50.2 300 600 900 1200 1500 SE +/- 0.66, N = 4 SE +/- 0.98, N = 4 SE +/- 1.09, N = 4 1298.47 1296.36 1299.28 -lSHOCCommonMPI -pthread -lmpi_cxx -lmpi 1. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt
SHOC Scalable HeterOgeneous Computing CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 900 1666 4099 21.50 900 1559 4099 21.50.2 900 1554 4093 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
SHOC Scalable HeterOgeneous Computing CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 1.1 10.5 21.50 0.0 1.2 12.6 21.50.2 0.0 1.1 8.0 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Usage (Summary) Monitor 4 8 12 16 20
SHOC Scalable HeterOgeneous Computing GPU Frequency Monitor Min Avg Max 21.40.2 225 919 1190 21.50 225 907 1190 21.50.2 225 935 1190 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Frequency Monitor 400 800 1200 1600 2000
SHOC Scalable HeterOgeneous Computing GPU Memory Usage Monitor Min Avg Max 21.40.2 217 435 605 21.50 245 464 634 21.50.2 243 473 632 OpenBenchmarking.org Megabytes, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Memory Usage Monitor 200 400 600 800 1000
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max 21.40.2 5.1 22.5 51.1 21.50 5.2 22.1 49.0 21.50.2 5.2 23.2 48.1 OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Power Consumption Monitor 15 30 45 60 75
SHOC Scalable HeterOgeneous Computing GPU Temperature Monitor Min Avg Max 21.40.2 41.0 49.4 54.0 21.50 41.0 49.3 54.0 21.50.2 41.0 48.7 53.0 OpenBenchmarking.org Celsius, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Temperature Monitor 15 30 45 60 75
SHOC Scalable HeterOgeneous Computing GPU Usage Monitor Min Avg Max 21.40.2 39.0 98.6 100.0 21.50 8.0 97.0 100.0 21.50.2 8.0 95.2 100.0 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Usage Monitor 20 40 60 80 100
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: MD5 Hash OpenBenchmarking.org GHash/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: MD5 Hash 21.40.2 21.50 21.50.2 1.0182 2.0364 3.0546 4.0728 5.091 SE +/- 0.0011, N = 8 SE +/- 0.0009, N = 8 SE +/- 0.0011, N = 8 4.5235 4.5249 4.5254 -lSHOCCommonMPI -pthread -lmpi_cxx -lmpi 1. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt
SHOC Scalable HeterOgeneous Computing CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 900 1777 4080 21.50 900 1751 4097 21.50.2 900 1840 4099 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
SHOC Scalable HeterOgeneous Computing CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 0.8 8.3 21.50 0.0 0.6 5.8 21.50.2 0.0 0.9 10.0 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Usage (Summary) Monitor 4 8 12 16 20
SHOC Scalable HeterOgeneous Computing GPU Frequency Monitor Min Avg Max 21.40.2 225 689 1190 21.50 225 680 1190 21.50.2 225 648 1190 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Frequency Monitor 400 800 1200 1600 2000
SHOC Scalable HeterOgeneous Computing GPU Memory Usage Monitor Min Avg Max 21.40.2 217.0 262.2 303.0 21.50 245.0 290.6 331.0 21.50.2 243.0 291.3 329.0 OpenBenchmarking.org Megabytes, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Memory Usage Monitor 80 160 240 320 400
