NVIDIA vs. Radeon OpenCL Linux GPU Compute

NVIDIA Linux GPU computing benchmarks by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1901304-SP-1901305SP07
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Additional Graphs

Show Perf Per Clock Calculation Graphs Where Applicable

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
GTX 1060
January 27 2019
  27 Minutes
GTX 1070
January 25 2019
  23 Minutes
GTX 1070 Ti
January 25 2019
  24 Minutes
GTX 1080
January 25 2019
  23 Minutes
GTX 1080 Ti
January 25 2019
  22 Minutes
RTX 2060
January 27 2019
  23 Minutes
RTX 2070
January 27 2019
  22 Minutes
RTX 2080
January 26 2019
  22 Minutes
RTX 2080 Ti
January 26 2019
  22 Minutes
TITAN RTX
January 26 2019
  22 Minutes
RX 580
January 28 2019
  1 Hour, 3 Minutes
RX 590
January 29 2019
  1 Hour, 1 Minute
RX Vega 56
January 28 2019
  56 Minutes
RX Vega 64
January 28 2019
  53 Minutes
amdocl
January 30 2019
  1 Hour, 1 Minute
Invert Behavior (Only Show Selected Data)
  35 Minutes

Only show results where is faster than
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):


NVIDIA vs. Radeon OpenCL Linux GPU ComputeProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiTITAN RTXRX 580RX 590RX Vega 56RX Vega 64amdoclIntel Core i9-9900K @ 5.00GHz (8 Cores / 16 Threads)ASUS PRIME Z390-A (0602 BIOS)Intel Cannon Lake PCH Shared SRAM16384MBSamsung SSD 970 EVO 250GB + 2000GB SABRENTNVIDIA GeForce GTX 1060 6GB (1506/4006MHz)Realtek ALC1220Acer B286HKIntel I219-VUbuntu 18.104.20.3-042003-generic (x86_64)GNOME Shell 3.30.1X Server 1.20.1NVIDIA 415.274.6.0OpenCL 1.2 CUDA 10.0.1321.1.84GCC 8.2.0ext43840x2160NVIDIA GeForce GTX 1070 8GB (1506/4006MHz)Zotac NVIDIA GeForce GTX 1070 Ti 8GB (1607/4006MHz)NVIDIA GeForce GTX 1080 8GB (1607/5005MHz)NVIDIA GeForce GTX 1080 Ti 11GB (1480/5508MHz)NVIDIA GeForce RTX 2060 6GB (1365/7000MHz)ASUS NVIDIA GeForce RTX 2070 8GB (1410/7000MHz)Zotac NVIDIA GeForce RTX 2080 8GB (1515/7000MHz)NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz)NVIDIA TITAN RTX 24GB (1350/7000MHz)MSI AMD Radeon RX 470/480/570/570X/580/580X 8GB (1366/2000MHz)5.0.0-050000rc4-generic (x86_64) 201901274.5 Mesa 19.0.0-devel padoka PPA (LLVM 9.0.0)OpenCL 2.1 AMD-APP (2783.0)1.1.90Sapphire AMD Radeon RX 470/480/570/570X/580/580X 8GB (1560/2100MHz)AMD Radeon RX 64 8GB (1590/800MHz)AMD Radeon RX 64 8GB (1630/945MHz)AMD Ryzen 7 2700 Eight-Core @ 3.20GHz (8 Cores / 16 Threads)ASRock X370 Taichi (P5.10 BIOS)AMD Family 17h32768MB1024GB INTEL SSDPEKKW010T7 + Samsung SSD 960 EVO 500GB + 512GB Crucial_CT512M55 + 1000GB SanDisk SDSSDH31 + 2000GB SanDisk SDSSDH32AMD Radeon RX 56/64 8GB (1590/800MHz)AMD Device aaf8SAMSUNGIntel I211Arch rolling4.20.5-zen1-1-zen (x86_64)KDE Plasma 5.14.5X Server 1.20.3amdgpu 18.1.04.5 Mesa 19.0.0-devel (git-69edc972fc) (LLVM 9.0.0)OpenCL 2.1 AMD-APP (2766.4)Clang 7.0.1 + LLVM 7.0.1xfsOpenBenchmarking.orgCompiler Details- GTX 1060: --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v- GTX 1070: --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v- GTX 1070 Ti: --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v- GTX 1080: --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v- GTX 1080 Ti: --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v- RTX 2060: --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v- RTX 2070: --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v- RTX 2080: --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v- RTX 2080 Ti: --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v- TITAN RTX: --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v- RX 580: --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v- RX 590: --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v- RX Vega 56: --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v- RX Vega 64: --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v- amdocl: --disable-libssp --disable-libstdcxx-pch --disable-libunwind-exceptions --disable-werror --enable-__cxa_atexit --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-install-libiberty --enable-languages=c,c++,ada,fortran,go,lto,objc,obj-c++ --enable-libmpx --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-isl --with-linker-hash-style=gnuProcessor Details- GTX 1060: Scaling Governor: intel_pstate performance- GTX 1070: Scaling Governor: intel_pstate performance- GTX 1070 Ti: Scaling Governor: intel_pstate performance- GTX 1080: Scaling Governor: intel_pstate performance- GTX 1080 Ti: Scaling Governor: intel_pstate performance- RTX 2060: Scaling Governor: intel_pstate performance- RTX 2070: Scaling Governor: intel_pstate performance- RTX 2080: Scaling Governor: intel_pstate performance- RTX 2080 Ti: Scaling Governor: intel_pstate performance- TITAN RTX: Scaling Governor: intel_pstate performance- RX 580: Scaling Governor: intel_pstate performance- RX 590: Scaling Governor: intel_pstate performance- RX Vega 56: Scaling Governor: intel_pstate performance- RX Vega 64: Scaling Governor: intel_pstate performance- amdocl: Scaling Governor: acpi-cpufreq schedutilOpenCL Details- GTX 1060: GPU Compute Cores: 1280- GTX 1070: GPU Compute Cores: 1920- GTX 1070 Ti: GPU Compute Cores: 2432- GTX 1080: GPU Compute Cores: 2560- GTX 1080 Ti: GPU Compute Cores: 3584- RTX 2060: GPU Compute Cores: 1920- RTX 2070: GPU Compute Cores: 2304- RTX 2080: GPU Compute Cores: 2944- RTX 2080 Ti: GPU Compute Cores: 4352- TITAN RTX: GPU Compute Cores: 4608Python Details- GTX 1060: Python 2.7.15+ + Python 3.6.7- GTX 1070: Python 2.7.15+ + Python 3.6.7- GTX 1070 Ti: Python 2.7.15+ + Python 3.6.7- GTX 1080: Python 2.7.15+ + Python 3.6.7- GTX 1080 Ti: Python 2.7.15+ + Python 3.6.7- RTX 2060: Python 2.7.15+ + Python 3.6.7- RTX 2070: Python 2.7.15+ + Python 3.6.7- RTX 2080: Python 2.7.15+ + Python 3.6.7- RTX 2080 Ti: Python 2.7.15+ + Python 3.6.7- TITAN RTX: Python 2.7.15+ + Python 3.6.7- RX 580: Python 2.7.15+ + Python 3.6.7- RX 590: Python 2.7.15+ + Python 3.6.7- RX Vega 56: Python 2.7.15+ + Python 3.6.7- RX Vega 64: Python 2.7.15+ + Python 3.6.7- amdocl: Python 3.7.2Security Details- GTX 1060: __user pointer sanitization + Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + SSB disabled via prctl and seccomp- GTX 1070: __user pointer sanitization + Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + SSB disabled via prctl and seccomp- GTX 1070 Ti: __user pointer sanitization + Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + SSB disabled via prctl and seccomp- GTX 1080: __user pointer sanitization + Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + SSB disabled via prctl and seccomp- GTX 1080 Ti: __user pointer sanitization + Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + SSB disabled via prctl and seccomp- RTX 2060: __user pointer sanitization + Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + SSB disabled via prctl and seccomp- RTX 2070: __user pointer sanitization + Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + SSB disabled via prctl and seccomp- RTX 2080: __user pointer sanitization + Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + SSB disabled via prctl and seccomp- RTX 2080 Ti: __user pointer sanitization + Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + SSB disabled via prctl and seccomp- TITAN RTX: __user pointer sanitization + Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + SSB disabled via prctl and seccomp- RX 580: __user pointer sanitization + Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + SSB disabled via prctl and seccomp- RX 590: __user pointer sanitization + Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + SSB disabled via prctl and seccomp- RX Vega 56: __user pointer sanitization + Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + SSB disabled via prctl and seccomp- RX Vega 64: __user pointer sanitization + Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + SSB disabled via prctl and seccomp- amdocl: __user pointer sanitization + Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + SSB disabled via prctl and seccompKernel Details- amdocl: amdgpu.ppfeaturemask=0xffffffff amdgpu.gpu_recovery=1Graphics Details- amdocl: GLAMOR

GTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiTITAN RTXRX 580RX 590RX Vega 56RX Vega 64amdoclResult OverviewPhoronix Test Suite100%203%306%409%LeelaChessZeroLuxMarkcl-memPlaidMLSHOC Scalable HeterOgeneous ComputingclpeakJuliaGPU

