OpenCL ROCm AMD AMD Ryzen 9 7950X 16-Core testing with a ASUS ROG CROSSHAIR X670E HERO (9922 BIOS) and Sapphire AMD Radeon RX 6500 XT 4GB on Ubuntu 23.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2303112-NE-OPENCLROC53&grt&sro .
OpenCL ROCm AMD Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL OpenCL Compiler File-System Screen Resolution RX 6600 RX 6700 XT 6700 XT AMD 6700XT RX 6500 XT AMD Ryzen 9 7950X 16-Core @ 4.50GHz (16 Cores / 32 Threads) ASUS ROG CROSSHAIR X670E HERO (9922 BIOS) AMD Device 14d8 2 x 16 GB DDR5-6000MT/s F5-6000J3038F16G Western Digital WD_BLACK SN850X 1000GB + 2000GB Gigabyte AMD Radeon RX 6600 8GB (2750/875MHz) AMD Navi 21/23 ASUS MG28U Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411 Ubuntu 23.04 6.2.2-060202-generic (x86_64) GNOME Shell 43.2 X Server 1.21.1.6 4.6 Mesa 23.1.0-devel (git-5f5e30b 2023-03-09 lunar-oibaf-ppa) (LLVM 15.0.7 DRM 3.49) OpenCL 2.1 AMD-APP (3513.0) GCC 12.2.0 ext4 3840x2160 AMD Radeon RX 6700 XT 12GB (2855/1000MHz) Sapphire AMD Radeon RX 6500 XT 4GB (2975/1124MHz) OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-EzbZRD/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-EzbZRD/gcc-12-12.2.0/debian/tmp-gcn/usr --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 Processor Details - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203 Graphics Details - RX 6600: BAR1 / Visible vRAM Size: 8176 MB - vBIOS Version: 113-D53201-R66E - RX 6700 XT: BAR1 / Visible vRAM Size: 12272 MB - vBIOS Version: 113-D5121100-101 - 6700 XT: BAR1 / Visible vRAM Size: 12272 MB - vBIOS Version: 113-D5121100-101 - AMD 6700XT: BAR1 / Visible vRAM Size: 12272 MB - vBIOS Version: 113-D5121100-101 - RX 6500 XT: BAR1 / Visible vRAM Size: 4080 MB - vBIOS Version: 113-D6320100-S06 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
OpenCL ROCm AMD clpeak: Kernel Latency clpeak: Integer Compute clpeak: Integer 24-bit Compute clpeak: Global Memory Bandwidth clpeak: Double-Precision Compute clpeak: Single-Precision Compute clpeak: Transfer Bandwidth enqueueReadBuffer clpeak: Transfer Bandwidth enqueueWriteBuffer fluidx3d: FP32-FP32 fluidx3d: FP32-FP16C fluidx3d: FP32-FP16S lczero: OpenCL shoc: OpenCL - S3D shoc: OpenCL - Triad shoc: OpenCL - MD5 Hash shoc: OpenCL - Reduction shoc: OpenCL - GEMM SGEMM_N shoc: OpenCL - Bus Speed Download shoc: OpenCL - Bus Speed Readback shoc: OpenCL - Texture Read Bandwidth RX 6600 RX 6700 XT 6700 XT AMD 6700XT RX 6500 XT 11.80 2164.23 7831.73 191.26 569.74 8032.82 4.97 22.64 962 1838 1816 14791 79.7646 12.2654 11.8971 208.076 1778.07 14.3363 14.0904 603.589 13.39 2991.01 10802.43 311.69 807.53 11441.23 4.99 22.65 1382 2793 2786 19460 110.295 23.6167 16.3937 626.308 4337.60 28.8561 26.4047 641.156 13.11 2986.9 10793.54 310.6 807.78 11246.9 5.07 22.82 1375 2789 2785 19699 111.154 24.0596 16.4005 624.597 4608.74 28.8549 26.3997 661.364 13.21 2994.05 10709.57 310.61 810.76 11260.17 5.04 22.15 1377 2828 2805 19930 108.208 23.0553 16.397 626.408 4550.61 28.8561 26.4033 647.199 11.45 1270.59 4680.82 122.86 336.00 4790.97 5.01 23.52 495 1030 1011 7390 23.5439 6.3591 7.0820 139.266 1063.03 7.1636 7.0477 535.113 OpenBenchmarking.org