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max 21.40.2 5.1 21.7 41.1 21.50 5.2 21.4 41.2 21.50.2 5.2 20.6 41.2 OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Power Consumption Monitor 11 22 33 44 55
SHOC Scalable HeterOgeneous Computing GPU Temperature Monitor Min Avg Max 21.40.2 43.0 48.2 54.0 21.50 43.0 48.4 54.0 21.50.2 43.0 48.3 54.0 OpenBenchmarking.org Celsius, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Temperature Monitor 15 30 45 60 75
SHOC Scalable HeterOgeneous Computing GPU Usage Monitor Min Avg Max 21.40.2 14.0 96.9 100.0 21.50 3.0 90.7 100.0 21.50.2 36.0 97.8 100.0 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Usage Monitor 20 40 60 80 100
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Reduction OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Reduction 21.40.2 21.50 21.50.2 20 40 60 80 100 SE +/- 0.98, N = 15 SE +/- 0.93, N = 8 SE +/- 0.97, N = 15 109.01 109.61 110.10 -lSHOCCommonMPI -pthread -lmpi_cxx -lmpi 1. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt
SHOC Scalable HeterOgeneous Computing CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 900 2241 4097 21.50 900 2145 4097 21.50.2 900 2206 4094 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
SHOC Scalable HeterOgeneous Computing CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 4.5 10.0 21.50 0.0 4.5 10.7 21.50.2 0.0 4.6 10.1 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Usage (Summary) Monitor 4 8 12 16 20
SHOC Scalable HeterOgeneous Computing GPU Frequency Monitor Min Avg Max 21.40.2 225 620 1140 21.50 225 620 1140 21.50.2 225 640 1140 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Frequency Monitor 200 400 600 800 1000
SHOC Scalable HeterOgeneous Computing GPU Memory Usage Monitor Min Avg Max 21.40.2 217.0 295.9 370.0 21.50 245.0 321.3 399.0 21.50.2 243.0 323.9 396.0 OpenBenchmarking.org Megabytes, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Memory Usage Monitor 110 220 330 440 550
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max 21.40.2 5.2 15.0 29.2 21.50 5.2 15.7 31.0 21.50.2 5.2 16.1 30.1 OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Power Consumption Monitor 9 18 27 36 45
SHOC Scalable HeterOgeneous Computing GPU Temperature Monitor Min Avg Max 21.40.2 45.0 49.7 53.0 21.50 45.0 48.9 52.0 21.50.2 45.0 49.0 52.0 OpenBenchmarking.org Celsius, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Temperature Monitor 15 30 45 60 75
SHOC Scalable HeterOgeneous Computing GPU Usage Monitor Min Avg Max 21.40.2 6.0 66.4 96.0 21.50 1.0 65.2 96.0 21.50.2 4.0 68.9 97.0 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Usage Monitor 20 40 60 80 100
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Triad OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Triad 21.40.2 21.50 21.50.2 0.6617 1.3234 1.9851 2.6468 3.3085 SE +/- 0.0097, N = 8 SE +/- 0.0077, N = 8 SE +/- 0.0084, N = 8 2.9173 2.9409 2.9373 -lSHOCCommonMPI -pthread -lmpi_cxx -lmpi 1. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt
SHOC Scalable HeterOgeneous Computing CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 900 2770 4092 21.50 900 2594 4097 21.50.2 900 2477 4094 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