NVIDIA vs. Radeon OpenCL Linux GPU Computeclpeak: Kernel Latencydarktable: Boat - OpenCLdarktable: Server Room - OpenCLshoc: OpenCL - Texture Read Bandwidthclpeak: Double-Precision Doubleshoc: OpenCL - FFT SPlczero: OpenCLshoc: OpenCL - MD5 Hashplaidml: No - Inference - VGG16 - OpenCLplaidml: Yes - Inference - VGG16 - OpenCLplaidml: No - Inference - ResNet 50 - OpenCLplaidml: No - Training - Mobilenet - OpenCLluxmark: GPU - Luxball HDRcl-mem: Readplaidml: Yes - Inference - ResNet 50 - OpenCLclpeak: Global Memory Bandwidthclpeak: Transfer Bandwidth enqueueWriteBuffercl-mem: Writecl-mem: Copyplaidml: No - Inference - IMDB LSTM - OpenCLplaidml: No - Inference - Inception V3 - OpenCLplaidml: No - Inference - Mobilenet - OpenCLplaidml: Yes - Inference - Inception V3 - OpenCLjuliagpu: GPUplaidml: Yes - Inference - Mobilenet - OpenCLplaidml: No - Training - IMDB LSTM - OpenCLdarktable: Server Rack - OpenCLshoc: OpenCL - Triadclpeak: Transfer Bandwidth enqueueReadBufferdarktable: Masskrug - OpenCLdarktable: Server Rack - OpenCLdarktable: Server Room - OpenCLdarktable: Masskrug - OpenCLdarktable: Boat - OpenCLclpeak: Integer Compute INTclpeak: Single-Precision FloatGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiTITAN RTXRX 580RX 590RX Vega 56RX Vega 64amdocl3.783.661.314111512978997.2894.0894.6219486.941225615318314512.5413913818086.1159288.851837826265521340.1311.9311.154.17125242393.642.891.10447224453143010.471291262571071728720523719612.601921872281167641172181720626641560.1212.1911.333.92168158783.922.931.16433242501147811.631311282621031677620523719712.551901872241187551202215480166451530.1312.1911.154.01206867763.772.721.10527297575175014.191431392921031380322926422212.592162092591338011322391313246861670.1312.3011.343.97239879343.992.261.03596415972233319.681891943391252168233733432912.573363173301678831672651628757741870.1212.5111.293.873263108533.652.220.821024231803148415.871501483091132135629628227612.602452473471338631342516119897791880.1112.4311.293.82670566303.641.930.751077266988172918.421891793761322953239233336512.4831333038215610081572656820468301980.1012.5711.253.68778079683.651.920.8111213431083225923.742031924001332914639235436812.5232332745717210451682788292388932160.1112.5711.133.789952102703.831.640.7511735191445310735.132732505371564278754445850512.5943945460522512912113009222419712460.1012.6811.293.6914906153523.851.640.7411585401553327536.282892645561604602256547452512.5848948361022913362153036654479772440.1012.6811.163.6914848163864.9713.544.182113925476408.0565.1860.9813342.041527116212820644.9717918419369.0541476.592830788515631300.179.1015.845.30125262024.6913.964.282414365706839.1668.6964.0414245.611722117813721744.1918519321875.4145382.713026234405991440.179.3615.925.45141670697.0113.474.1835569892775812.70120.44106.6622871.233107915119531744.97305204263106.65720109.033464840645751780.177.5516.635.281997103576.9613.724.2142583392285616.39137.62119.9927074.313256515921336244.31356222279119.06835120.033661594385871840.177.5416.225.3224791246933.79369689895118912.95120.11108.3626275.092814034021531837.97325309270138.74781116.4931279256549815912.4415.790.090.754.812.72196110591OpenBenchmarking.org

clpeak

OpenBenchmarking.orgus, Fewer Is BetterclpeakOpenCL Test: Kernel LatencyGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl816243240SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.14, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.10, N = 3SE +/- 0.24, N = 33.783.643.923.773.993.653.643.653.834.974.697.016.963.8533.791. (CXX) g++ options: -O3 -rdynamic -lOpenCL

LeelaChessZero

OpenBenchmarking.orgWatts, Fewer Is BetterLeelaChessZero 0.20.1System Power Consumption MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX60120180240300Min: 41.9 / Avg: 150.59 / Max: 180Min: 42.6 / Avg: 184.04 / Max: 213.3Min: 80 / Avg: 156.39 / Max: 189.7Min: 40.2 / Avg: 148.14 / Max: 249.5Min: 96.9 / Avg: 265.17 / Max: 323.1Min: 69.4 / Avg: 196.01 / Max: 230Min: 75.1 / Avg: 186.61 / Max: 251.7Min: 88.3 / Avg: 222.99 / Max: 288.3Min: 48.2 / Avg: 205.76 / Max: 349.4Min: 69.3 / Avg: 171.21 / Max: 229.5Min: 75.2 / Avg: 188.72 / Max: 253.3Min: 47.2 / Avg: 173.2 / Max: 262.2Min: 50.2 / Avg: 313.27 / Max: 342.7Min: 97.7 / Avg: 148.16 / Max: 357.7

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.4.4Test: Boat - Acceleration: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX48121620SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 33.662.892.932.722.262.221.931.921.6413.5413.9613.4713.721.64

LeelaChessZero

OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterLeelaChessZero 0.20.1Backend: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX5101520255.977.779.4511.818.807.579.2710.1315.103.743.624.382.7322.11

PlaidML

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX60120180240300Min: 72.7 / Avg: 144.61 / Max: 170.9Min: 43.1 / Avg: 162.78 / Max: 197.9Min: 47.9 / Avg: 146.58 / Max: 171.7Min: 45.1 / Avg: 180.6 / Max: 225Min: 127.7 / Avg: 231.45 / Max: 296.9Min: 44 / Avg: 167.51 / Max: 215.1Min: 68.7 / Avg: 183.65 / Max: 245.5Min: 50.9 / Avg: 188.45 / Max: 269.3Min: 47.6 / Avg: 212.98 / Max: 331.1Min: 73 / Avg: 163.55 / Max: 194.8Min: 86.9 / Avg: 184.98 / Max: 216.4Min: 78.5 / Avg: 188.36 / Max: 262.2Min: 52.7 / Avg: 216.48 / Max: 338.1Min: 55.4 / Avg: 223.68 / Max: 345.8

LuxMark

OpenBenchmarking.orgWatts, Fewer Is BetterLuxMark 3.1System Power Consumption MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX60120180240300Min: 111.3 / Avg: 143.3 / Max: 145.4Min: 82.6 / Avg: 175.54 / Max: 179.2Min: 47.6 / Avg: 146.95 / Max: 149.7Min: 89.3 / Avg: 173.79 / Max: 175.8Min: 161.6 / Avg: 242.69 / Max: 248.1Min: 44 / Avg: 192.74 / Max: 197.4Min: 46 / Avg: 225.28 / Max: 233.2Min: 48.9 / Avg: 235.08 / Max: 244.1Min: 47.7 / Avg: 320.7 / Max: 332Min: 71.5 / Avg: 189.63 / Max: 196.7Min: 82.1 / Avg: 218.27 / Max: 228.9Min: 60.2 / Avg: 257.74 / Max: 269.1Min: 49.5 / Avg: 329.31 / Max: 338.6Min: 50.6 / Avg: 334.61 / Max: 351.7

PlaidML

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX60120180240300Min: 71.5 / Avg: 140.59 / Max: 158.7Min: 43.1 / Avg: 156.77 / Max: 185.9Min: 48.9 / Avg: 127.46 / Max: 146.6Min: 115.7 / Avg: 176.49 / Max: 201.1Min: 50.4 / Avg: 194.3 / Max: 254.7Min: 45.1 / Avg: 125.88 / Max: 192.6Min: 46.5 / Avg: 126.45 / Max: 198.6Min: 47.4 / Avg: 135.75 / Max: 228.3Min: 48.3 / Avg: 198.43 / Max: 287.4Min: 72.7 / Avg: 136.8 / Max: 186.1Min: 78.3 / Avg: 178.69 / Max: 218.6Min: 49.4 / Avg: 145.38 / Max: 261.4Min: 88.8 / Avg: 211.83 / Max: 333.3Min: 52.5 / Avg: 178.13 / Max: 298.5

cl-mem

OpenBenchmarking.orgWatts, Fewer Is Bettercl-mem 2017-01-13System Power Consumption MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX60120180240300Min: 57.7 / Avg: 108.33 / Max: 126.1Min: 64.6 / Avg: 132.44 / Max: 150.8Min: 49.3 / Avg: 113.36 / Max: 139.4Min: 43.2 / Avg: 119.3 / Max: 162.2Min: 49.6 / Avg: 139.67 / Max: 192.8Min: 43.7 / Avg: 111.03 / Max: 156.9Min: 115.9 / Avg: 150.6 / Max: 185.3Min: 52.6 / Avg: 141.73 / Max: 186.7Min: 136 / Avg: 198.3 / Max: 260.6Min: 73.1 / Avg: 141.22 / Max: 169.4Min: 194.4 / Avg: 199.58 / Max: 203.7Min: 49.6 / Avg: 203.34 / Max: 252.9Min: 51.9 / Avg: 197.96 / Max: 328.9Min: 54.7 / Avg: 99.5 / Max: 144.3

PlaidML

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX60120180240300Min: 58.2 / Avg: 131.14 / Max: 167.2Min: 43.1 / Avg: 136.92 / Max: 191.2Min: 48.4 / Avg: 125.32 / Max: 169.8Min: 70.3 / Avg: 172.91 / Max: 216.6Min: 65.2 / Avg: 179.46 / Max: 287.9Min: 62.3 / Avg: 137.76 / Max: 208Min: 47.2 / Avg: 141.31 / Max: 234Min: 49.8 / Avg: 158.89 / Max: 252.8Min: 47.7 / Avg: 180.78 / Max: 312Min: 73.2 / Avg: 147.27 / Max: 187.1Min: 79.7 / Avg: 162.83 / Max: 210.1Min: 50.2 / Avg: 151.48 / Max: 258.1Min: 53.4 / Avg: 217.55 / Max: 319.8Min: 58.3 / Avg: 176.01 / Max: 322.5

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX60120180240300Min: 71.4 / Avg: 121.65 / Max: 172.6Min: 45.2 / Avg: 145.44 / Max: 201.2Min: 48.6 / Avg: 134.71 / Max: 168.9Min: 91.9 / Avg: 152.34 / Max: 225.3Min: 61.2 / Avg: 185.7 / Max: 280.5Min: 65 / Avg: 134.41 / Max: 208.9Min: 49.8 / Avg: 153.92 / Max: 242.3Min: 48.4 / Avg: 158.95 / Max: 257.5Min: 100.3 / Avg: 172.57 / Max: 323.3Min: 73 / Avg: 145.33 / Max: 194.5Min: 81 / Avg: 162.42 / Max: 220Min: 50.1 / Avg: 150.39 / Max: 271.1Min: 81.5 / Avg: 177.38 / Max: 338.2Min: 102.3 / Avg: 194.3 / Max: 332.7

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX60120180240300Min: 70.6 / Avg: 141.88 / Max: 164.5Min: 85.2 / Avg: 157.11 / Max: 185.1Min: 50 / Avg: 141.65 / Max: 161.4Min: 91.6 / Avg: 167.52 / Max: 214.9Min: 123.8 / Avg: 205.47 / Max: 275.7Min: 45.2 / Avg: 158.66 / Max: 201.6Min: 47.5 / Avg: 159.79 / Max: 224.3Min: 50.1 / Avg: 167.47 / Max: 240.9Min: 49.3 / Avg: 185.12 / Max: 298.3Min: 71.3 / Avg: 157.31 / Max: 201.8Min: 79.3 / Avg: 178.28 / Max: 235.4Min: 78.5 / Avg: 172.43 / Max: 257.5Min: 50.9 / Avg: 173.75 / Max: 315.1Min: 63.8 / Avg: 192.88 / Max: 301.5