clpeak OpenCL Test: Kernel Latency OpenBenchmarking.org us, Fewer Is Better clpeak 1.1.2 OpenCL Test: Kernel Latency 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 3 6 9 12 15 SE +/- 0.09, N = 3 SE +/- 0.10, N = 15 SE +/- 0.10, N = 15 13.11 13.21 11.45 11.80 13.39 1. (CXX) g++ options: -O3
clpeak GPU Power Consumption Monitor Min Avg Max 6700 XT 5.0 5.1 6.0 AMD 6700XT 5.0 7.1 26.0 RX 6600 3.0 4.8 19.0 RX 6700 XT 4.0 6.1 26.0 OpenBenchmarking.org Watts, Fewer Is Better clpeak 1.1.2 GPU Power Consumption Monitor 8 16 24 32 40
clpeak OpenCL Test: Integer Compute OpenBenchmarking.org GIOPS, More Is Better clpeak 1.1.2 OpenCL Test: Integer Compute 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 600 1200 1800 2400 3000 SE +/- 3.85, N = 3 SE +/- 6.13, N = 7 SE +/- 3.08, N = 7 2986.90 2994.05 1270.59 2164.23 2991.01 1. (CXX) g++ options: -O3
clpeak OpenCL Test: Integer Compute OpenBenchmarking.org GIOPS Per Watt, More Is Better clpeak 1.1.2 OpenCL Test: Integer Compute 6700 XT AMD 6700XT RX 6600 RX 6700 XT 40 80 120 160 200 160.59 147.69 142.02 139.75
clpeak GPU Power Consumption Monitor Min Avg Max 6700 XT 5.0 18.6 141.0 AMD 6700XT 5.0 20.3 129.0 RX 6600 3.0 15.2 100.0 RX 6700 XT 4.0 21.4 142.0 OpenBenchmarking.org Watts, Fewer Is Better clpeak 1.1.2 GPU Power Consumption Monitor 40 80 120 160 200
clpeak OpenCL Test: Integer 24-bit Compute OpenBenchmarking.org GIOPS, More Is Better clpeak 1.1.2 OpenCL Test: Integer 24-bit Compute 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 2K 4K 6K 8K 10K SE +/- 11.19, N = 3 SE +/- 14.90, N = 7 SE +/- 16.15, N = 7 10793.54 10709.57 4680.82 7831.73 10802.43 1. (CXX) g++ options: -O3
clpeak OpenCL Test: Integer 24-bit Compute OpenBenchmarking.org GIOPS Per Watt, More Is Better clpeak 1.1.2 OpenCL Test: Integer 24-bit Compute 6700 XT AMD 6700XT RX 6600 RX 6700 XT 300 600 900 1200 1500 691.89 1554.62 938.10 954.02
clpeak GPU Power Consumption Monitor Min Avg Max 6700 XT 4.0 15.6 112.0 AMD 6700XT 4.0 6.9 25.0 RX 6600 3.0 8.3 100.0 RX 6700 XT 4.0 11.3 161.0 OpenBenchmarking.org Watts, Fewer Is Better clpeak 1.1.2 GPU Power Consumption Monitor 50 100 150 200 250
clpeak OpenCL Test: Global Memory Bandwidth OpenBenchmarking.org GBPS, More Is Better clpeak 1.1.2 OpenCL Test: Global Memory Bandwidth 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 70 140 210 280 350 SE +/- 0.31, N = 3 SE +/- 0.57, N = 5 SE +/- 0.82, N = 5 310.60 310.61 122.86 191.26 311.69 1. (CXX) g++ options: -O3
clpeak OpenCL Test: Global Memory Bandwidth OpenBenchmarking.org GBPS Per Watt, More Is Better clpeak 1.1.2 OpenCL Test: Global Memory Bandwidth 6700 XT AMD 6700XT RX 6600 RX 6700 XT 3 6 9 12 15 10.120 7.933 6.714 9.043
clpeak GPU Power Consumption Monitor Min Avg Max 6700 XT 5.0 30.7 118.0 AMD 6700XT 5.0 39.2 120.0 RX 6600 3.0 28.5 72.0 RX 6700 XT 4.0 34.5 123.0 OpenBenchmarking.org Watts, Fewer Is Better clpeak 1.1.2 GPU Power Consumption Monitor 40 80 120 160 200