SHOC Scalable HeterOgeneous Computing CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 5.1 11.1 21.50 0.0 5.1 10.7 21.50.2 0.0 4.8 10.7 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Usage (Summary) Monitor 4 8 12 16 20
SHOC Scalable HeterOgeneous Computing GPU Frequency Monitor Min Avg Max 21.40.2 225.0 320.5 400.0 21.50 225.0 316.6 535.0 21.50.2 225.0 310.9 400.0 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Frequency Monitor 140 280 420 560 700
SHOC Scalable HeterOgeneous Computing GPU Memory Usage Monitor Min Avg Max 21.40.2 217.0 305.7 403.0 21.50 245.0 329.9 432.0 21.50.2 252.0 329.8 430.0 OpenBenchmarking.org Megabytes, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Memory Usage Monitor 110 220 330 440 550
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max 21.40.2 5.1 5.9 7.1 21.50 5.2 6.2 8.1 21.50.2 5.2 6.4 8.0 OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Power Consumption Monitor 3 6 9 12 15
SHOC Scalable HeterOgeneous Computing GPU Temperature Monitor Min Avg Max 21.40.2 44.0 45.2 47.0 21.50 45.0 45.6 46.0 21.50.2 45.0 45.5 47.0 OpenBenchmarking.org Celsius, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Temperature Monitor 14 28 42 56 70
SHOC Scalable HeterOgeneous Computing GPU Usage Monitor Min Avg Max 21.40.2 61.0 80.9 100.0 21.50 1.0 64.1 100.0 21.50.2 1.0 72.6 100.0 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Usage Monitor 20 40 60 80 100
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: S3D OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: S3D 21.40.2 21.50 21.50.2 8 16 24 32 40 SE +/- 0.04, N = 3 SE +/- 0.12, N = 3 SE +/- 0.25, N = 3 32.39 32.18 31.55 -lSHOCCommonMPI -pthread -lmpi_cxx -lmpi 1. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt
SHOC Scalable HeterOgeneous Computing CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 900 3956 4101 21.50 900 3963 4101 21.50.2 901 3961 4100 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
SHOC Scalable HeterOgeneous Computing CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 11.9 18.3 21.50 0.0 11.9 14.5 21.50.2 0.0 11.9 23.8 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 CPU Usage (Summary) Monitor 8 16 24 32 40
SHOC Scalable HeterOgeneous Computing GPU Frequency Monitor Min Avg Max 21.40.2 225.0 269.9 400.0 21.50 225.0 271.2 400.0 21.50.2 225.0 264.9 400.0 OpenBenchmarking.org Megahertz, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Frequency Monitor 110 220 330 440 550
SHOC Scalable HeterOgeneous Computing GPU Memory Usage Monitor Min Avg Max 21.40.2 226 693 870 21.50 245 719 899 21.50.2 252 724 896 OpenBenchmarking.org Megabytes, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Memory Usage Monitor 200 400 600 800 1000
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max 21.40.2 5.1 5.3 7.1 21.50 5.2 5.4 7.2 21.50.2 5.2 5.5 7.2 OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Power Consumption Monitor 3 6 9 12 15
SHOC Scalable HeterOgeneous Computing GPU Temperature Monitor Min Avg Max 21.40.2 39.0 39.9 43.0 21.50 40.0 41.5 44.0 21.50.2 39.0 40.8 44.0 OpenBenchmarking.org Celsius, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Temperature Monitor 12 24 36 48 60