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX50100150200250Min: 70.1 / Avg: 124.21 / Max: 145Min: 82.2 / Avg: 136.83 / Max: 164.9Min: 104.8 / Avg: 123.57 / Max: 135.6Min: 90.8 / Avg: 146.71 / Max: 176.8Min: 50.4 / Avg: 165.05 / Max: 214.8Min: 44.3 / Avg: 116.14 / Max: 162.7Min: 47.1 / Avg: 127.27 / Max: 169.5Min: 46.4 / Avg: 138.03 / Max: 185.4Min: 48.6 / Avg: 159.87 / Max: 223.7Min: 71.3 / Avg: 146.11 / Max: 185.3Min: 80.2 / Avg: 152.62 / Max: 212.4Min: 74.8 / Avg: 165.69 / Max: 271.3Min: 52.2 / Avg: 165.89 / Max: 305.6Min: 57.5 / Avg: 152.07 / Max: 231.9

clpeak

OpenBenchmarking.orgWatts, Fewer Is BetterclpeakSystem Power Consumption MonitorRX 580RX 590RX Vega 56RX Vega 6460120180240300Min: 71 / Avg: 109.44 / Max: 203.5Min: 79.2 / Avg: 117.14 / Max: 233.2Min: 49.1 / Avg: 89.06 / Max: 257.9Min: 52.7 / Avg: 104.67 / Max: 335.3

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10System Power Consumption MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX50100150200250Min: 42.1 / Avg: 105.4 / Max: 135.1Min: 43.3 / Avg: 130.75 / Max: 158.9Min: 48.4 / Avg: 122.39 / Max: 144.2Min: 43.4 / Avg: 134.92 / Max: 163.8Min: 53.7 / Avg: 180.42 / Max: 218.2Min: 148.5 / Avg: 159.28 / Max: 177.5Min: 52.2 / Avg: 156.43 / Max: 195Min: 169.9 / Avg: 187.73 / Max: 213.5Min: 49 / Avg: 235.34 / Max: 283.1Min: 69.1 / Avg: 131.16 / Max: 160.2Min: 78.3 / Avg: 160.59 / Max: 187.1Min: 47.3 / Avg: 173.9 / Max: 235.2Min: 49.7 / Avg: 228.87 / Max: 263.7Min: 49.4 / Avg: 244.67 / Max: 287.4

clpeak

OpenBenchmarking.orgWatts, Fewer Is BetterclpeakSystem Power Consumption MonitorRX 580RX 590RX Vega 56RX Vega 6460120180240300Min: 69.5 / Avg: 116.89 / Max: 196.7Min: 77.7 / Avg: 124.39 / Max: 220.8Min: 47.5 / Avg: 112.24 / Max: 264.2Min: 63.8 / Avg: 133.52 / Max: 322.1

PlaidML

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX60120180240300Min: 60.4 / Avg: 122.52 / Max: 164.5Min: 83.8 / Avg: 134.85 / Max: 189.4Min: 48.5 / Avg: 113.89 / Max: 160.8Min: 91.6 / Avg: 162.7 / Max: 211.1Min: 122.3 / Avg: 187.68 / Max: 270.3Min: 86.5 / Avg: 143.68 / Max: 202.9Min: 78.4 / Avg: 132.98 / Max: 222.4Min: 47.4 / Avg: 148.19 / Max: 240.2Min: 48.4 / Avg: 155.12 / Max: 292.5Min: 73.6 / Avg: 141.5 / Max: 187.8Min: 81.1 / Avg: 153.59 / Max: 208.6Min: 50.5 / Avg: 141.19 / Max: 254.3Min: 82.4 / Avg: 172.03 / Max: 313.6Min: 52.6 / Avg: 162.76 / Max: 301.7

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX50100150200250Min: 87.5 / Avg: 132.19 / Max: 156.7Min: 81.8 / Avg: 153.87 / Max: 183Min: 56.1 / Avg: 132.15 / Max: 155Min: 89.5 / Avg: 168.75 / Max: 202.8Min: 120.7 / Avg: 202.56 / Max: 256.6Min: 45 / Avg: 144.95 / Max: 190.7Min: 45.8 / Avg: 146.81 / Max: 206.6Min: 47.5 / Avg: 155.97 / Max: 224.6Min: 48.4 / Avg: 188.73 / Max: 275.6Min: 73.1 / Avg: 146.45 / Max: 195.4Min: 91.8 / Avg: 163.54 / Max: 221.5Min: 58.9 / Avg: 147.82 / Max: 249.5Min: 50.6 / Avg: 181.52 / Max: 296Min: 51.5 / Avg: 168.92 / Max: 275.4

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX50100150200250Min: 41.8 / Avg: 76.7 / Max: 94.4Min: 45.9 / Avg: 107.3 / Max: 155.1Min: 49.7 / Avg: 93.67 / Max: 125.7Min: 44.3 / Avg: 147.75 / Max: 195.1Min: 53.3 / Avg: 125.73 / Max: 165.2Min: 43.1 / Avg: 95.9 / Max: 118.8Min: 115.1 / Avg: 115.83 / Max: 116.5Min: 52 / Avg: 97.93 / Max: 121Min: 48.2 / Avg: 152.87 / Max: 274.6Min: 71.7 / Avg: 114.33 / Max: 178.6Min: 82.4 / Avg: 137.7 / Max: 205.5Min: 72.5 / Avg: 123.7 / Max: 259.6Min: 52.5 / Avg: 111.85 / Max: 223.9Min: 54 / Avg: 200.17 / Max: 274.2

cl-mem

OpenBenchmarking.orgWatts, Fewer Is Bettercl-mem 2017-01-13System Power Consumption MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX50100150200250Min: 55.5 / Avg: 114.96 / Max: 125.8Min: 46.7 / Avg: 129.34 / Max: 151Min: 49 / Avg: 121.24 / Max: 139.8Min: 102.3 / Avg: 149.02 / Max: 162.5Min: 52.6 / Avg: 161.7 / Max: 217.6Min: 45.9 / Avg: 126.65 / Max: 159.6Min: 48.6 / Avg: 145.97 / Max: 196.3Min: 50.4 / Avg: 148 / Max: 197.9Min: 57.7 / Avg: 161.45 / Max: 265.2Min: 73.5 / Avg: 144 / Max: 170.7Min: 82 / Avg: 176.16 / Max: 207.2Min: 50.8 / Avg: 153.05 / Max: 254.1Min: 55.2 / Avg: 211.77 / Max: 297.7Min: 55.2 / Avg: 156.17 / Max: 266.5

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10System Power Consumption MonitorRX 580RX 590RX Vega 56RX Vega 6450100150200250Min: 92.2 / Avg: 137.05 / Max: 181.9Min: 138.3 / Avg: 188 / Max: 237.7Min: 47.8 / Avg: 120.9 / Max: 194Min: 62.2 / Avg: 183.8 / Max: 305.4

cl-mem

OpenBenchmarking.orgWatts, Fewer Is Bettercl-mem 2017-01-13System Power Consumption MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX50100150200250Min: 43.4 / Avg: 98.27 / Max: 126.2Min: 84.4 / Avg: 137.36 / Max: 151.6Min: 50 / Avg: 124.63 / Max: 140.5Min: 92.2 / Avg: 141.24 / Max: 162.2Min: 216.4 / Avg: 217.73 / Max: 218.8Min: 44.2 / Avg: 131.53 / Max: 164.4Min: 46.9 / Avg: 139.57 / Max: 185.9Min: 98.5 / Avg: 128.93 / Max: 169.3Min: 51 / Avg: 155.07 / Max: 243.7Min: 73 / Avg: 147.4 / Max: 169Min: 78.7 / Avg: 161.08 / Max: 200.6Min: 207.8 / Avg: 229.9 / Max: 252.1Min: 52.5 / Avg: 191.32 / Max: 275.7Min: 55 / Avg: 190.13 / Max: 258.3

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.4.4Test: Server Room - Acceleration: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX0.9631.9262.8893.8524.815SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 31.311.101.161.101.030.820.750.810.754.184.284.184.210.74

PlaidML

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX4080120160200Min: 43.2 / Avg: 99.8 / Max: 140.7Min: 48.4 / Avg: 126.46 / Max: 165Min: 48.1 / Avg: 99.69 / Max: 140.6Min: 91.7 / Avg: 152.84 / Max: 169.4Min: 47.2 / Avg: 121.72 / Max: 213.3Min: 47.3 / Avg: 110.84 / Max: 168.5Min: 49.9 / Avg: 120.6 / Max: 185.8Min: 48 / Avg: 132.2 / Max: 198.2Min: 48.4 / Avg: 137.54 / Max: 235.7Min: 73.6 / Avg: 119.65 / Max: 155.1Min: 78.7 / Avg: 135.11 / Max: 174.8Min: 49.7 / Avg: 124.48 / Max: 221.8Min: 75.8 / Avg: 156.29 / Max: 240.3Min: 56 / Avg: 163.54 / Max: 245.3

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: Texture Read BandwidthGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl30060090012001500SE +/- 1.03, N = 3SE +/- 0.82, N = 3SE +/- 0.80, N = 3SE +/- 0.28, N = 3SE +/- 1.91, N = 3SE +/- 0.24, N = 3SE +/- 1.24, N = 3SE +/- 2.94, N = 3SE +/- 1.02, N = 3SE +/- 1.47, N = 3SE +/- 1.57, N = 3SE +/- 0.86, N = 3SE +/- 0.60, N = 3SE +/- 3.52, N = 3SE +/- 1.03, N = 3411447433527596102410771121117321124135542511583691. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

clpeak

OpenBenchmarking.orgWatts, Fewer Is BetterclpeakSystem Power Consumption MonitorRX 580RX 590RX Vega 56RX Vega 6450100150200250Min: 73.3 / Avg: 98.79 / Max: 101.9Min: 79.3 / Avg: 107.03 / Max: 127.7Min: 49.2 / Avg: 81.54 / Max: 259Min: 51.6 / Avg: 87.77 / Max: 273.2