clpeak OpenCL Test: Double-Precision Compute OpenBenchmarking.org GFLOPS, More Is Better clpeak 1.1.2 OpenCL Test: Double-Precision Compute 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 200 400 600 800 1000 SE +/- 0.44, N = 3 SE +/- 1.11, N = 6 SE +/- 0.76, N = 6 807.78 810.76 336.00 569.74 807.53 1. (CXX) g++ options: -O3
clpeak OpenCL Test: Double-Precision Compute OpenBenchmarking.org GFLOPS Per Watt, More Is Better clpeak 1.1.2 OpenCL Test: Double-Precision Compute 6700 XT AMD 6700XT RX 6600 RX 6700 XT 9 18 27 36 45 37.33 32.43 34.86 35.80
clpeak GPU Power Consumption Monitor Min Avg Max 6700 XT 4.0 21.6 81.0 AMD 6700XT 5.0 25.0 98.0 RX 6600 3.0 16.3 80.0 RX 6700 XT 4.0 22.6 97.0 OpenBenchmarking.org Watts, Fewer Is Better clpeak 1.1.2 GPU Power Consumption Monitor 20 40 60 80 100
clpeak OpenCL Test: Single-Precision Compute OpenBenchmarking.org GFLOPS, More Is Better clpeak 1.1.2 OpenCL Test: Single-Precision Compute 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 2K 4K 6K 8K 10K SE +/- 48.42, N = 3 SE +/- 27.15, N = 7 SE +/- 41.68, N = 7 11246.90 11260.17 4790.97 8032.82 11441.23 1. (CXX) g++ options: -O3
clpeak OpenCL Test: Single-Precision Compute OpenBenchmarking.org GFLOPS Per Watt, More Is Better clpeak 1.1.2 OpenCL Test: Single-Precision Compute 6700 XT AMD 6700XT RX 6600 RX 6700 XT 400 800 1200 1600 2000 1984.75 647.14 839.62 916.94
clpeak GPU Power Consumption Monitor Min Avg Max 6700 XT 4.0 5.7 10.0 AMD 6700XT 4.0 17.4 130.0 RX 6600 3.0 9.6 94.0 RX 6700 XT 4.0 12.5 135.0 OpenBenchmarking.org Watts, Fewer Is Better clpeak 1.1.2 GPU Power Consumption Monitor 40 80 120 160 200
clpeak OpenCL Test: Transfer Bandwidth enqueueReadBuffer OpenBenchmarking.org GBPS, More Is Better clpeak 1.1.2 OpenCL Test: Transfer Bandwidth enqueueReadBuffer 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 1.1408 2.2816 3.4224 4.5632 5.704 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 5.07 5.04 5.01 4.97 4.99 1. (CXX) g++ options: -O3
clpeak OpenCL Test: Transfer Bandwidth enqueueReadBuffer OpenBenchmarking.org GBPS Per Watt, More Is Better clpeak 1.1.2 OpenCL Test: Transfer Bandwidth enqueueReadBuffer 6700 XT AMD 6700XT RX 6600 RX 6700 XT 0.351 0.702 1.053 1.404 1.755 1.225 1.235 1.560 1.229
clpeak GPU Power Consumption Monitor Min Avg Max 6700 XT 4.0 4.1 5.0 AMD 6700XT 4.0 4.1 5.0 RX 6600 3.0 3.2 8.0 RX 6700 XT 4.0 4.1 11.0 OpenBenchmarking.org Watts, Fewer Is Better clpeak 1.1.2 GPU Power Consumption Monitor 4 8 12 16 20
clpeak OpenCL Test: Transfer Bandwidth enqueueWriteBuffer OpenBenchmarking.org GBPS, More Is Better clpeak 1.1.2 OpenCL Test: Transfer Bandwidth enqueueWriteBuffer 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 6 12 18 24 30 SE +/- 0.20, N = 15 SE +/- 0.18, N = 15 SE +/- 0.01, N = 3 22.82 22.15 23.52 22.64 22.65 1. (CXX) g++ options: -O3
clpeak OpenCL Test: Transfer Bandwidth enqueueWriteBuffer OpenBenchmarking.org GBPS Per Watt, More Is Better clpeak 1.1.2 OpenCL Test: Transfer Bandwidth enqueueWriteBuffer 6700 XT AMD 6700XT RX 6600 RX 6700 XT 2 4 6 8 10 5.539 5.279 7.173 5.644
clpeak GPU Power Consumption Monitor Min Avg Max 6700 XT 4.0 4.1 5.0 AMD 6700XT 4.0 4.2 5.0 RX 6600 3.0 3.2 8.0 RX 6700 XT 4.0 4.0 5.0 OpenBenchmarking.org Watts, Fewer Is Better clpeak 1.1.2 GPU Power Consumption Monitor 3 6 9 12 15