FAHBench OpenBenchmarking.org Ns Per Day, More Is Better FAHBench 2.3.2 21.40.2 21.50 21.50.2 9 18 27 36 45 SE +/- 0.11, N = 3 SE +/- 0.14, N = 3 SE +/- 0.35, N = 3 40.47 40.84 41.18
FAHBench CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 900 2797 4099 21.50 900 2811 4099 21.50.2 884 2824 4100 OpenBenchmarking.org Megahertz, More Is Better FAHBench 2.3.2 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
FAHBench CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 9.8 20.2 21.50 0.0 9.6 16.2 21.50.2 0.0 9.5 17.0 OpenBenchmarking.org Percent, Fewer Is Better FAHBench 2.3.2 CPU Usage (Summary) Monitor 6 12 18 24 30
FAHBench GPU Frequency Monitor Min Avg Max 21.40.2 225 648 1190 21.50 225 653 1190 21.50.2 225 649 1190 OpenBenchmarking.org Megahertz, More Is Better FAHBench 2.3.2 GPU Frequency Monitor 400 800 1200 1600 2000
FAHBench GPU Memory Usage Monitor Min Avg Max 21.40.2 217.0 307.3 317.0 21.50 254.0 339.0 346.0 21.50.2 243.0 334.5 344.0 OpenBenchmarking.org Megabytes, Fewer Is Better FAHBench 2.3.2 GPU Memory Usage Monitor 100 200 300 400 500
FAHBench GPU Power Consumption Monitor Min Avg Max 21.40.2 5.1 15.9 32.1 21.50 5.2 16.5 33.2 21.50.2 5.2 16.3 33.1 OpenBenchmarking.org Watts, Fewer Is Better FAHBench 2.3.2 GPU Power Consumption Monitor 10 20 30 40 50
FAHBench GPU Temperature Monitor Min Avg Max 21.40.2 38.0 45.8 57.0 21.50 39.0 46.9 57.0 21.50.2 38.0 46.6 57.0 OpenBenchmarking.org Celsius, Fewer Is Better FAHBench 2.3.2 GPU Temperature Monitor 16 32 48 64 80
FAHBench GPU Usage Monitor Min Avg Max 21.40.2 7.0 75.3 100.0 21.50 5.0 72.5 100.0 21.50.2 4.0 77.2 100.0 OpenBenchmarking.org Percent, Fewer Is Better FAHBench 2.3.2 GPU Usage Monitor 20 40 60 80 100
LuxMark OpenCL Device: GPU - Scene: Luxball HDR OpenBenchmarking.org Score, More Is Better LuxMark 3.1 OpenCL Device: GPU - Scene: Luxball HDR 21.40.2 21.50 21.50.2 2K 4K 6K 8K 10K SE +/- 25.70, N = 3 SE +/- 50.82, N = 3 SE +/- 18.84, N = 3 9664 9717 9665
LuxMark CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 900 1583 4098 21.50 900 1537 4098 21.50.2 900 1499 4099 OpenBenchmarking.org Megahertz, More Is Better LuxMark 3.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
LuxMark CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 1.7 20.6 21.50 0.0 0.7 16.0 21.50.2 0.0 1.4 25.7 OpenBenchmarking.org Percent, Fewer Is Better LuxMark 3.1 CPU Usage (Summary) Monitor 8 16 24 32 40
LuxMark GPU Frequency Monitor Min Avg Max 21.40.2 225 1152 1190 21.50 225 1152 1190 21.50.2 225 1153 1190 OpenBenchmarking.org Megahertz, More Is Better LuxMark 3.1 GPU Frequency Monitor 400 800 1200 1600 2000
LuxMark GPU Memory Usage Monitor Min Avg Max 21.40.2 226 744 792 21.50 254 775 821 21.50.2 252 773 818 OpenBenchmarking.org Megabytes, Fewer Is Better LuxMark 3.1 GPU Memory Usage Monitor 200 400 600 800 1000
LuxMark GPU Power Consumption Monitor Min Avg Max 21.40.2 5.2 34.9 37.1 21.50 6.0 35.3 37.2 21.50.2 6.0 34.9 37.0 OpenBenchmarking.org Watts, Fewer Is Better LuxMark 3.1 GPU Power Consumption Monitor 11 22 33 44 55
