OpenCL ROCm AMD AMD Ryzen 9 7950X 16-Core testing with a ASUS ROG CROSSHAIR X670E HERO (9922 BIOS) and Gigabyte AMD Radeon RX 6600 8GB on Ubuntu 23.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2303092-NE-OPENCLROC28&gru .
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 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 OpenBenchmarking.org - Transparent Huge Pages: madvise - --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 - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203 - BAR1 / Visible vRAM Size: 8176 MB - vBIOS Version: 113-D53201-R66E - 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 shoc: OpenCL - Triad shoc: OpenCL - Reduction shoc: OpenCL - Bus Speed Download shoc: OpenCL - Bus Speed Readback shoc: OpenCL - Texture Read Bandwidth clpeak: Global Memory Bandwidth clpeak: Transfer Bandwidth enqueueReadBuffer clpeak: Transfer Bandwidth enqueueWriteBuffer shoc: OpenCL - S3D clpeak: Double-Precision Compute clpeak: Single-Precision Compute shoc: OpenCL - GEMM SGEMM_N shoc: OpenCL - MD5 Hash clpeak: Integer Compute clpeak: Integer 24-bit Compute fluidx3d: FP32-FP32 fluidx3d: FP32-FP16C fluidx3d: FP32-FP16S lczero: OpenCL clpeak: Kernel Latency RX 6600 6.4413 207.898 7.1308 7.0694 589.766 191.31 4.98 23.03 80.3312 570.89 8117.45 1779.19 11.9076 2165.47 7891.46 965 1844 1822 14607 12.03 OpenBenchmarking.org
GPU Power Consumption Monitor Phoronix Test Suite System Monitoring Min Avg Max RX 6600 3.0 9.4 100.0 OpenBenchmarking.org Watts GPU Power Consumption Monitor Phoronix Test Suite System Monitoring 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 RX 6600 2 4 6 8 10 SE +/- 0.0504, N = 4 6.4413 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 RX 6600 0.2563 0.5126 0.7689 1.0252 1.2815 1.139
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 RX 6600 50 100 150 200 250 SE +/- 0.16, N = 4 207.90 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 RX 6600 5 10 15 20 25 20.85
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 RX 6600 2 4 6 8 10 SE +/- 0.0002, N = 4 7.1308 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 RX 6600 0.2349 0.4698 0.7047 0.9396 1.1745 1.044
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 RX 6600 2 4 6 8 10 SE +/- 0.0005, N = 4 7.0694 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 RX 6600 0.2504 0.5008 0.7512 1.0016 1.252 1.113
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 RX 6600 130 260 390 520 650 SE +/- 4.68, N = 9 589.77 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 RX 6600 8 16 24 32 40 35.50
clpeak OpenCL Test: Global Memory Bandwidth OpenBenchmarking.org GBPS, More Is Better clpeak 1.1.2 OpenCL Test: Global Memory Bandwidth RX 6600 40 80 120 160 200 SE +/- 0.40, N = 5 191.31 1. (CXX) g++ options: -O3
clpeak OpenCL Test: Transfer Bandwidth enqueueReadBuffer OpenBenchmarking.org GBPS, More Is Better clpeak 1.1.2 OpenCL Test: Transfer Bandwidth enqueueReadBuffer RX 6600 1.1205 2.241 3.3615 4.482 5.6025 SE +/- 0.05, N = 3 4.98 1. (CXX) g++ options: -O3
clpeak OpenCL Test: Transfer Bandwidth enqueueWriteBuffer OpenBenchmarking.org GBPS, More Is Better clpeak 1.1.2 OpenCL Test: Transfer Bandwidth enqueueWriteBuffer RX 6600 6 12 18 24 30 SE +/- 0.16, N = 15 23.03 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 RX 6600 2 4 6 8 10 6.868
clpeak OpenCL Test: Transfer Bandwidth enqueueReadBuffer OpenBenchmarking.org GBPS Per Watt, More Is Better clpeak 1.1.2 OpenCL Test: Transfer Bandwidth enqueueReadBuffer RX 6600 0.3686 0.7372 1.1058 1.4744 1.843 1.638