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision DoubleGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl2004006008001000SE +/- 0.05, N = 3SE +/- 0.26, N = 3SE +/- 0.24, N = 3SE +/- 0.02, N = 3SE +/- 0.14, N = 3SE +/- 0.60, N = 3SE +/- 0.72, N = 3SE +/- 0.98, N = 3SE +/- 1.25, N = 3SE +/- 0.01, N = 3SE +/- 0.21, N = 3SE +/- 1.26, N = 3SE +/- 1.09, N = 3SE +/- 1.29, N = 3SE +/- 1.18, N = 31512242422974152312663435193924366988335406891. (CXX) g++ options: -O3 -rdynamic -lOpenCL

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.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: FFT SPGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl30060090012001500SE +/- 2.45, N = 3SE +/- 8.74, N = 3SE +/- 1.30, N = 3SE +/- 1.43, N = 3SE +/- 2.56, N = 3SE +/- 10.50, N = 3SE +/- 46.80, N = 3SE +/- 6.71, N = 3SE +/- 11.70, N = 3SE +/- 0.36, N = 3SE +/- 1.04, N = 3SE +/- 1.97, N = 3SE +/- 0.34, N = 3SE +/- 2.67, N = 3SE +/- 2.55, N = 32974535015759728039881083144554757092792215538951. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

JuliaGPU

OpenBenchmarking.orgWatts, Fewer Is BetterJuliaGPU 1.2pts1System Power Consumption MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX4080120160200Min: 57.5 / Avg: 112.76 / Max: 128.1Min: 42.3 / Avg: 116.82 / Max: 147.4Min: 47.7 / Avg: 111.88 / Max: 128.2Min: 42.3 / Avg: 127 / Max: 157.8Min: 67.7 / Avg: 159.15 / Max: 189.8Min: 43.5 / Avg: 112.53 / Max: 153.7Min: 52.9 / Avg: 116.58 / Max: 157.4Min: 46.4 / Avg: 134.7 / Max: 169Min: 99.5 / Avg: 147.3 / Max: 199.5Min: 93.8 / Avg: 132.17 / Max: 160.8Min: 75.7 / Avg: 142.48 / Max: 179.1Min: 47.6 / Avg: 160.43 / Max: 218.2Min: 49.9 / Avg: 71.23 / Max: 89Min: 51.3 / Avg: 148.68 / Max: 204

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.20.1Backend: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl7001400210028003500SE +/- 6.27, N = 3SE +/- 9.63, N = 3SE +/- 13.26, N = 3SE +/- 32.06, N = 3SE +/- 25.14, N = 3SE +/- 13.06, N = 3SE +/- 20.57, N = 3SE +/- 22.18, N = 3SE +/- 20.98, N = 3SE +/- 2.68, N = 3SE +/- 2.57, N = 3SE +/- 2.66, N = 3SE +/- 5.51, N = 3SE +/- 28.14, N = 3SE +/- 16.88, N = 589914301478175023331484172922593107640683758856327511891. (CXX) g++ options: -lpthread

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.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: MD5 HashGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl816243240SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.40, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.35, N = 3SE +/- 0.02, N = 37.2810.4711.6314.1919.6815.8718.4223.7435.138.059.1612.7016.3936.2812.951. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

cl-mem

OpenBenchmarking.orgGB/s Per Watt, More Is Bettercl-mem 2017-01-13Benchmark: ReadGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RX 580RX 590RX Vega 56RX Vega 64TITAN RTX0.81451.6292.44353.2584.07251.331.591.691.542.092.342.692.651.121.010.990.753.62

PlaidML

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX4080120160200Min: 42.1 / Avg: 107.84 / Max: 141.6Min: 42.8 / Avg: 91.98 / Max: 117.4Min: 48.7 / Avg: 98.18 / Max: 132.6Min: 43.7 / Avg: 93.48 / Max: 127.3Min: 91.6 / Avg: 149.17 / Max: 203.2Min: 45.5 / Avg: 121.65 / Max: 166.1Min: 46 / Avg: 93.68 / Max: 129.3Min: 56.3 / Avg: 130.87 / Max: 184.7Min: 48.4 / Avg: 94.48 / Max: 113.3Min: 75.6 / Avg: 109.4 / Max: 179Min: 82.3 / Avg: 126.56 / Max: 194.9Min: 49.6 / Avg: 92.35 / Max: 157.7Min: 54 / Avg: 69.27 / Max: 82.4Min: 52.9 / Avg: 110.8 / Max: 140.2

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Texture Read BandwidthGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX2468103.903.423.543.913.306.436.885.974.981.611.502.041.864.73

PlaidML

This test profile uses PlaidML deep learning framework for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl60120180240300SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.12, N = 3SE +/- 0.16, N = 3SE +/- 0.27, N = 3SE +/- 0.17, N = 3SE +/- 0.36, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.18, N = 3SE +/- 0.11, N = 3SE +/- 0.72, N = 3SE +/- 0.04, N = 394.08129.00131.00143.00189.00150.00189.00203.00273.0065.1868.69120.44137.62289.00120.11

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl60120180240300SE +/- 0.03, N = 3SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.32, N = 3SE +/- 0.15, N = 3SE +/- 0.26, N = 3SE +/- 0.32, N = 3SE +/- 0.20, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.43, N = 3SE +/- 0.55, N = 394.62126.00128.00139.00194.00148.00179.00192.00250.0060.9864.04106.66119.99264.00108.36

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl120240360480600SE +/- 0.11, N = 3SE +/- 0.45, N = 3SE +/- 0.24, N = 3SE +/- 0.41, N = 3SE +/- 0.55, N = 3SE +/- 0.26, N = 3SE +/- 0.33, N = 3SE +/- 0.45, N = 3SE +/- 0.31, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 2.52, N = 3SE +/- 1.40, N = 3SE +/- 1.67, N = 3SE +/- 0.31, N = 3194257262292339309376400537133142228270556262

clpeak

OpenBenchmarking.orgWatts, Fewer Is BetterclpeakSystem Power Consumption MonitorRX 580RX 590RX Vega 56RX Vega 64306090120150Min: 69.4 / Avg: 100.72 / Max: 186.8Min: 76.7 / Avg: 105.71 / Max: 119.2Min: 47.8 / Avg: 76.77 / Max: 77.8Min: 49.5 / Avg: 80.89 / Max: 182.7

Darktable

OpenBenchmarking.orgWatts, Fewer Is BetterDarktable 2.4.4System Power Consumption MonitorRX 580RX 590RX Vega 56RX Vega 644080120160200Min: 74.4 / Avg: 164 / Max: 184.5Min: 80.8 / Avg: 170.15 / Max: 205Min: 118.8 / Avg: 139.2 / Max: 147Min: 52.7 / Avg: 132.86 / Max: 151.4

OpenBenchmarking.orgWatts, Fewer Is BetterDarktable 2.4.4System Power Consumption MonitorRX 580RX 590RX Vega 56RX Vega 64306090120150Min: 73 / Avg: 131.16 / Max: 186.9Min: 79.3 / Avg: 145.78 / Max: 178.8Min: 48.4 / Avg: 110.52 / Max: 178.2Min: 127.1 / Avg: 138.95 / Max: 150.8

PlaidML

OpenBenchmarking.orgExamples Per Second Per Watt, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX0.33750.6751.01251.351.68750.720.921.020.801.081.081.271.211.380.410.390.700.551.50

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Training - Network: Mobilenet - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl4080120160200SE +/- 0.03, N = 3SE +/- 0.15, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.18, N = 3SE +/- 0.11, N = 3SE +/- 0.18, N = 3SE +/- 0.21, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.17, N = 3SE +/- 0.19, N = 3SE +/- 0.10, N = 386.94107.00103.00103.00125.00113.00132.00133.00156.0042.0445.6171.2374.31160.0075.09

Darktable

OpenBenchmarking.orgWatts, Fewer Is BetterDarktable 2.4.4System Power Consumption MonitorRX 580RX 590RX Vega 56RX Vega 64306090120150Min: 71.4 / Avg: 101.98 / Max: 180.7Min: 77.5 / Avg: 115.43 / Max: 145.8Min: 48.3 / Avg: 83.05 / Max: 115.5Min: 159.8 / Avg: 170.75 / Max: 181.7

LuxMark

LuxMark is a multi-platform OpenGL benchmark using LuxRender. LuxMark supports targeting different OpenCL devices and has multiple scenes available for rendering. LuxMark is a fully open-source OpenCL program with real-world rendering examples. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: Luxball HDRGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl10K20K30K40K50KSE +/- 46.58, N = 3SE +/- 1.33, N = 3SE +/- 14.90, N = 3SE +/- 42.00, N = 3SE +/- 8.33, N = 3SE +/- 31.58, N = 3SE +/- 107.00, N = 3SE +/- 25.12, N = 3SE +/- 155.67, N = 3SE +/- 17.84, N = 3SE +/- 74.83, N = 3SE +/- 65.67, N = 3SE +/- 583.87, N = 3SE +/- 103.04, N = 3SE +/- 124.42, N = 3122561728716776138032168221356295322914642787152711722131079325654602228140

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: ReadGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl120240360480600SE +/- 0.17, N = 3SE +/- 0.09, N = 3SE +/- 0.27, N = 3SE +/- 0.18, N = 3SE +/- 0.52, N = 3SE +/- 0.15, N = 3SE +/- 1.98, N = 3SE +/- 1.81, N = 3SE +/- 0.50, N = 3SE +/- 0.15, N = 3SE +/- 0.58, N = 3SE +/- 0.06, N = 3SE +/- 0.18, N = 3SE +/- 0.38, N = 3SE +/- 0.54, N = 31532052052293372963923925441621781511595653401. (CC) gcc options: -O2 -flto -lOpenCL

PlaidML

This test profile uses PlaidML deep learning framework for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl100200300400500SE +/- 0.17, N = 3SE +/- 0.38, N = 3SE +/- 0.16, N = 3SE +/- 0.24, N = 3SE +/- 0.34, N = 3SE +/- 0.26, N = 3SE +/- 0.76, N = 3SE +/- 0.40, N = 3SE +/- 1.03, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.13, N = 3SE +/- 1.16, N = 3SE +/- 2.54, N = 3183237237264334282333354458128137195213474215

clpeak

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory BandwidthGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl110220330440550SE +/- 0.95, N = 3SE +/- 0.02, N = 3SE +/- 0.22, N = 3SE +/- 0.05, N = 3SE +/- 0.68, N = 3SE +/- 0.19, N = 3SE +/- 2.69, N = 3SE +/- 0.37, N = 3SE +/- 0.48, N = 3SE +/- 1.46, N = 3SE +/- 1.82, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 1.70, N = 3SE +/- 0.34, N = 31451961972223292763653685052062173173625253181. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Transfer Bandwidth enqueueWriteBufferGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl1020304050SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.22, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.42, N = 312.5412.6012.5512.5912.5712.6012.4812.5212.5944.9744.1944.9744.3112.5837.971. (CXX) g++ options: -O3 -rdynamic -lOpenCL