LuxMark GPU Temperature Monitor Min Avg Max 21.40.2 49.0 58.9 65.0 21.50 47.0 60.2 67.0 21.50.2 49.0 58.9 64.0 OpenBenchmarking.org Celsius, Fewer Is Better LuxMark 3.1 GPU Temperature Monitor 20 40 60 80 100
LuxMark GPU Usage Monitor Min Avg Max 21.40.2 22.0 98.5 100.0 21.50 6.0 98.9 100.0 21.50.2 28.0 98.4 100.0 OpenBenchmarking.org Percent, Fewer Is Better LuxMark 3.1 GPU Usage Monitor 20 40 60 80 100
LuxMark OpenCL Device: GPU - Scene: Microphone OpenBenchmarking.org Score, More Is Better LuxMark 3.1 OpenCL Device: GPU - Scene: Microphone 21.40.2 21.50 21.50.2 1400 2800 4200 5600 7000 SE +/- 16.50, N = 3 SE +/- 19.00, N = 3 SE +/- 17.04, N = 3 6421 6351 6423
LuxMark CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 900 1618 4099 21.50 900 1610 4099 21.50.2 900 1626 4100 OpenBenchmarking.org Megahertz, More Is Better LuxMark 3.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
LuxMark CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 2.5 34.3 21.50 0.0 2.0 33.4 21.50.2 0.0 2.3 29.5 OpenBenchmarking.org Percent, Fewer Is Better LuxMark 3.1 CPU Usage (Summary) Monitor 10 20 30 40 50
LuxMark GPU Frequency Monitor Min Avg Max 21.40.2 225 1131 1190 21.50 225 1131 1190 21.50.2 225 1132 1190 OpenBenchmarking.org Megahertz, More Is Better LuxMark 3.1 GPU Frequency Monitor 400 800 1200 1600 2000
LuxMark GPU Memory Usage Monitor Min Avg Max 21.40.2 228 1113 1161 21.50 256 1139 1190 21.50.2 254 1138 1188 OpenBenchmarking.org Megabytes, Fewer Is Better LuxMark 3.1 GPU Memory Usage Monitor 400 800 1200 1600 2000
LuxMark GPU Power Consumption Monitor Min Avg Max 21.40.2 5.2 33.3 37.1 21.50 6.0 33.7 37.2 21.50.2 6.0 33.1 37.1 OpenBenchmarking.org Watts, Fewer Is Better LuxMark 3.1 GPU Power Consumption Monitor 11 22 33 44 55
LuxMark GPU Temperature Monitor Min Avg Max 21.40.2 49.0 57.5 63.0 21.50 51.0 58.5 63.0 21.50.2 50.0 57.0 62.0 OpenBenchmarking.org Celsius, Fewer Is Better LuxMark 3.1 GPU Temperature Monitor 20 40 60 80 100
LuxMark GPU Usage Monitor Min Avg Max 21.40.2 44.0 98.9 100.0 21.50 4.0 98.1 100.0 21.50.2 4.0 98.8 100.0 OpenBenchmarking.org Percent, Fewer Is Better LuxMark 3.1 GPU Usage Monitor 20 40 60 80 100
LuxMark OpenCL Device: GPU - Scene: Hotel OpenBenchmarking.org Score, More Is Better LuxMark 3.1 OpenCL Device: GPU - Scene: Hotel 21.40.2 21.50 21.50.2 400 800 1200 1600 2000 SE +/- 5.78, N = 3 SE +/- 1.00, N = 3 SE +/- 5.70, N = 3 1686 1694 1691
LuxMark CPU Peak Freq (Highest CPU Core Frequency) Monitor Min Avg Max 21.40.2 900 1980 4099 21.50 900 1684 4099 21.50.2 900 1743 4099 OpenBenchmarking.org Megahertz, More Is Better LuxMark 3.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1100 2200 3300 4400 5500
LuxMark CPU Usage (Summary) Monitor Min Avg Max 21.40.2 0.0 3.8 95.3 21.50 0.0 3.1 63.8 21.50.2 0.0 2.6 72.6 OpenBenchmarking.org Percent, Fewer Is Better LuxMark 3.1 CPU Usage (Summary) Monitor 20 40 60 80 100
LuxMark GPU Frequency Monitor Min Avg Max 21.40.2 225 1084 1190 21.50 225 1085 1190 21.50.2 225 1087 1190 OpenBenchmarking.org Megahertz, More Is Better LuxMark 3.1 GPU Frequency Monitor 400 800 1200 1600 2000