FluidX3D Test: FP32-FP32 OpenBenchmarking.org MLUPs/s, More Is Better FluidX3D 2.3 Test: FP32-FP32 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 300 600 900 1200 1500 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 4.84, N = 3 1375 1377 495 962 1382
FluidX3D Test: FP32-FP32 OpenBenchmarking.org MLUPs/s Per Watt, More Is Better FluidX3D 2.3 Test: FP32-FP32 6700 XT AMD 6700XT RX 6600 RX 6700 XT 4 8 12 16 20 14.07 14.02 16.11 13.82
FluidX3D GPU Power Consumption Monitor Min Avg Max 6700 XT 4.0 97.7 107.0 AMD 6700XT 4.0 98.2 107.0 RX 6600 3.0 59.7 65.0 RX 6700 XT 4.0 100.0 110.0 OpenBenchmarking.org Watts, Fewer Is Better FluidX3D 2.3 GPU Power Consumption Monitor 20 40 60 80 100
FluidX3D Test: FP32-FP16C OpenBenchmarking.org MLUPs/s, More Is Better FluidX3D 2.3 Test: FP32-FP16C 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 600 1200 1800 2400 3000 SE +/- 0.88, N = 3 SE +/- 2.19, N = 3 SE +/- 2.03, N = 3 2789 2828 1030 1838 2793
FluidX3D Test: FP32-FP16C OpenBenchmarking.org MLUPs/s Per Watt, More Is Better FluidX3D 2.3 Test: FP32-FP16C 6700 XT AMD 6700XT RX 6600 RX 6700 XT 5 10 15 20 25 21.12 21.17 22.52 20.86
FluidX3D GPU Power Consumption Monitor Min Avg Max 6700 XT 5.0 132.1 155.0 AMD 6700XT 4.0 133.6 155.0 RX 6600 3.0 81.6 91.0 RX 6700 XT 5.0 133.9 156.0 OpenBenchmarking.org Watts, Fewer Is Better FluidX3D 2.3 GPU Power Consumption Monitor 40 80 120 160 200
FluidX3D Test: FP32-FP16S OpenBenchmarking.org MLUPs/s, More Is Better FluidX3D 2.3 Test: FP32-FP16S 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 600 1200 1800 2400 3000 SE +/- 0.58, N = 3 SE +/- 0.88, N = 3 SE +/- 6.36, N = 3 2785 2805 1011 1816 2786
FluidX3D Test: FP32-FP16S OpenBenchmarking.org MLUPs/s Per Watt, More Is Better FluidX3D 2.3 Test: FP32-FP16S 6700 XT AMD 6700XT RX 6600 RX 6700 XT 7 14 21 28 35 26.31 26.45 28.09 26.03
FluidX3D GPU Power Consumption Monitor Min Avg Max 6700 XT 4.0 105.9 123.0 AMD 6700XT 5.0 106.1 124.0 RX 6600 3.0 64.6 72.0 RX 6700 XT 4.0 107.0 124.0 OpenBenchmarking.org Watts, Fewer Is Better FluidX3D 2.3 GPU Power Consumption Monitor 40 80 120 160 200
GPU Power Consumption Monitor Phoronix Test Suite System Monitoring OpenBenchmarking.org Watts GPU Power Consumption Monitor Phoronix Test Suite System Monitoring 6700 XT AMD 6700XT RX 6600 RX 6700 XT 30 60 90 120 150 Min: 4 / Avg: 62.11 / Max: 188 Min: 4 / Avg: 62.25 / Max: 187 Min: 3 / Avg: 38.83 / Max: 100 Min: 4 / Avg: 66.55 / Max: 188
LeelaChessZero Backend: OpenCL OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: OpenCL 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 4K 8K 12K 16K 20K SE +/- 6.69, N = 3 SE +/- 29.31, N = 3 SE +/- 146.89, N = 3 19699 19930 7390 14791 19460 1. (CXX) g++ options: -flto -pthread
LeelaChessZero Backend: OpenCL OpenBenchmarking.org Nodes Per Second Per Watt, More Is Better LeelaChessZero 0.28 Backend: OpenCL 6700 XT AMD 6700XT RX 6600 RX 6700 XT 30 60 90 120 150 112.72 114.22 152.26 115.31