PlaidML

OpenBenchmarking.orgExamples Per Second Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX0.69981.39962.09942.79923.4991.591.771.941.921.822.302.442.513.110.920.881.511.522.86

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: WriteGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl110220330440550SE +/- 0.19, N = 3SE +/- 0.07, N = 3SE +/- 0.30, N = 3SE +/- 0.09, N = 3SE +/- 0.09, N = 3SE +/- 0.95, N = 3SE +/- 0.59, N = 3SE +/- 0.73, N = 3SE +/- 1.92, N = 3SE +/- 0.33, N = 3SE +/- 0.10, N = 3SE +/- 0.32, N = 3SE +/- 11.23, N = 3SE +/- 2.45, N = 3SE +/- 0.27, N = 31391921902163362453133234391791853053564893251. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl100200300400500SE +/- 0.15, N = 3SE +/- 0.07, N = 3SE +/- 0.29, N = 3SE +/- 0.06, N = 3SE +/- 0.17, N = 3SE +/- 0.18, N = 3SE +/- 0.18, N = 3SE +/- 0.35, N = 3SE +/- 0.23, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.20, N = 3SE +/- 0.06, N = 3SE +/- 0.64, N = 3SE +/- 0.12, N = 31381871872093172473303274541841932042224833091. (CC) gcc options: -O2 -flto -lOpenCL

PlaidML

OpenBenchmarking.orgExamples Per Second Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX0.29030.58060.87091.16121.45150.650.790.890.790.820.901.031.081.280.400.370.640.641.29

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl130260390520650SE +/- 0.33, N = 3SE +/- 0.21, N = 3SE +/- 0.19, N = 3SE +/- 0.45, N = 3SE +/- 0.59, N = 3SE +/- 0.31, N = 3SE +/- 0.60, N = 3SE +/- 1.09, N = 3SE +/- 2.13, N = 3SE +/- 0.23, N = 3SE +/- 0.63, N = 3SE +/- 0.20, N = 3SE +/- 1.42, N = 3SE +/- 0.76, N = 3SE +/- 0.46, N = 3180228224259330347382457605193218263279610270

OpenBenchmarking.orgExamples Per Second Per Watt, More Is BetterPlaidMLFP16: No - Mode: Training - Network: Mobilenet - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX0.25430.50860.76291.01721.27150.870.851.030.671.031.021.091.011.130.350.340.570.480.98

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl50100150200250SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.18, N = 3SE +/- 0.08, N = 3SE +/- 0.28, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.13, N = 3SE +/- 0.38, N = 3SE +/- 0.11, N = 3SE +/- 0.06, N = 3SE +/- 0.00, N = 3SE +/- 0.40, N = 3SE +/- 0.53, N = 3SE +/- 0.24, N = 386.11116.00118.00133.00167.00133.00156.00172.00225.0069.0575.41106.65119.06229.00138.74

OpenBenchmarking.orgExamples Per Second Per Watt, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX0.66381.32761.99142.65523.3191.491.762.081.621.781.962.512.392.950.910.891.381.242.92

OpenBenchmarking.orgExamples Per Second Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX36912157.727.128.065.427.029.008.7010.678.453.623.295.827.476.67

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl30060090012001500SE +/- 3.04, N = 3SE +/- 1.02, N = 3SE +/- 0.31, N = 3SE +/- 0.61, N = 3SE +/- 4.51, N = 3SE +/- 1.86, N = 3SE +/- 1.43, N = 3SE +/- 0.31, N = 3SE +/- 1.39, N = 3SE +/- 0.26, N = 3SE +/- 0.24, N = 3SE +/- 9.70, N = 3SE +/- 7.40, N = 3SE +/- 3.01, N = 3SE +/- 2.78, N = 35927647558018838631008104512914144537208351336781

JuliaGPU

OpenBenchmarking.orgSamples/sec Per Watt, More Is BetterJuliaGPU 1.2pts1OpenCL Device: GPUGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1.1M2.2M3.3M4.4M5.5M16298571867592198022918829241666119223605422790652070002204292121418322124046215967651402822042478

LuxMark

OpenBenchmarking.orgCelsius, Fewer Is BetterLuxMark 3.1GPU Temperature MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1632486480Min: 43 / Avg: 58.4 / Max: 61Min: 54 / Avg: 67.07 / Max: 70Min: 41 / Avg: 48.91 / Max: 51Min: 49 / Avg: 64.55 / Max: 67Min: 56 / Avg: 72.55 / Max: 75Min: 49 / Avg: 63.65 / Max: 67Min: 47 / Avg: 67.5 / Max: 72Min: 48 / Avg: 75.04 / Max: 79Min: 49 / Avg: 69.88 / Max: 74Min: 29 / Avg: 55.16 / Max: 60Min: 44 / Avg: 65.27 / Max: 73Min: 44 / Avg: 69.66 / Max: 74Min: 43 / Avg: 79.26 / Max: 86Min: 44 / Avg: 71.96 / Max: 78

PlaidML

OpenBenchmarking.orgExamples Per Second Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX0.27230.54460.81691.08921.36150.610.740.830.790.810.840.981.031.210.440.420.620.691.19

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10System Power Consumption MonitorRX 580RX 590RX Vega 56RX Vega 64306090120150Min: 80.6 / Avg: 100.5 / Max: 136Min: 47.7 / Avg: 48.75 / Max: 49.8Min: 50.5 / Avg: 65.45 / Max: 80.4

PlaidML

OpenBenchmarking.orgExamples Per Second Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX0.77181.54362.31543.08723.8591.281.461.761.471.702.763.023.373.051.411.221.811.323.43

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Inception V3 - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl50100150200250SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.30, N = 3SE +/- 0.07, N = 3SE +/- 0.58, N = 3SE +/- 0.44, N = 3SE +/- 0.18, N = 3SE +/- 0.40, N = 3SE +/- 0.48, N = 3SE +/- 0.04, N = 3SE +/- 0.11, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 1.30, N = 3SE +/- 0.34, N = 388.85117.00120.00132.00167.00134.00157.00168.00211.0076.5982.71109.03120.03215.00116.49

LeelaChessZero

OpenBenchmarking.orgCelsius, Fewer Is BetterLeelaChessZero 0.20.1GPU Temperature MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1428425670Min: 38 / Avg: 51.69 / Max: 59Min: 35 / Avg: 46.2 / Max: 55Min: 46 / Avg: 50.13 / Max: 53Min: 32 / Avg: 40.8 / Max: 58Min: 41 / Avg: 51.43 / Max: 61Min: 39 / Avg: 50.33 / Max: 58Min: 33 / Avg: 44.86 / Max: 52Min: 57 / Avg: 66.29 / Max: 73Min: 50 / Avg: 55.6 / Max: 60Min: 27 / Avg: 45.13 / Max: 61Min: 37 / Avg: 50.65 / Max: 67Min: 28 / Avg: 41.93 / Max: 60Min: 46 / Avg: 64.5 / Max: 72Min: 34 / Avg: 36.91 / Max: 47

PlaidML

OpenBenchmarking.orgExamples Per Second Per Watt, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Inception V3 - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX0.2880.5760.8641.1521.440.670.760.900.780.820.921.071.081.120.520.510.740.661.28

clpeak

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterclpeakOpenCL Test: Single-Precision FloatRX 580RX 590RX Vega 56RX Vega 6430609012015061.5866.87135.00154.00

cl-mem

OpenBenchmarking.orgGB/s Per Watt, More Is Bettercl-mem 2017-01-13Benchmark: WriteGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX0.63681.27361.91042.54723.1841.421.401.521.531.541.872.252.502.831.211.151.331.862.57

OpenBenchmarking.orgGB/s Per Watt, More Is Bettercl-mem 2017-01-13Benchmark: CopyGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2080RX 580RX 590RX Vega 56RX Vega 640.51981.03961.55942.07922.5991.281.411.651.762.272.222.311.300.971.001.12

clpeak

OpenBenchmarking.orgWatts, Fewer Is BetterclpeakSystem Power Consumption MonitorRX 580RX 590RX Vega 56RX Vega 6420406080100Min: 69.7 / Avg: 98.35 / Max: 99.6Min: 78.8 / Avg: 105.05 / Max: 110.8Min: 47.4 / Avg: 76.29 / Max: 77.6Min: 59.1 / Avg: 78.52 / Max: 79.5

OpenBenchmarking.orgWatts, Fewer Is BetterclpeakSystem Power Consumption MonitorRX 580RX 590RX Vega 56RX Vega 6420406080100Min: 70.1 / Avg: 99 / Max: 100.8Min: 78.6 / Avg: 105.13 / Max: 109.6Min: 48.2 / Avg: 76.77 / Max: 79.1Min: 51.4 / Avg: 79.27 / Max: 81.1

PlaidML

OpenBenchmarking.orgCelsius, Fewer Is BetterPlaidMLGPU Temperature MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1428425670Min: 43 / Avg: 51.9 / Max: 59Min: 49 / Avg: 56.06 / Max: 63Min: 41 / Avg: 45.18 / Max: 50Min: 52 / Avg: 58.85 / Max: 65Min: 53 / Avg: 60.07 / Max: 67Min: 43 / Avg: 50.75 / Max: 59Min: 42 / Avg: 48.87 / Max: 56Min: 53 / Avg: 59.79 / Max: 68Min: 46 / Avg: 51 / Max: 57Min: 31 / Avg: 42.94 / Max: 51Min: 42 / Avg: 53.46 / Max: 61Min: 52 / Avg: 59.68 / Max: 69Min: 55 / Avg: 63.35 / Max: 70Min: 42 / Avg: 47.33 / Max: 54

clpeak

OpenBenchmarking.orgWatts, Fewer Is BetterclpeakSystem Power Consumption MonitorRX 580RX 590RX Vega 56RX Vega 6420406080100Min: 69.5 / Avg: 98.49 / Max: 101Min: 78.6 / Avg: 105.05 / Max: 110.7Min: 73.9 / Avg: 77.01 / Max: 77.7Min: 49.9 / Avg: 78.27 / Max: 81