LuxMark GPU Memory Usage Monitor Min Avg Max 21.40.2 226 1327 1393 21.50 252 1356 1421 21.50.2 249 1354 1419 OpenBenchmarking.org Megabytes, Fewer Is Better LuxMark 3.1 GPU Memory Usage Monitor 400 800 1200 1600 2000
LuxMark GPU Power Consumption Monitor Min Avg Max 21.40.2 5.1 30.6 35.2 21.50 5.2 31.3 36.1 21.50.2 5.2 30.9 35.3 OpenBenchmarking.org Watts, Fewer Is Better LuxMark 3.1 GPU Power Consumption Monitor 10 20 30 40 50
LuxMark GPU Temperature Monitor Min Avg Max 21.40.2 44.0 56.2 62.0 21.50 44.0 57.6 66.0 21.50.2 44.0 56.8 65.0 OpenBenchmarking.org Celsius, Fewer Is Better LuxMark 3.1 GPU Temperature Monitor 20 40 60 80 100
LuxMark GPU Usage Monitor Min Avg Max 21.40.2 63.0 99.3 100.0 21.50 1.0 98.3 100.0 21.50.2 40.0 99.2 100.0 OpenBenchmarking.org Percent, Fewer Is Better LuxMark 3.1 GPU Usage Monitor 20 40 60 80 100
CPU Peak Freq (Highest CPU Core Frequency) Monitor Phoronix Test Suite System Monitoring OpenBenchmarking.org Megahertz CPU Peak Freq (Highest CPU Core Frequency) Monitor Phoronix Test Suite System Monitoring 21.40.2 21.50 21.50.2 700 1400 2100 2800 3500 Min: 805 / Avg: 2314.18 / Max: 4101 Min: 860 / Avg: 2237.81 / Max: 4101 Min: 801 / Avg: 2250.84 / Max: 4101
CPU Usage (Summary) Monitor Phoronix Test Suite System Monitoring OpenBenchmarking.org Percent CPU Usage (Summary) Monitor Phoronix Test Suite System Monitoring 21.40.2 21.50 21.50.2 20 40 60 80 100 Min: 0 / Avg: 4.61 / Max: 95.31 Min: 0 / Avg: 4.41 / Max: 63.75 Min: 0 / Avg: 4.29 / Max: 72.59
GPU Frequency Monitor Phoronix Test Suite System Monitoring OpenBenchmarking.org Megahertz GPU Frequency Monitor Phoronix Test Suite System Monitoring 21.40.2 21.50 21.50.2 200 400 600 800 1000 Min: 225 / Avg: 737.57 / Max: 1190 Min: 225 / Avg: 735.48 / Max: 1190 Min: 225 / Avg: 738.88 / Max: 1190
GPU Memory Usage Monitor Phoronix Test Suite System Monitoring OpenBenchmarking.org Megabytes GPU Memory Usage Monitor Phoronix Test Suite System Monitoring 21.40.2 21.50 21.50.2 500 1000 1500 2000 2500 Min: 217 / Avg: 603.56 / Max: 2490 Min: 245 / Avg: 639.35 / Max: 2590 Min: 243 / Avg: 613.79 / Max: 2482
GPU Power Consumption Monitor Phoronix Test Suite System Monitoring OpenBenchmarking.org Watts GPU Power Consumption Monitor Phoronix Test Suite System Monitoring 21.40.2 21.50 21.50.2 10 20 30 40 50 Min: 5.05 / Avg: 19.56 / Max: 51.11 Min: 5.15 / Avg: 19.93 / Max: 49.03 Min: 5.15 / Avg: 19.6 / Max: 48.15
GPU Temperature Monitor Phoronix Test Suite System Monitoring OpenBenchmarking.org Celsius GPU Temperature Monitor Phoronix Test Suite System Monitoring 21.40.2 21.50 21.50.2 13 26 39 52 65 Min: 37 / Avg: 49.13 / Max: 65 Min: 38 / Avg: 50.1 / Max: 67 Min: 38 / Avg: 49.31 / Max: 65
GPU Usage Monitor Phoronix Test Suite System Monitoring OpenBenchmarking.org Percent GPU Usage Monitor Phoronix Test Suite System Monitoring 21.40.2 21.50 21.50.2 20 40 60 80 100 Min: 1 / Avg: 93.76 / Max: 100 Min: 1 / Avg: 92.64 / Max: 100 Min: 1 / Avg: 92.92 / Max: 100
SHOC Scalable HeterOgeneous Computing GPU Usage Monitor Min Avg Max 21.50 2.0 40.6 100.0 OpenBenchmarking.org Percent, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Usage Monitor 20 40 60 80 100
Phoronix Test Suite v10.8.4