Vega 56 OpenCL

AMD Ryzen 7 3800X 8-Core testing with a ASUS CROSSHAIR VI HERO (7704 BIOS) and Sapphire AMD Radeon RX 56/64 8GB on Gentoo/Linux via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1912317-HU-VEGA56OPE86
Jump To Table - Results

Statistics

Remove Outliers Before Calculating Averages

Graph Settings

Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Vega 56
January 01 2020
  24 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


Vega 56 OpenCLOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 7 3800X 8-Core @ 3.90GHz (8 Cores / 16 Threads)ASUS CROSSHAIR VI HERO (7704 BIOS)AMD Starship/Matisse16384MB480GB KINGSTON SA1000M8480G + 500GB Seagate ST3500418AS + 1000GB Western Digital WD1003FZEX-0 + 240GB SanDisk SDSSDA24Sapphire AMD Radeon RX 56/64 8GB (1590/800MHz)AMD Vega 10 HDMI Audio2369MIntel I211Gentoo/Linux5.4.3-gentoo-ck1 (x86_64)KDE Plasma 5.17.4X Server 1.20.5modesetting 1.20.54.5 Mesa 19.3.1 (LLVM 9.0.0)OpenCL 2.0 AMD-APP.internal (3052.0)1.1.107GCC 9.2.0 + Clang 9.0.0 + LLVM 9.0.0ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionVega 56 OpenCL BenchmarksSystem Logs- amdgpu.ppfeaturemask=0xffffffff- --bindir=/usr/x86_64-pc-linux-gnu/gcc-bin/9.2.0 --build=x86_64-pc-linux-gnu --datadir=/usr/share/gcc-data/x86_64-pc-linux-gnu/9.2.0 --disable-altivec --disable-esp --disable-fixed-point --disable-isl-version-check --disable-libmudflap --disable-libssp --disable-systemtap --disable-werror --enable-__cxa_atexit --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-languages=c,c++,fortran --enable-libgomp --enable-libstdcxx-time --enable-lto --enable-multilib --enable-nls --enable-obsolete --enable-secureplt --enable-shared --enable-targets=all --enable-threads=posix --enable-vtable-verify --host=x86_64-pc-linux-gnu --includedir=/usr/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include --mandir=/usr/share/gcc-data/x86_64-pc-linux-gnu/9.2.0/man --with-build-config=bootstrap-lto --with-isl --with-multilib-list=m32,m64 --with-python-dir=/share/gcc-data/x86_64-pc-linux-gnu/9.2.0/python - Scaling Governor: acpi-cpufreq schedutil - CPU Microcode: 0x8701013- GLAMOR- Python 3.6.9- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + 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 AMD retpoline IBPB: conditional STIBP: conditional RSB filling + tsx_async_abort: Not affected

Vega 56 OpenCLshoc: OpenCL - Triadshoc: OpenCL - FFT SPshoc: OpenCL - Max SP Flopsshoc: OpenCL - Bus Speed Downloadshoc: OpenCL - Bus Speed Readbackcl-mem: Copycl-mem: Readcl-mem: Writeparboil: OpenCL BFSparboil: OpenCL LBMparboil: OpenCL TPACFrodinia: OpenCL Heartwallsmallpt-gpu: GPU - 1920 x 1080 - Causticsmallpt-gpu: GPU - 1920 x 1080 - Cornellsmallpt-gpu: GPU - 1920 x 1080 - Caustic3clpeak: Kernel Latencyclpeak: Integer Compute INTclpeak: Single-Precision Floatclpeak: Double-Precision Doubleclpeak: Global Memory Bandwidthclpeak: Transfer Bandwidth enqueueReadBufferclpeak: Transfer Bandwidth enqueueWriteBufferVega 567.9518951.6232714729.58489.0251197.0349.4341.41.4627659.2289411.5355063.2881577849958157785009315778502299.472049.6510627.16707.74318.8421.8229.70OpenBenchmarking.org

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: TriadVega 56246810SE +/- 0.0679, N = 37.95181. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: FFT SPVega 562004006008001000SE +/- 1.02, N = 3951.621. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Max SP FlopsVega 5660K120K180K240K300KSE +/- 259.45, N = 32714721. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Bus Speed DownloadVega 563691215SE +/- 0.0030, N = 39.58481. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Bus Speed ReadbackVega 563691215SE +/- 0.0019, N = 39.02511. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

cl-mem

A basic OpenCL memory benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyVega 564080120160200SE +/- 0.15, N = 3197.01. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadVega 5680160240320400SE +/- 0.03, N = 3349.41. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteVega 5670140210280350SE +/- 0.06, N = 3341.41. (CC) gcc options: -O2 -flto -lOpenCL

Parboil

The Parboil Benchmarks from the IMPACT Research Group at University of Illinois are a set of throughput computing applications for looking at computing architecture and compilers. Parboil test-cases support OpenMP, OpenCL, and CUDA multi-processing environments. However, at this time the test profile is just making use of the OpenMP and OpenCL test workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenCL BFSVega 560.32910.65820.98731.31641.6455SE +/- 0.007074, N = 31.4627651. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenCL LBMVega 563691215SE +/- 0.029134, N = 39.2289411. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenCL TPACFVega 560.34550.6911.03651.3821.7275SE +/- 0.013381, N = 31.5355061. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes the OpenCL and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenCL HeartwallVega 560.73981.47962.21942.95923.699SE +/- 0.011, N = 33.2881. (CXX) g++ options: -O2 -lOpenCL

SmallPT GPU

SmallPT GPU is an OpenCL benchmark that's run with various PTS changes compared to upstream and multiple rendering scenes are available. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSamples/sec, More Is BetterSmallPT GPU 1.6pts1OpenCL Device: GPU - Resolution: 1920 x 1080 - Scene: CausticVega 56300M600M900M1200M1500MSE +/- 25.12, N = 315778499581. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

OpenBenchmarking.orgSamples/sec, More Is BetterSmallPT GPU 1.6pts1OpenCL Device: GPU - Resolution: 1920 x 1080 - Scene: CornellVega 56300M600M900M1200M1500MSE +/- 24.25, N = 315778500931. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

OpenBenchmarking.orgSamples/sec, More Is BetterSmallPT GPU 1.6pts1OpenCL Device: GPU - Resolution: 1920 x 1080 - Scene: Caustic3Vega 56300M600M900M1200M1500MSE +/- 25.12, N = 315778502291. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus, Fewer Is BetterclpeakOpenCL Test: Kernel LatencyVega 563691215SE +/- 0.06, N = 39.471. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTVega 56400800120016002000SE +/- 1.45, N = 32049.651. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision FloatVega 562K4K6K8K10KSE +/- 3.52, N = 310627.161. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision DoubleVega 56150300450600750SE +/- 0.67, N = 3707.741. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory BandwidthVega 5670140210280350SE +/- 0.22, N = 3318.841. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Transfer Bandwidth enqueueReadBufferVega 56510152025SE +/- 0.04, N = 321.821. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Transfer Bandwidth enqueueWriteBufferVega 56714212835SE +/- 0.02, N = 329.701. (CXX) g++ options: -O3 -rdynamic -lOpenCL