clpeak OpenCL Test: Transfer Bandwidth enqueueWriteBuffer OpenBenchmarking.org GBPS Per Watt, More Is Better clpeak 1.1.2 OpenCL Test: Transfer Bandwidth enqueueWriteBuffer RX 6600 2 4 6 8 10 7.529
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 RX 6600 3 6 9 12 15 11.91
clpeak OpenCL Test: Double-Precision Compute OpenBenchmarking.org GFLOPS Per Watt, More Is Better clpeak 1.1.2 OpenCL Test: Double-Precision Compute RX 6600 8 16 24 32 40 35.39
clpeak OpenCL Test: Single-Precision Compute OpenBenchmarking.org GFLOPS Per Watt, More Is Better clpeak 1.1.2 OpenCL Test: Single-Precision Compute RX 6600 200 400 600 800 1000 856.49
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 RX 6600 20 40 60 80 100 82.16
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 RX 6600 20 40 60 80 100 SE +/- 1.16, N = 3 80.33 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
clpeak OpenCL Test: Double-Precision Compute OpenBenchmarking.org GFLOPS, More Is Better clpeak 1.1.2 OpenCL Test: Double-Precision Compute RX 6600 120 240 360 480 600 SE +/- 0.52, N = 6 570.89 1. (CXX) g++ options: -O3
clpeak OpenCL Test: Single-Precision Compute OpenBenchmarking.org GFLOPS, More Is Better clpeak 1.1.2 OpenCL Test: Single-Precision Compute RX 6600 2K 4K 6K 8K 10K SE +/- 29.84, N = 7 8117.45 1. (CXX) g++ options: -O3
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 RX 6600 400 800 1200 1600 2000 SE +/- 4.57, N = 4 1779.19 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, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: MD5 Hash RX 6600 3 6 9 12 15 SE +/- 0.01, N = 4 11.91 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 RX 6600 0.2752 0.5504 0.8256 1.1008 1.376 1.223
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 RX 6600 200 400 600 800 1000 1112.68
clpeak OpenCL Test: Integer Compute OpenBenchmarking.org GIOPS, More Is Better clpeak 1.1.2 OpenCL Test: Integer Compute RX 6600 500 1000 1500 2000 2500 SE +/- 5.37, N = 7 2165.47 1. (CXX) g++ options: -O3
clpeak OpenCL Test: Integer 24-bit Compute OpenBenchmarking.org GIOPS, More Is Better clpeak 1.1.2 OpenCL Test: Integer 24-bit Compute RX 6600 2K 4K 6K 8K 10K SE +/- 31.77, N = 7 7891.46 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 RX 6600 30 60 90 120 150 147.13
FluidX3D Test: FP32-FP32 OpenBenchmarking.org MLUPs/s Per Watt, More Is Better FluidX3D 2.3 Test: FP32-FP32 RX 6600 4 8 12 16 20 16.11
FluidX3D Test: FP32-FP16C OpenBenchmarking.org MLUPs/s Per Watt, More Is Better FluidX3D 2.3 Test: FP32-FP16C RX 6600 5 10 15 20 25 22.69
FluidX3D Test: FP32-FP16S OpenBenchmarking.org MLUPs/s Per Watt, More Is Better FluidX3D 2.3 Test: FP32-FP16S RX 6600 7 14 21 28 35 28.22
FluidX3D Test: FP32-FP32 OpenBenchmarking.org MLUPs/s, More Is Better FluidX3D 2.3 Test: FP32-FP32 RX 6600 200 400 600 800 1000 SE +/- 0.33, N = 3 965
FluidX3D Test: FP32-FP16C OpenBenchmarking.org MLUPs/s, More Is Better FluidX3D 2.3 Test: FP32-FP16C RX 6600 400 800 1200 1600 2000 SE +/- 2.19, N = 3 1844
FluidX3D Test: FP32-FP16S OpenBenchmarking.org MLUPs/s, More Is Better FluidX3D 2.3 Test: FP32-FP16S RX 6600 400 800 1200 1600 2000 SE +/- 1.45, N = 3 1822
LeelaChessZero Backend: OpenCL OpenBenchmarking.org Nodes Per Second Per Watt, More Is Better LeelaChessZero 0.28 Backend: OpenCL RX 6600 30 60 90 120 150 156.10
LeelaChessZero Backend: OpenCL OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: OpenCL RX 6600 3K 6K 9K 12K 15K SE +/- 28.17, N = 3 14607 1. (CXX) g++ options: -flto -pthread