PlaidML

OpenBenchmarking.orgCelsius, Fewer Is BetterPlaidMLGPU Temperature MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1326395265Min: 41 / Avg: 47.52 / Max: 54Min: 51 / Avg: 56.59 / Max: 60Min: 38 / Avg: 42.62 / Max: 46Min: 60 / Avg: 61.64 / Max: 63Min: 44 / Avg: 53.18 / Max: 61Min: 43 / Avg: 48.84 / Max: 55Min: 42 / Avg: 47.65 / Max: 53Min: 52 / Avg: 58.56 / Max: 66Min: 44 / Avg: 48.59 / Max: 53Min: 30 / Avg: 37.96 / Max: 46Min: 42 / Avg: 49 / Max: 56Min: 40 / Avg: 49.89 / Max: 64Min: 45 / Avg: 55.21 / Max: 65Min: 43 / Avg: 48.07 / Max: 53

OpenBenchmarking.orgExamples Per Second Per Watt, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX36912155.127.226.577.345.196.418.876.8210.285.144.746.238.488.82

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgCelsius, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10GPU Temperature MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1326395265Min: 46 / Avg: 48.5 / Max: 49Min: 57 / Avg: 57.33 / Max: 58Min: 42 / Avg: 42.6 / Max: 43Min: 54 / Avg: 55.54 / Max: 57Min: 56 / Avg: 59.67 / Max: 61Min: 48 / Avg: 54.5 / Max: 56Min: 52 / Avg: 54.2 / Max: 56Min: 57 / Avg: 63.86 / Max: 67Min: 59 / Avg: 62 / Max: 65Min: 31 / Avg: 41.38 / Max: 45Min: 35 / Avg: 43.11 / Max: 47Min: 38 / Avg: 46.29 / Max: 52Min: 49 / Avg: 59.89 / Max: 65Min: 55 / Avg: 63.4 / Max: 66

PlaidML

OpenBenchmarking.orgCelsius, Fewer Is BetterPlaidMLGPU Temperature MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1428425670Min: 45 / Avg: 52 / Max: 57Min: 48 / Avg: 54.81 / Max: 60Min: 43 / Avg: 45.94 / Max: 49Min: 51 / Avg: 57.64 / Max: 63Min: 55 / Avg: 59.71 / Max: 66Min: 43 / Avg: 49.73 / Max: 56Min: 42 / Avg: 48.08 / Max: 55Min: 56 / Avg: 61.08 / Max: 66Min: 49 / Avg: 52.45 / Max: 57Min: 33 / Avg: 42.3 / Max: 50Min: 40 / Avg: 50.41 / Max: 60Min: 39 / Avg: 50.92 / Max: 65Min: 47 / Avg: 59.05 / Max: 70Min: 39 / Avg: 44.46 / Max: 52

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10System Power Consumption MonitorRX 580RX 590RX Vega 56RX Vega 6420406080100Min: 81.9 / Avg: 92.65 / Max: 103.4Min: 49 / Avg: 65 / Max: 81Min: 51.7 / Avg: 64.95 / Max: 78.2

PlaidML

OpenBenchmarking.orgCelsius, Fewer Is BetterPlaidMLGPU Temperature MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1326395265Min: 44 / Avg: 52.44 / Max: 59Min: 58 / Avg: 61.79 / Max: 65Min: 43 / Avg: 47.13 / Max: 50Min: 58 / Avg: 63.21 / Max: 68Min: 60 / Avg: 64.36 / Max: 69Min: 40 / Avg: 48.69 / Max: 56Min: 49 / Avg: 54.67 / Max: 60Min: 57 / Avg: 63.18 / Max: 68Min: 52 / Avg: 54.78 / Max: 59Min: 33 / Avg: 45.16 / Max: 54Min: 44 / Avg: 55.88 / Max: 64Min: 50 / Avg: 58.4 / Max: 68Min: 50 / Avg: 59.52 / Max: 69Min: 51 / Avg: 55.27 / Max: 60

clpeak

OpenBenchmarking.orgGIOPS Per Watt, More Is BetterclpeakOpenCL Test: Integer Compute INTRX 580RX 590RX Vega 56RX Vega 6461218243011.4412.0922.4323.68

OpenBenchmarking.orgCelsius, Fewer Is BetterclpeakGPU Temperature MonitorRX 580RX 590RX Vega 56RX Vega 641326395265Min: 32 / Avg: 39.04 / Max: 50Min: 36 / Avg: 41.8 / Max: 54Min: 35 / Avg: 42.72 / Max: 57Min: 36 / Avg: 47.48 / Max: 66

OpenBenchmarking.orgGBPS Per Watt, More Is BetterclpeakOpenCL Test: Global Memory BandwidthRX 580RX 590RX Vega 56RX Vega 640.92931.85862.78793.71724.64652.082.023.894.13

PlaidML

OpenBenchmarking.orgCelsius, Fewer Is BetterPlaidMLGPU Temperature MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1428425670Min: 52 / Avg: 58.35 / Max: 62Min: 56 / Avg: 62.15 / Max: 66Min: 43 / Avg: 47.69 / Max: 50Min: 59 / Avg: 64.36 / Max: 68Min: 61 / Avg: 65.7 / Max: 70Min: 46 / Avg: 55.73 / Max: 61Min: 47 / Avg: 54.45 / Max: 60Min: 56 / Avg: 63.5 / Max: 70Min: 49 / Avg: 54.38 / Max: 59Min: 35 / Avg: 47.27 / Max: 53Min: 43 / Avg: 54.21 / Max: 59Min: 51 / Avg: 59.53 / Max: 66Min: 50 / Avg: 60.38 / Max: 68Min: 50 / Avg: 55.25 / Max: 61

JuliaGPU

JuliaGPU is an OpenCL benchmark with this version containing various PTS-specific enhancements. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSamples/sec, More Is BetterJuliaGPU 1.2pts1OpenCL Device: GPUGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl80M160M240M320M400MSE +/- 513835.53, N = 3SE +/- 621591.58, N = 3SE +/- 297139.02, N = 3SE +/- 121634.53, N = 3SE +/- 720633.38, N = 3SE +/- 815068.63, N = 3SE +/- 333271.02, N = 3SE +/- 1536969.33, N = 3SE +/- 1417039.09, N = 3SE +/- 570650.48, N = 3SE +/- 366170.21, N = 3SE +/- 834530.58, N = 3SE +/- 419189.48, N = 3SE +/- 908628.37, N = 3SE +/- 7293118.99, N = 121837826262181720622215480162391313242651628752516119892656820462788292383009222412830788513026234403464840643661594383036654473127925651. (CC) gcc options: -O3 -march=native -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL -lm

PlaidML

This test profile uses PlaidML deep learning framework for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl2004006008001000SE +/- 0.87, N = 3SE +/- 4.06, N = 3SE +/- 3.15, N = 3SE +/- 5.02, N = 3SE +/- 3.70, N = 3SE +/- 1.27, N = 3SE +/- 1.07, N = 3SE +/- 1.63, N = 3SE +/- 2.70, N = 3SE +/- 1.03, N = 3SE +/- 1.00, N = 3SE +/- 6.73, N = 3SE +/- 9.53, N = 3SE +/- 3.45, N = 3SE +/- 5.20, N = 3552664645686774779830893971563599575587977498

OpenBenchmarking.orgCelsius, Fewer Is BetterPlaidMLGPU Temperature MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1326395265Min: 47 / Avg: 50.92 / Max: 55Min: 54 / Avg: 57.18 / Max: 61Min: 43 / Avg: 45.8 / Max: 48Min: 58 / Avg: 60 / Max: 63Min: 59 / Avg: 61.1 / Max: 64Min: 46 / Avg: 50.9 / Max: 56Min: 46 / Avg: 48.78 / Max: 53Min: 58 / Avg: 61.6 / Max: 65Min: 49 / Avg: 51.2 / Max: 55Min: 35 / Avg: 41.89 / Max: 48Min: 44 / Avg: 51.33 / Max: 58Min: 52 / Avg: 59.73 / Max: 67Min: 52 / Avg: 59.71 / Max: 67Min: 44 / Avg: 46.33 / Max: 52

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Training - Network: IMDB LSTM - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl50100150200250SE +/- 0.17, N = 3SE +/- 0.50, N = 3SE +/- 0.03, N = 3SE +/- 0.60, N = 3SE +/- 0.49, N = 3SE +/- 0.38, N = 3SE +/- 0.82, N = 3SE +/- 0.27, N = 3SE +/- 0.72, N = 3SE +/- 0.25, N = 3SE +/- 0.19, N = 3SE +/- 0.24, N = 3SE +/- 0.19, N = 3SE +/- 0.96, N = 3SE +/- 0.57, N = 3134156153167187188198216246130144178184244159

Darktable

OpenBenchmarking.orgWatts, Fewer Is BetterDarktable 2.4.4System Power Consumption MonitorRX 580RX 590RX Vega 56RX Vega 6420406080100Min: 77.8 / Avg: 77.9 / Max: 78Min: 48 / Avg: 51.55 / Max: 55.1Min: 50.3 / Avg: 70.55 / Max: 90.8

PlaidML

OpenBenchmarking.orgCelsius, Fewer Is BetterPlaidMLGPU Temperature MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1326395265Min: 44 / Avg: 49.23 / Max: 54Min: 51 / Avg: 55.42 / Max: 59Min: 39 / Avg: 42.75 / Max: 45Min: 53 / Avg: 57.58 / Max: 61Min: 59 / Avg: 61.75 / Max: 63Min: 40 / Avg: 45 / Max: 50Min: 41 / Avg: 45.18 / Max: 49Min: 50 / Avg: 54.64 / Max: 59Min: 52 / Avg: 53.5 / Max: 56Min: 34 / Avg: 42.71 / Max: 48Min: 46 / Avg: 53.31 / Max: 59Min: 49 / Avg: 56.67 / Max: 63Min: 51 / Avg: 58.38 / Max: 64Min: 52 / Avg: 53.8 / Max: 56

clpeak

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterclpeakOpenCL Test: Double-Precision DoubleRX 580RX 590RX Vega 56RX Vega 642468103.353.506.226.24

PlaidML

OpenBenchmarking.orgCelsius, Fewer Is BetterPlaidMLGPU Temperature MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1326395265Min: 41 / Avg: 45.25 / Max: 47Min: 59 / Avg: 60.33 / Max: 61Min: 48 / Avg: 48 / Max: 48Min: 62 / Avg: 62 / Max: 62Min: 63 / Avg: 64 / Max: 65Min: 39 / Avg: 44.25 / Max: 48Min: 55 / Avg: 55 / Max: 55Min: 66 / Avg: 66 / Max: 66Min: 54 / Avg: 55.67 / Max: 58Min: 36 / Avg: 40.83 / Max: 46Min: 47 / Avg: 51.5 / Max: 56Min: 51 / Avg: 52.8 / Max: 57Min: 54 / Avg: 55.6 / Max: 59Min: 55 / Avg: 55 / Max: 55

