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 NVIDIA vs. Radeon OpenCL Linux GPU Compute - Phoronix Test Suite NVIDIA vs. Radeon OpenCL Linux GPU Compute NVIDIA Linux GPU computing benchmarks by Michael Larabel for a future article.
HTML result view exported from: https://openbenchmarking.org/result/1901304-SP-1901305SP07&grs&sro .
NVIDIA vs. Radeon OpenCL Linux GPU Compute Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Vulkan Compiler File-System Screen Resolution GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti TITAN RTX RX 580 RX 590 RX Vega 56 RX Vega 64 amdocl Intel Core i9-9900K @ 5.00GHz (8 Cores / 16 Threads) ASUS PRIME Z390-A (0602 BIOS) Intel Cannon Lake PCH Shared SRAM 16384MB Samsung SSD 970 EVO 250GB + 2000GB SABRENT NVIDIA GeForce GTX 1060 6GB (1506/4006MHz) Realtek ALC1220 Acer B286HK Intel I219-V Ubuntu 18.10 4.20.3-042003-generic (x86_64) GNOME Shell 3.30.1 X Server 1.20.1 NVIDIA 415.27 4.6.0 OpenCL 1.2 CUDA 10.0.132 1.1.84 GCC 8.2.0 ext4 3840x2160 NVIDIA 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) 20190127 4.5 Mesa 19.0.0-devel padoka PPA (LLVM 9.0.0) OpenCL 2.1 AMD-APP (2783.0) 1.1.90 Sapphire 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 17h 32768MB 1024GB INTEL SSDPEKKW010T7 + Samsung SSD 960 EVO 500GB + 512GB Crucial_CT512M55 + 1000GB SanDisk SDSSDH31 + 2000GB SanDisk SDSSDH32 AMD Radeon RX 56/64 8GB (1590/800MHz) AMD Device aaf8 SAMSUNG Intel I211 Arch rolling 4.20.5-zen1-1-zen (x86_64) KDE Plasma 5.14.5 X Server 1.20.3 amdgpu 18.1.0 4.5 Mesa 19.0.0-devel (git-69edc972fc) (LLVM 9.0.0) OpenCL 2.1 AMD-APP (2766.4) Clang 7.0.1 + LLVM 7.0.1 xfs OpenBenchmarking.org Compiler 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=gnu Processor 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 schedutil OpenCL 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: 4608 Python 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 3.7.2 Security 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 seccomp Kernel Details - amdocl: amdgpu.ppfeaturemask=0xffffffff amdgpu.gpu_recovery=1 Graphics Details - amdocl: GLAMOR
NVIDIA vs. Radeon OpenCL Linux GPU Compute clpeak: Kernel Latency darktable: Boat - OpenCL darktable: Server Room - OpenCL shoc: OpenCL - Texture Read Bandwidth clpeak: Double-Precision Double shoc: OpenCL - FFT SP lczero: OpenCL shoc: OpenCL - MD5 Hash plaidml: No - Inference - VGG16 - OpenCL plaidml: Yes - Inference - VGG16 - OpenCL plaidml: No - Inference - ResNet 50 - OpenCL plaidml: No - Training - Mobilenet - OpenCL luxmark: GPU - Luxball HDR cl-mem: Read plaidml: Yes - Inference - ResNet 50 - OpenCL clpeak: Global Memory Bandwidth clpeak: Transfer Bandwidth enqueueWriteBuffer cl-mem: Write cl-mem: Copy plaidml: No - Inference - IMDB LSTM - OpenCL plaidml: No - Inference - Inception V3 - OpenCL plaidml: No - Inference - Mobilenet - OpenCL plaidml: Yes - Inference - Inception V3 - OpenCL juliagpu: GPU plaidml: Yes - Inference - Mobilenet - OpenCL plaidml: No - Training - IMDB LSTM - OpenCL darktable: Server Rack - OpenCL shoc: OpenCL - Triad clpeak: Transfer Bandwidth enqueueReadBuffer darktable: Masskrug - OpenCL darktable: Server Rack - OpenCL darktable: Server Room - OpenCL darktable: Masskrug - OpenCL darktable: Boat - OpenCL clpeak: Integer Compute INT clpeak: Single-Precision Float GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti TITAN RTX RX 580 RX 590 RX Vega 56 RX Vega 64 amdocl 3.78 3.66 1.31 411 151 297 899 7.28 94.08 94.62 194 86.94 12256 153 183 145 12.54 139 138 180 86.11 592 88.85 183782626 552 134 0.13 11.93 11.15 4.17 1252 4239 3.64 2.89 1.10 447 224 453 1430 10.47 129 126 257 107 17287 205 237 196 12.60 192 187 228 116 764 117 218172062 664 156 0.12 12.19 11.33 3.92 1681 5878 3.92 2.93 1.16 433 242 501 1478 11.63 131 128 262 103 16776 205 237 197 12.55 190 187 224 118 755 120 221548016 645 153 0.13 12.19 11.15 4.01 2068 6776 3.77 2.72 1.10 527 297 575 1750 14.19 143 139 292 103 13803 229 264 222 12.59 216 209 259 133 801 132 239131324 686 167 0.13 12.30 11.34 3.97 2398 7934 3.99 2.26 1.03 596 415 972 2333 19.68 189 194 339 125 21682 337 334 329 12.57 336 317 330 167 883 167 265162875 774 187 0.12 12.51 11.29 3.87 3263 10853 3.65 2.22 0.82 1024 231 803 1484 15.87 150 148 309 113 21356 296 282 276 12.60 245 247 347 133 863 134 251611989 779 188 0.11 12.43 11.29 3.82 6705 6630 3.64 1.93 0.75 1077 266 988 1729 18.42 189 179 376 132 29532 392 333 365 12.48 313 330 382 156 1008 157 265682046 830 198 0.10 12.57 11.25 3.68 7780 7968 3.65 1.92 0.81 1121 343 1083 2259 23.74 203 192 400 133 29146 392 354 368 12.52 323 327 457 172 1045 168 278829238 893 216 0.11 12.57 11.13 3.78 9952 10270 3.83 1.64 0.75 1173 519 1445 3107 35.13 273 250 537 156 42787 544 458 505 12.59 439 454 605 225 1291 211 300922241 971 246 0.10 12.68 11.29 3.69 14906 15352 3.85 1.64 0.74 1158 540 1553 3275 36.28 289 264 556 160 46022 565 474 525 12.58 489 483 610 229 1336 215 303665447 977 244 0.10 12.68 11.16 3.69 14848 16386 4.97 13.54 4.18 211 392 547 640 8.05 65.18 60.98 133 42.04 15271 162 128 206 44.97 179 184 193 69.05 414 76.59 283078851 563 130 0.17 9.10 15.84 5.30 1252 6202 4.69 13.96 4.28 241 436 570 683 9.16 68.69 64.04 142 45.61 17221 178 137 217 44.19 185 193 218 75.41 453 82.71 302623440 599 144 0.17 9.36 15.92 5.45 1416 7069 7.01 13.47 4.18 355 698 927 758 12.70 120.44 106.66 228 71.23 31079 151 195 317 44.97 305 204 263 106.65 720 109.03 346484064 575 178 0.17 7.55 16.63 5.28 1997 10357 6.96 13.72 4.21 425 833 922 856 16.39 137.62 119.99 270 74.31 32565 159 213 362 44.31 356 222 279 119.06 835 120.03 366159438 587 184 0.17 7.54 16.22 5.32 2479 12469 33.79 369 689 895 1189 12.95 120.11 108.36 262 75.09 28140 340 215 318 37.97 325 309 270 138.74 781 116.49 312792565 498 159 12.44 15.79 0.09 0.75 4.81 2.72 1961 10591 OpenBenchmarking.org