Meta Performance Per Watts Performance Per Watts OpenBenchmarking.org Performance Per Watts, More Is Better Meta Performance Per Watts Performance Per Watts RX 6600 11 22 33 44 55 50.55
clpeak OpenCL Test: Kernel Latency OpenBenchmarking.org us, Fewer Is Better clpeak 1.1.2 OpenCL Test: Kernel Latency RX 6600 3 6 9 12 15 SE +/- 0.13, N = 15 12.03 1. (CXX) g++ options: -O3
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 6.7 15.0 OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Power Consumption Monitor 5 10 15 20 25
FluidX3D GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 59.9 65.0 OpenBenchmarking.org Watts, Fewer Is Better FluidX3D 2.3 GPU Power Consumption Monitor 20 40 60 80 100
FluidX3D GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 81.3 90.0 OpenBenchmarking.org Watts, Fewer Is Better FluidX3D 2.3 GPU Power Consumption Monitor 20 40 60 80 100
FluidX3D GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 64.6 72.0 OpenBenchmarking.org Watts, Fewer Is Better FluidX3D 2.3 GPU Power Consumption Monitor 20 40 60 80 100
clpeak GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 4.3 19.0 OpenBenchmarking.org Watts, Fewer Is Better clpeak 1.1.2 GPU Power Consumption Monitor 6 12 18 24 30
clpeak GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 14.7 100.0 OpenBenchmarking.org Watts, Fewer Is Better clpeak 1.1.2 GPU Power Consumption Monitor 20 40 60 80 100
clpeak GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 7.1 100.0 OpenBenchmarking.org Watts, Fewer Is Better clpeak 1.1.2 GPU Power Consumption Monitor 20 40 60 80 100
clpeak GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 27.9 72.0 OpenBenchmarking.org Watts, Fewer Is Better clpeak 1.1.2 GPU Power Consumption Monitor 20 40 60 80 100
clpeak GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 16.1 82.0 OpenBenchmarking.org Watts, Fewer Is Better clpeak 1.1.2 GPU Power Consumption Monitor 20 40 60 80 100
clpeak GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 9.5 95.0 OpenBenchmarking.org Watts, Fewer Is Better clpeak 1.1.2 GPU Power Consumption Monitor 20 40 60 80 100
clpeak GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 3.0 4.0 OpenBenchmarking.org Watts, Fewer Is Better clpeak 1.1.2 GPU Power Consumption Monitor 1.125 2.25 3.375 4.5 5.625
clpeak GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 3.1 13.0 OpenBenchmarking.org Watts, Fewer Is Better clpeak 1.1.2 GPU Power Consumption Monitor 4 8 12 16 20
LeelaChessZero GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 93.6 100.0 OpenBenchmarking.org Watts, Fewer Is Better LeelaChessZero 0.28 GPU Power Consumption Monitor 20 40 60 80 100
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 5.7 24.0 OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Power Consumption Monitor 8 16 24 32 40
SHOC Scalable HeterOgeneous Computing GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 9.7 100.0 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 GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 10.0 65.0 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 GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 21.7 97.0 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 GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 6.8 30.0 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 GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 6.4 29.0 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 GPU Power Consumption Monitor Min Avg Max RX 6600 3.0 16.6 82.0 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