LeelaChessZero GPU Power Consumption Monitor Min Avg Max 6700 XT 4.0 174.8 188.0 AMD 6700XT 4.0 174.5 187.0 RX 6600 3.0 97.1 100.0 RX 6700 XT 4.0 168.8 188.0 OpenBenchmarking.org Watts, Fewer Is Better LeelaChessZero 0.28 GPU Power Consumption Monitor 50 100 150 200 250
Meta Performance Per Watts Performance Per Watts OpenBenchmarking.org Performance Per Watts, More Is Better Meta Performance Per Watts Performance Per Watts 6700 XT AMD 6700XT RX 6600 RX 6700 XT 90 180 270 360 450 435.92 433.56 284.22 433.14
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 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 20 40 60 80 100 SE +/- 0.95, N = 15 SE +/- 0.18, N = 3 SE +/- 0.83, N = 11 111.15 108.21 23.54 79.76 110.30 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: S3D OpenBenchmarking.org GFLOPS Per Watt, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: S3D 6700 XT AMD 6700XT RX 6600 RX 6700 XT 3 6 9 12 15 13.05 11.88 12.16 12.52
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max 6700 XT 4.0 8.5 21.0 AMD 6700XT 4.0 9.1 21.0 RX 6600 3.0 6.6 15.0 RX 6700 XT 4.0 8.8 21.0 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 Target: OpenCL - Benchmark: Triad OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Triad 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 6 12 18 24 30 SE +/- 0.0647, N = 3 SE +/- 0.0985, N = 15 SE +/- 0.1999, N = 4 24.0596 23.0553 6.3591 12.2654 23.6167 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Triad OpenBenchmarking.org GB/s Per Watt, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Triad 6700 XT AMD 6700XT RX 6600 RX 6700 XT 0.8442 1.6884 2.5326 3.3768 4.221 3.752 3.384 2.125 3.497
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max 6700 XT 5.0 6.4 28.0 AMD 6700XT 5.0 6.8 29.0 RX 6600 3.0 5.8 24.0 RX 6700 XT 5.0 6.8 28.0 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 Target: OpenCL - Benchmark: MD5 Hash OpenBenchmarking.org GHash/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: MD5 Hash 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 4 8 12 16 20 SE +/- 0.0003, N = 3 SE +/- 0.0013, N = 4 SE +/- 0.0023, N = 4 16.4005 16.3970 7.0820 11.8971 16.3937 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: MD5 Hash OpenBenchmarking.org GHash/s Per Watt, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: MD5 Hash 6700 XT AMD 6700XT RX 6600 RX 6700 XT 0.2581 0.5162 0.7743 1.0324 1.2905 0.968 1.093 1.147 1.002
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max 6700 XT 5.0 16.9 174.0 AMD 6700XT 5.0 15.0 175.0 RX 6600 3.0 10.4 100.0 RX 6700 XT 4.0 16.4 176.0 OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Power Consumption Monitor 50 100 150 200 250
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 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 140 280 420 560 700 SE +/- 0.02, N = 3 SE +/- 0.14, N = 4 SE +/- 1.07, N = 4 624.60 626.41 139.27 208.08 626.31 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Reduction OpenBenchmarking.org GB/s Per Watt, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Reduction 6700 XT AMD 6700XT RX 6600 RX 6700 XT 16 32 48 64 80 67.07 73.44 20.34 70.82