clpeak OpenCL Test: Kernel Latency OpenBenchmarking.org us, Fewer Is Better clpeak OpenCL Test: Kernel Latency GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 8 16 24 32 40 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.14, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.00, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.10, N = 3 SE +/- 0.24, N = 3 3.78 3.64 3.92 3.77 3.99 3.65 3.64 3.65 3.83 4.97 4.69 7.01 6.96 3.85 33.79 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
LeelaChessZero System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better LeelaChessZero 0.20.1 System Power Consumption Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 60 120 180 240 300 Min: 41.9 / Avg: 150.59 / Max: 180 Min: 42.6 / Avg: 184.04 / Max: 213.3 Min: 80 / Avg: 156.39 / Max: 189.7 Min: 40.2 / Avg: 148.14 / Max: 249.5 Min: 96.9 / Avg: 265.17 / Max: 323.1 Min: 69.4 / Avg: 196.01 / Max: 230 Min: 75.1 / Avg: 186.61 / Max: 251.7 Min: 88.3 / Avg: 222.99 / Max: 288.3 Min: 48.2 / Avg: 205.76 / Max: 349.4 Min: 69.3 / Avg: 171.21 / Max: 229.5 Min: 75.2 / Avg: 188.72 / Max: 253.3 Min: 47.2 / Avg: 173.2 / Max: 262.2 Min: 50.2 / Avg: 313.27 / Max: 342.7 Min: 97.7 / Avg: 148.16 / Max: 357.7
Darktable Test: Boat - Acceleration: OpenCL OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.4.4 Test: Boat - Acceleration: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 3.66 2.89 2.93 2.72 2.26 2.22 1.93 1.92 1.64 13.54 13.96 13.47 13.72 1.64
LeelaChessZero Backend: OpenCL OpenBenchmarking.org Nodes Per Second Per Watt, More Is Better LeelaChessZero 0.20.1 Backend: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 5 10 15 20 25 5.97 7.77 9.45 11.81 8.80 7.57 9.27 10.13 15.10 3.74 3.62 4.38 2.73 22.11
PlaidML System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 60 120 180 240 300 Min: 72.7 / Avg: 144.61 / Max: 170.9 Min: 43.1 / Avg: 162.78 / Max: 197.9 Min: 47.9 / Avg: 146.58 / Max: 171.7 Min: 45.1 / Avg: 180.6 / Max: 225 Min: 127.7 / Avg: 231.45 / Max: 296.9 Min: 44 / Avg: 167.51 / Max: 215.1 Min: 68.7 / Avg: 183.65 / Max: 245.5 Min: 50.9 / Avg: 188.45 / Max: 269.3 Min: 47.6 / Avg: 212.98 / Max: 331.1 Min: 73 / Avg: 163.55 / Max: 194.8 Min: 86.9 / Avg: 184.98 / Max: 216.4 Min: 78.5 / Avg: 188.36 / Max: 262.2 Min: 52.7 / Avg: 216.48 / Max: 338.1 Min: 55.4 / Avg: 223.68 / Max: 345.8