OpenBenchmarking.orgExamples Per Second Per Watt, More Is BetterPlaidMLFP16: No - Mode: Training - Network: IMDB LSTM - Device: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX0.36450.7291.09351.4581.82251.081.141.241.141.141.621.561.561.540.890.951.071.111.60

OpenBenchmarking.orgCelsius, Fewer Is BetterPlaidMLGPU Temperature MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1326395265Min: 52 / Avg: 56.5 / Max: 59Min: 55 / Avg: 60 / Max: 64Min: 43 / Avg: 45.83 / Max: 48Min: 58 / Avg: 62 / Max: 65Min: 59 / Avg: 63 / Max: 66Min: 46 / Avg: 51.8 / Max: 55Min: 51 / Avg: 53.25 / Max: 55Min: 58 / Avg: 61.5 / Max: 64Min: 50 / Avg: 51.33 / Max: 53Min: 37 / Avg: 45.13 / Max: 49Min: 47 / Avg: 53.5 / Max: 58Min: 52 / Avg: 59.67 / Max: 64Min: 52 / Avg: 59.71 / Max: 65Min: 51 / Avg: 54 / Max: 58

OpenBenchmarking.orgCelsius, Fewer Is BetterPlaidMLGPU Temperature MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1326395265Min: 50 / Avg: 54.8 / Max: 58Min: 56 / Avg: 59.9 / Max: 64Min: 44 / Avg: 46.22 / Max: 48Min: 60 / Avg: 62.5 / Max: 65Min: 61 / Avg: 63.11 / Max: 66Min: 46 / Avg: 50.11 / Max: 56Min: 50 / Avg: 53.44 / Max: 58Min: 59 / Avg: 62.38 / Max: 66Min: 51 / Avg: 53.29 / Max: 57Min: 37 / Avg: 44.64 / Max: 50Min: 47 / Avg: 54.23 / Max: 60Min: 49 / Avg: 55.36 / Max: 63Min: 48 / Avg: 54.5 / Max: 60Min: 52 / Avg: 54.86 / Max: 58

LuxMark

OpenBenchmarking.orgScore Per Watt, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: Luxball HDRGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX30609012015085.5398.48114.1679.4289.34110.80131.09123.99133.4280.5378.90120.5898.89137.54

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.4.4Test: Server Rack - Acceleration: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX0.03830.07660.11490.15320.1915SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.130.120.130.130.120.110.100.110.100.170.170.170.170.10

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: TriadGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl3691215SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.21, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 311.9312.1912.1912.3012.5112.4312.5712.5712.689.109.367.557.5412.6812.441. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

clpeak

OpenBenchmarking.orgCelsius, Fewer Is BetterclpeakGPU Temperature MonitorRX 580RX 590RX Vega 56RX Vega 641122334455Min: 34 / Avg: 37.71 / Max: 50Min: 38 / Avg: 41.36 / Max: 56Min: 40 / Avg: 43.74 / Max: 49Min: 42 / Avg: 46.65 / Max: 57

PlaidML

OpenBenchmarking.orgCelsius, Fewer Is BetterPlaidMLGPU Temperature MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1224364860Min: 49 / Avg: 50 / Max: 51Min: 47 / Avg: 49.5 / Max: 51Min: 46 / Avg: 47 / Max: 48Min: 47 / Avg: 49.75 / Max: 51Min: 56 / Avg: 56.67 / Max: 57Min: 46 / Avg: 47.75 / Max: 50Min: 45 / Avg: 46.75 / Max: 48Min: 61 / Avg: 61.67 / Max: 62Min: 52 / Avg: 52.5 / Max: 53Min: 38 / Avg: 42 / Max: 47Min: 45 / Avg: 48.88 / Max: 53Min: 40 / Avg: 42.75 / Max: 46Min: 49 / Avg: 50.83 / Max: 54Min: 41 / Avg: 41.5 / Max: 42

JuliaGPU

OpenBenchmarking.orgCelsius, Fewer Is BetterJuliaGPU 1.2pts1GPU Temperature MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1122334455Min: 46 / Avg: 47.2 / Max: 49Min: 53 / Avg: 54.4 / Max: 56Min: 38 / Avg: 40.6 / Max: 42Min: 51 / Avg: 52.5 / Max: 54Min: 52 / Avg: 54.6 / Max: 57Min: 43 / Avg: 47.5 / Max: 50Min: 46 / Avg: 47 / Max: 48Min: 53 / Avg: 54.5 / Max: 56Min: 48 / Avg: 51.25 / Max: 53Min: 36 / Avg: 42.75 / Max: 46Min: 45 / Avg: 48 / Max: 49Min: 40 / Avg: 42.67 / Max: 45Min: 50 / Avg: 52.33 / Max: 55Min: 49 / Avg: 52.5 / Max: 54

clpeak

OpenBenchmarking.orgCelsius, Fewer Is BetterclpeakGPU Temperature MonitorRX 580RX 590RX Vega 56RX Vega 641020304050Min: 31 / Avg: 33.28 / Max: 41Min: 37 / Avg: 39.72 / Max: 48Min: 39 / Avg: 41.36 / Max: 48Min: 41 / Avg: 43.79 / Max: 49

Darktable

OpenBenchmarking.orgCelsius, Fewer Is BetterDarktable 2.4.4GPU Temperature MonitorRX 580RX 590RX Vega 56RX Vega 641020304050Min: 33 / Avg: 35 / Max: 39Min: 39 / Avg: 41.7 / Max: 45Min: 42 / Avg: 43.78 / Max: 49Min: 44 / Avg: 46.5 / Max: 52

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgCelsius, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10GPU Temperature MonitorRX 580RX 590RX Vega 56RX Vega 641122334455Min: 35 / Avg: 42 / Max: 49Min: 39 / Avg: 44.67 / Max: 55Min: 38 / Avg: 39.5 / Max: 41

cl-mem

OpenBenchmarking.orgCelsius, Fewer Is Bettercl-mem 2017-01-13GPU Temperature MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1224364860Min: 48 / Avg: 51.14 / Max: 52Min: 55 / Avg: 57.17 / Max: 58Min: 43 / Avg: 44 / Max: 45Min: 56 / Avg: 57 / Max: 58Min: 60 / Avg: 60.67 / Max: 61Min: 49 / Avg: 54 / Max: 56Min: 50 / Avg: 53.67 / Max: 56Min: 62 / Avg: 62 / Max: 62Min: 56 / Avg: 58.33 / Max: 61Min: 41 / Avg: 46.8 / Max: 49Min: 53 / Avg: 55.5 / Max: 57Min: 48 / Avg: 55.2 / Max: 60Min: 58 / Avg: 59.8 / Max: 62Min: 60 / Avg: 61 / Max: 62

OpenBenchmarking.orgCelsius, Fewer Is Bettercl-mem 2017-01-13GPU Temperature MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1326395265Min: 53 / Avg: 53 / Max: 53Min: 60 / Avg: 60.6 / Max: 61Min: 43 / Avg: 44.83 / Max: 46Min: 60 / Avg: 60.2 / Max: 61Min: 64 / Avg: 64 / Max: 64Min: 55 / Avg: 56 / Max: 57Min: 54 / Avg: 55.33 / Max: 56Min: 61 / Avg: 63.75 / Max: 65Min: 61 / Avg: 62 / Max: 63Min: 49 / Avg: 49.6 / Max: 50Min: 56 / Avg: 59.5 / Max: 62Min: 51 / Avg: 58.6 / Max: 62Min: 59 / Avg: 62.4 / Max: 65Min: 59 / Avg: 63 / Max: 65

clpeak

OpenBenchmarking.orgCelsius, Fewer Is BetterclpeakGPU Temperature MonitorRX 580RX 590RX Vega 56RX Vega 641020304050Min: 32 / Avg: 33.27 / Max: 37Min: 35 / Avg: 37.05 / Max: 40Min: 35 / Avg: 38.05 / Max: 43Min: 36 / Avg: 40.64 / Max: 48

OpenBenchmarking.orgCelsius, Fewer Is BetterclpeakGPU Temperature MonitorRX 580RX 590RX Vega 56RX Vega 641020304050Min: 32 / Avg: 32.71 / Max: 45Min: 36 / Avg: 37.43 / Max: 48Min: 36 / Avg: 37.93 / Max: 40Min: 38 / Avg: 40.13 / Max: 43

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Transfer Bandwidth enqueueReadBufferGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl48121620SE +/- 0.09, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 3SE +/- 0.01, N = 3SE +/- 0.33, N = 3SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.13, N = 311.1511.3311.1511.3411.2911.2911.2511.1311.2915.8415.9216.6316.2211.1615.791. (CXX) g++ options: -O3 -rdynamic -lOpenCL

cl-mem

OpenBenchmarking.orgCelsius, Fewer Is Bettercl-mem 2017-01-13GPU Temperature MonitorGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1428425670Min: 54 / Avg: 55.88 / Max: 57Min: 64 / Avg: 64.8 / Max: 66Min: 47 / Avg: 47 / Max: 47Min: 63 / Avg: 64.17 / Max: 65Min: 68 / Avg: 68.33 / Max: 69Min: 56 / Avg: 58.5 / Max: 60Min: 60 / Avg: 62 / Max: 63Min: 67 / Avg: 68.67 / Max: 70Min: 66 / Avg: 67 / Max: 68Min: 47 / Avg: 52 / Max: 53Min: 59 / Avg: 64 / Max: 66Min: 64 / Avg: 66 / Max: 68Min: 61 / Avg: 66.4 / Max: 69Min: 66 / Avg: 68.33 / Max: 70

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.4.4Test: Masskrug - Acceleration: OpenCLGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTX1.22632.45263.67894.90526.1315SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 34.173.924.013.973.873.823.683.783.695.305.455.285.323.69

clpeak

OpenBenchmarking.orgGBPS Per Watt, More Is BetterclpeakOpenCL Test: Transfer Bandwidth enqueueReadBufferRX 580RX 590RX Vega 56RX Vega 640.04950.0990.14850.1980.24750.160.150.220.21