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max 6700 XT 5.0 9.3 73.0 AMD 6700XT 5.0 8.5 63.0 RX 6600 4.0 10.2 65.0 RX 6700 XT 4.0 8.8 79.0 OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Power Consumption 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 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 1000 2000 3000 4000 5000 SE +/- 1.40, N = 3 SE +/- 3.55, N = 4 SE +/- 57.13, N = 15 4608.74 4550.61 1063.03 1778.07 4337.60 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: GEMM SGEMM_N OpenBenchmarking.org GFLOPS Per Watt, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: GEMM SGEMM_N 6700 XT AMD 6700XT RX 6600 RX 6700 XT 60 120 180 240 300 227.59 275.30 102.61 228.49
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max 6700 XT 5.0 20.3 161.0 AMD 6700XT 5.0 16.5 164.0 RX 6600 3.0 17.3 99.0 RX 6700 XT 4.0 19.0 174.0 OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Power Consumption Monitor 50 100 150 200 250
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 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 7 14 21 28 35 SE +/- 0.0003, N = 3 SE +/- 0.0012, N = 4 SE +/- 0.0008, N = 4 28.8549 28.8561 7.1636 14.3363 28.8561 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Bus Speed Download OpenBenchmarking.org GB/s Per Watt, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Download 6700 XT AMD 6700XT RX 6600 RX 6700 XT 1.2402 2.4804 3.7206 4.9608 6.201 5.512 4.157 2.789 4.461
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max 6700 XT 4.0 5.2 10.0 AMD 6700XT 4.0 6.9 40.0 RX 6600 3.0 5.1 31.0 RX 6700 XT 4.0 6.5 44.0 OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Power Consumption Monitor 12 24 36 48 60
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 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 6 12 18 24 30 SE +/- 0.0002, N = 3 SE +/- 0.0085, N = 4 SE +/- 0.0007, N = 4 26.3997 26.4033 7.0477 14.0904 26.4047 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Bus Speed Readback OpenBenchmarking.org GB/s Per Watt, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Readback 6700 XT AMD 6700XT RX 6600 RX 6700 XT 0.9799 1.9598 2.9397 3.9196 4.8995 4.234 3.772 2.662 4.355
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max 6700 XT 4.0 6.2 37.0 AMD 6700XT 4.0 7.0 42.0 RX 6600 3.0 5.3 32.0 RX 6700 XT 4.0 6.1 42.0 OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Power Consumption Monitor 12 24 36 48 60
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 6700 XT AMD 6700XT RX 6500 XT RX 6600 RX 6700 XT 140 280 420 560 700 SE +/- 2.35, N = 3 SE +/- 3.98, N = 15 SE +/- 1.16, N = 4 661.36 647.20 535.11 603.59 641.16 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Texture Read Bandwidth OpenBenchmarking.org GB/s Per Watt, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Texture Read Bandwidth 6700 XT AMD 6700XT RX 6600 RX 6700 XT 9 18 27 36 45 36.74 36.07 38.22 33.83
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max 6700 XT 4.0 18.0 89.0 AMD 6700XT 4.0 17.9 90.0 RX 6600 3.0 15.8 83.0 RX 6700 XT 4.0 19.0 84.0 OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Power Consumption Monitor 20 40 60 80 100
Phoronix Test Suite v10.8.5