LuxMark System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better LuxMark 3.1 System Power Consumption Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 60 120 180 240 300 Min: 111.3 / Avg: 143.3 / Max: 145.4 Min: 82.6 / Avg: 175.54 / Max: 179.2 Min: 47.6 / Avg: 146.95 / Max: 149.7 Min: 89.3 / Avg: 173.79 / Max: 175.8 Min: 161.6 / Avg: 242.69 / Max: 248.1 Min: 44 / Avg: 192.74 / Max: 197.4 Min: 46 / Avg: 225.28 / Max: 233.2 Min: 48.9 / Avg: 235.08 / Max: 244.1 Min: 47.7 / Avg: 320.7 / Max: 332 Min: 71.5 / Avg: 189.63 / Max: 196.7 Min: 82.1 / Avg: 218.27 / Max: 228.9 Min: 60.2 / Avg: 257.74 / Max: 269.1 Min: 49.5 / Avg: 329.31 / Max: 338.6 Min: 50.6 / Avg: 334.61 / Max: 351.7
PlaidML System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 60 120 180 240 300 Min: 71.5 / Avg: 140.59 / Max: 158.7 Min: 43.1 / Avg: 156.77 / Max: 185.9 Min: 48.9 / Avg: 127.46 / Max: 146.6 Min: 115.7 / Avg: 176.49 / Max: 201.1 Min: 50.4 / Avg: 194.3 / Max: 254.7 Min: 45.1 / Avg: 125.88 / Max: 192.6 Min: 46.5 / Avg: 126.45 / Max: 198.6 Min: 47.4 / Avg: 135.75 / Max: 228.3 Min: 48.3 / Avg: 198.43 / Max: 287.4 Min: 72.7 / Avg: 136.8 / Max: 186.1 Min: 78.3 / Avg: 178.69 / Max: 218.6 Min: 49.4 / Avg: 145.38 / Max: 261.4 Min: 88.8 / Avg: 211.83 / Max: 333.3 Min: 52.5 / Avg: 178.13 / Max: 298.5
cl-mem System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better cl-mem 2017-01-13 System Power Consumption Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 60 120 180 240 300 Min: 57.7 / Avg: 108.33 / Max: 126.1 Min: 64.6 / Avg: 132.44 / Max: 150.8 Min: 49.3 / Avg: 113.36 / Max: 139.4 Min: 43.2 / Avg: 119.3 / Max: 162.2 Min: 49.6 / Avg: 139.67 / Max: 192.8 Min: 43.7 / Avg: 111.03 / Max: 156.9 Min: 115.9 / Avg: 150.6 / Max: 185.3 Min: 52.6 / Avg: 141.73 / Max: 186.7 Min: 136 / Avg: 198.3 / Max: 260.6 Min: 73.1 / Avg: 141.22 / Max: 169.4 Min: 194.4 / Avg: 199.58 / Max: 203.7 Min: 49.6 / Avg: 203.34 / Max: 252.9 Min: 51.9 / Avg: 197.96 / Max: 328.9 Min: 54.7 / Avg: 99.5 / Max: 144.3
PlaidML System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 60 120 180 240 300 Min: 58.2 / Avg: 131.14 / Max: 167.2 Min: 43.1 / Avg: 136.92 / Max: 191.2 Min: 48.4 / Avg: 125.32 / Max: 169.8 Min: 70.3 / Avg: 172.91 / Max: 216.6 Min: 65.2 / Avg: 179.46 / Max: 287.9 Min: 62.3 / Avg: 137.76 / Max: 208 Min: 47.2 / Avg: 141.31 / Max: 234 Min: 49.8 / Avg: 158.89 / Max: 252.8 Min: 47.7 / Avg: 180.78 / Max: 312 Min: 73.2 / Avg: 147.27 / Max: 187.1 Min: 79.7 / Avg: 162.83 / Max: 210.1 Min: 50.2 / Avg: 151.48 / Max: 258.1 Min: 53.4 / Avg: 217.55 / Max: 319.8 Min: 58.3 / Avg: 176.01 / Max: 322.5
PlaidML System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 60 120 180 240 300 Min: 71.4 / Avg: 121.65 / Max: 172.6 Min: 45.2 / Avg: 145.44 / Max: 201.2 Min: 48.6 / Avg: 134.71 / Max: 168.9 Min: 91.9 / Avg: 152.34 / Max: 225.3 Min: 61.2 / Avg: 185.7 / Max: 280.5 Min: 65 / Avg: 134.41 / Max: 208.9 Min: 49.8 / Avg: 153.92 / Max: 242.3 Min: 48.4 / Avg: 158.95 / Max: 257.5 Min: 100.3 / Avg: 172.57 / Max: 323.3 Min: 73 / Avg: 145.33 / Max: 194.5 Min: 81 / Avg: 162.42 / Max: 220 Min: 50.1 / Avg: 150.39 / Max: 271.1 Min: 81.5 / Avg: 177.38 / Max: 338.2 Min: 102.3 / Avg: 194.3 / Max: 332.7