Darktable

OpenBenchmarking.orgCelsius, Fewer Is BetterDarktable 2.4.4GPU Temperature MonitorRX 580RX 590RX Vega 56RX Vega 64918273645Min: 30 / Avg: 30.8 / Max: 31Min: 38 / Avg: 38.25 / Max: 39Min: 41 / Avg: 41.4 / Max: 42Min: 42 / Avg: 42.67 / Max: 43

clpeak

OpenBenchmarking.orgGBPS Per Watt, More Is BetterclpeakOpenCL Test: Transfer Bandwidth enqueueWriteBufferRX 580RX 590RX Vega 56RX Vega 640.13280.26560.39840.53120.6640.450.420.590.56

Darktable

OpenBenchmarking.orgCelsius, Fewer Is BetterDarktable 2.4.4GPU Temperature MonitorRX 580RX 590RX Vega 56RX Vega 64918273645Min: 30 / Avg: 30 / Max: 30Min: 37 / Avg: 37.67 / Max: 38Min: 40 / Avg: 40.25 / Max: 41Min: 42 / Avg: 42 / Max: 42

OpenBenchmarking.orgCelsius, Fewer Is BetterDarktable 2.4.4GPU Temperature MonitorRX 580RX 590RX Vega 56RX Vega 64918273645

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgCelsius, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10GPU Temperature MonitorRX 580RX 590RX Vega 56RX Vega 641020304050Min: 37 / Avg: 37 / Max: 37Min: 40 / Avg: 41 / Max: 42Min: 42 / Avg: 42.5 / Max: 43Min: 49 / Avg: 49.5 / Max: 50

clpeak

OpenBenchmarking.orgCelsius, Fewer Is BetterclpeakGPU Temperature MonitorRX 580RX 590RX Vega 56RX Vega 64816243240Min: 31 / Avg: 31.03 / Max: 32Min: 35 / Avg: 35.11 / Max: 38Min: 32 / Avg: 32.61 / Max: 34Min: 32 / Avg: 32.11 / Max: 33

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgCelsius, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10GPU Temperature MonitorRX 580RX 590RX Vega 56RX Vega 64918273645Min: 39 / Avg: 40.5 / Max: 42Min: 39 / Avg: 39.5 / Max: 40

clpeak

OpenBenchmarking.orgCelsius, Fewer Is BetterclpeakGPU Temperature MonitorRX 580RX 590RX Vega 56RX Vega 64816243240Min: 31 / Avg: 31.18 / Max: 32Min: 35 / Avg: 35.21 / Max: 36Min: 33 / Avg: 33.73 / Max: 35Min: 32 / Avg: 33.85 / Max: 36

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Server Rack - Acceleration: OpenCLamdocl0.02030.04060.06090.08120.1015SE +/- 0.00, N = 30.09

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Server Room - Acceleration: OpenCLamdocl0.16880.33760.50640.67520.844SE +/- 0.01, N = 30.75

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Masskrug - Acceleration: OpenCLamdocl1.08232.16463.24694.32925.4115SE +/- 0.06, N = 34.81

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Boat - Acceleration: OpenCLamdocl0.6121.2241.8362.4483.06SE +/- 0.01, N = 32.72

System Power Consumption Monitor

OpenBenchmarking.orgWattsSystem Power Consumption MonitorPhoronix Test Suite System MonitoringRX 580RX 590RX Vega 56RX Vega 6450100150200250Min: 69 / Avg: 125.65 / Max: 229.5Min: 75 / Avg: 138.2 / Max: 253.3Min: 47.1 / Avg: 125.63 / Max: 271.3Min: 49.7 / Avg: 129.09 / Max: 305.4

GPU Temperature Monitor

OpenBenchmarking.orgCelsiusGPU Temperature MonitorPhoronix Test Suite System MonitoringRX 580RX 590RX Vega 56RX Vega 641428425670Min: 26 / Avg: 39.71 / Max: 61Min: 35 / Avg: 46.18 / Max: 73Min: 28 / Avg: 47.45 / Max: 74Min: 45 / Avg: 52.93 / Max: 65

System Power Consumption Monitor

OpenBenchmarking.orgWattsSystem Power Consumption MonitorPhoronix Test Suite System MonitoringGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiTITAN RTX70140210280350Min: 42.3 / Avg: 142.19 / Max: 280.5Min: 47.2 / Avg: 123.43 / Max: 255.8Min: 40.2 / Avg: 143.79 / Max: 318.2Min: 47.2 / Avg: 198.85 / Max: 370.3Min: 42.5 / Avg: 144.37 / Max: 300.1Min: 43.9 / Avg: 160.13 / Max: 317.6Min: 46 / Avg: 176.62 / Max: 334.5Min: 47.2 / Avg: 220.83 / Max: 367.7Min: 49.4 / Avg: 228.34 / Max: 363.1

GPU Temperature Monitor

OpenBenchmarking.orgCelsiusGPU Temperature MonitorPhoronix Test Suite System MonitoringGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiTITAN RTX1632486480Min: 32 / Avg: 61.66 / Max: 76Min: 38 / Avg: 45.88 / Max: 53Min: 31 / Avg: 60.14 / Max: 74Min: 39 / Avg: 66.36 / Max: 82Min: 37 / Avg: 55.81 / Max: 70Min: 32 / Avg: 56.83 / Max: 74Min: 48 / Avg: 67.06 / Max: 83Min: 43 / Avg: 61.88 / Max: 77Min: 33 / Avg: 62.56 / Max: 79

clpeak

OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl3K6K9K12K15KSE +/- 38.63, N = 3SE +/- 21.00, N = 3SE +/- 6.17, N = 3SE +/- 25.25, N = 3SE +/- 76.28, N = 3SE +/- 444.77, N = 3SE +/- 498.12, N = 3SE +/- 679.58, N = 3SE +/- 517.75, N = 3SE +/- 0.02, N = 3SE +/- 6.53, N = 3SE +/- 1.32, N = 3SE +/- 3.01, N = 3SE +/- 1004.15, N = 3SE +/- 5.46, N = 3125216812068239832636705778099521490612521416199724791484819611. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision FloatGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRX 580RX 590RX Vega 56RX Vega 64TITAN RTXamdocl4K8K12K16K20KSE +/- 3.56, N = 3SE +/- 393.27, N = 3SE +/- 14.43, N = 3SE +/- 396.02, N = 3SE +/- 782.31, N = 3SE +/- 657.16, N = 3SE +/- 495.99, N = 3SE +/- 732.21, N = 3SE +/- 1065.18, N = 3SE +/- 1.21, N = 3SE +/- 15.75, N = 3SE +/- 38.50, N = 3SE +/- 41.13, N = 3SE +/- 688.69, N = 3SE +/- 10.63, N = 342395878677679341085366307968102701535262027069103571246916386105911. (CXX) g++ options: -O3 -rdynamic -lOpenCL

128 Results Shown

clpeak
LeelaChessZero
Darktable
LeelaChessZero:
  OpenCL
  System Power Consumption Monitor
  System Power Consumption Monitor
  System Power Consumption Monitor
  System Power Consumption Monitor
  System Power Consumption Monitor
  System Power Consumption Monitor
  System Power Consumption Monitor
  System Power Consumption Monitor
  System Power Consumption Monitor
  System Power Consumption Monitor
  System Power Consumption Monitor
  System Power Consumption Monitor
  System Power Consumption Monitor
  System Power Consumption Monitor
  System Power Consumption Monitor
  System Power Consumption Monitor
  System Power Consumption Monitor
Darktable
PlaidML
SHOC Scalable HeterOgeneous Computing
clpeak
clpeak
SHOC Scalable HeterOgeneous Computing
JuliaGPU
LeelaChessZero
SHOC Scalable HeterOgeneous Computing
cl-mem:
  Read
  System Power Consumption Monitor
  OpenCL - Texture Read Bandwidth
PlaidML:
  No - Inference - VGG16 - OpenCL
  Yes - Inference - VGG16 - OpenCL
  No - Inference - ResNet 50 - OpenCL
clpeak:
  System Power Consumption Monitor:
    Watts
    Watts
    Watts
  Yes - Inference - VGG16 - OpenCL:
    Examples Per Second Per Watt
PlaidML
Darktable
LuxMark
cl-mem
PlaidML
clpeak:
  Global Memory Bandwidth
  Transfer Bandwidth enqueueWriteBuffer
PlaidML
cl-mem:
  Write
  Copy
PlaidML
PlaidML
PlaidML
PlaidML
PlaidML:
  Yes - Inference - ResNet 50 - OpenCL
  No - Inference - Mobilenet - OpenCL
PlaidML
JuliaGPU:
  GPU
  GPU Temp Monitor
  No - Inference - Inception V3 - OpenCL
  System Power Consumption Monitor
  No - Inference - IMDB LSTM - OpenCL
PlaidML
LeelaChessZero:
  GPU Temp Monitor
  Yes - Inference - Inception V3 - OpenCL
  Single-Precision Float
  Write
  Copy
  System Power Consumption Monitor
  System Power Consumption Monitor
  GPU Temp Monitor
  System Power Consumption Monitor
  GPU Temp Monitor
  Yes - Inference - Mobilenet - OpenCL
  GPU Temp Monitor
  GPU Temp Monitor
  System Power Consumption Monitor
  GPU Temp Monitor
  Integer Compute INT
  GPU Temp Monitor
  Global Memory Bandwidth
  GPU Temp Monitor
JuliaGPU
PlaidML
PlaidML
PlaidML
Darktable:
  System Power Consumption Monitor
  GPU Temp Monitor
  Double-Precision Double
  GPU Temp Monitor
  No - Training - IMDB LSTM - OpenCL
  GPU Temp Monitor
  GPU Temp Monitor
  GPU - Luxball HDR
Darktable
SHOC Scalable HeterOgeneous Computing
clpeak:
  GPU Temp Monitor:
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
clpeak
cl-mem
Darktable
clpeak:
  Transfer Bandwidth enqueueReadBuffer
  GPU Temp Monitor
  Transfer Bandwidth enqueueWriteBuffer
  GPU Temp Monitor
  GPU Temp Monitor
  GPU Temp Monitor
  GPU Temp Monitor
  GPU Temp Monitor
  GPU Temp Monitor
Darktable:
  Server Rack - OpenCL
  Server Room - OpenCL
  Masskrug - OpenCL
  Boat - OpenCL
System Power Consumption Monitor:
  Phoronix Test Suite System Monitoring:
    Watts
    Celsius
    Watts
    Celsius
clpeak:
  Integer Compute INT
  Single-Precision Float