PlaidML System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 60 120 180 240 300 Min: 70.6 / Avg: 141.88 / Max: 164.5 Min: 85.2 / Avg: 157.11 / Max: 185.1 Min: 50 / Avg: 141.65 / Max: 161.4 Min: 91.6 / Avg: 167.52 / Max: 214.9 Min: 123.8 / Avg: 205.47 / Max: 275.7 Min: 45.2 / Avg: 158.66 / Max: 201.6 Min: 47.5 / Avg: 159.79 / Max: 224.3 Min: 50.1 / Avg: 167.47 / Max: 240.9 Min: 49.3 / Avg: 185.12 / Max: 298.3 Min: 71.3 / Avg: 157.31 / Max: 201.8 Min: 79.3 / Avg: 178.28 / Max: 235.4 Min: 78.5 / Avg: 172.43 / Max: 257.5 Min: 50.9 / Avg: 173.75 / Max: 315.1 Min: 63.8 / Avg: 192.88 / Max: 301.5
PlaidML System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 50 100 150 200 250 Min: 70.1 / Avg: 124.21 / Max: 145 Min: 82.2 / Avg: 136.83 / Max: 164.9 Min: 104.8 / Avg: 123.57 / Max: 135.6 Min: 90.8 / Avg: 146.71 / Max: 176.8 Min: 50.4 / Avg: 165.05 / Max: 214.8 Min: 44.3 / Avg: 116.14 / Max: 162.7 Min: 47.1 / Avg: 127.27 / Max: 169.5 Min: 46.4 / Avg: 138.03 / Max: 185.4 Min: 48.6 / Avg: 159.87 / Max: 223.7 Min: 71.3 / Avg: 146.11 / Max: 185.3 Min: 80.2 / Avg: 152.62 / Max: 212.4 Min: 74.8 / Avg: 165.69 / Max: 271.3 Min: 52.2 / Avg: 165.89 / Max: 305.6 Min: 57.5 / Avg: 152.07 / Max: 231.9
clpeak System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better clpeak System Power Consumption Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 60 120 180 240 300 Min: 71 / Avg: 109.44 / Max: 203.5 Min: 79.2 / Avg: 117.14 / Max: 233.2 Min: 49.1 / Avg: 89.06 / Max: 257.9 Min: 52.7 / Avg: 104.67 / Max: 335.3
SHOC Scalable HeterOgeneous Computing System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 System Power Consumption Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 50 100 150 200 250 Min: 42.1 / Avg: 105.4 / Max: 135.1 Min: 43.3 / Avg: 130.75 / Max: 158.9 Min: 48.4 / Avg: 122.39 / Max: 144.2 Min: 43.4 / Avg: 134.92 / Max: 163.8 Min: 53.7 / Avg: 180.42 / Max: 218.2 Min: 148.5 / Avg: 159.28 / Max: 177.5 Min: 52.2 / Avg: 156.43 / Max: 195 Min: 169.9 / Avg: 187.73 / Max: 213.5 Min: 49 / Avg: 235.34 / Max: 283.1 Min: 69.1 / Avg: 131.16 / Max: 160.2 Min: 78.3 / Avg: 160.59 / Max: 187.1 Min: 47.3 / Avg: 173.9 / Max: 235.2 Min: 49.7 / Avg: 228.87 / Max: 263.7 Min: 49.4 / Avg: 244.67 / Max: 287.4
clpeak System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better clpeak System Power Consumption Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 60 120 180 240 300 Min: 69.5 / Avg: 116.89 / Max: 196.7 Min: 77.7 / Avg: 124.39 / Max: 220.8 Min: 47.5 / Avg: 112.24 / Max: 264.2 Min: 63.8 / Avg: 133.52 / Max: 322.1
PlaidML System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 60 120 180 240 300 Min: 60.4 / Avg: 122.52 / Max: 164.5 Min: 83.8 / Avg: 134.85 / Max: 189.4 Min: 48.5 / Avg: 113.89 / Max: 160.8 Min: 91.6 / Avg: 162.7 / Max: 211.1 Min: 122.3 / Avg: 187.68 / Max: 270.3 Min: 86.5 / Avg: 143.68 / Max: 202.9 Min: 78.4 / Avg: 132.98 / Max: 222.4 Min: 47.4 / Avg: 148.19 / Max: 240.2 Min: 48.4 / Avg: 155.12 / Max: 292.5 Min: 73.6 / Avg: 141.5 / Max: 187.8 Min: 81.1 / Avg: 153.59 / Max: 208.6 Min: 50.5 / Avg: 141.19 / Max: 254.3 Min: 82.4 / Avg: 172.03 / Max: 313.6 Min: 52.6 / Avg: 162.76 / Max: 301.7
PlaidML System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 50 100 150 200 250 Min: 87.5 / Avg: 132.19 / Max: 156.7 Min: 81.8 / Avg: 153.87 / Max: 183 Min: 56.1 / Avg: 132.15 / Max: 155 Min: 89.5 / Avg: 168.75 / Max: 202.8 Min: 120.7 / Avg: 202.56 / Max: 256.6 Min: 45 / Avg: 144.95 / Max: 190.7 Min: 45.8 / Avg: 146.81 / Max: 206.6 Min: 47.5 / Avg: 155.97 / Max: 224.6 Min: 48.4 / Avg: 188.73 / Max: 275.6 Min: 73.1 / Avg: 146.45 / Max: 195.4 Min: 91.8 / Avg: 163.54 / Max: 221.5 Min: 58.9 / Avg: 147.82 / Max: 249.5 Min: 50.6 / Avg: 181.52 / Max: 296 Min: 51.5 / Avg: 168.92 / Max: 275.4
PlaidML System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 50 100 150 200 250 Min: 41.8 / Avg: 76.7 / Max: 94.4 Min: 45.9 / Avg: 107.3 / Max: 155.1 Min: 49.7 / Avg: 93.67 / Max: 125.7 Min: 44.3 / Avg: 147.75 / Max: 195.1 Min: 53.3 / Avg: 125.73 / Max: 165.2 Min: 43.1 / Avg: 95.9 / Max: 118.8 Min: 115.1 / Avg: 115.83 / Max: 116.5 Min: 52 / Avg: 97.93 / Max: 121 Min: 48.2 / Avg: 152.87 / Max: 274.6 Min: 71.7 / Avg: 114.33 / Max: 178.6 Min: 82.4 / Avg: 137.7 / Max: 205.5 Min: 72.5 / Avg: 123.7 / Max: 259.6 Min: 52.5 / Avg: 111.85 / Max: 223.9 Min: 54 / Avg: 200.17 / Max: 274.2
cl-mem System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better cl-mem 2017-01-13 System Power Consumption Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 50 100 150 200 250 Min: 55.5 / Avg: 114.96 / Max: 125.8 Min: 46.7 / Avg: 129.34 / Max: 151 Min: 49 / Avg: 121.24 / Max: 139.8 Min: 102.3 / Avg: 149.02 / Max: 162.5 Min: 52.6 / Avg: 161.7 / Max: 217.6 Min: 45.9 / Avg: 126.65 / Max: 159.6 Min: 48.6 / Avg: 145.97 / Max: 196.3 Min: 50.4 / Avg: 148 / Max: 197.9 Min: 57.7 / Avg: 161.45 / Max: 265.2 Min: 73.5 / Avg: 144 / Max: 170.7 Min: 82 / Avg: 176.16 / Max: 207.2 Min: 50.8 / Avg: 153.05 / Max: 254.1 Min: 55.2 / Avg: 211.77 / Max: 297.7 Min: 55.2 / Avg: 156.17 / Max: 266.5
SHOC Scalable HeterOgeneous Computing System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 System Power Consumption Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 50 100 150 200 250 Min: 92.2 / Avg: 137.05 / Max: 181.9 Min: 138.3 / Avg: 188 / Max: 237.7 Min: 47.8 / Avg: 120.9 / Max: 194 Min: 62.2 / Avg: 183.8 / Max: 305.4
cl-mem System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better cl-mem 2017-01-13 System Power Consumption Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 50 100 150 200 250 Min: 43.4 / Avg: 98.27 / Max: 126.2 Min: 84.4 / Avg: 137.36 / Max: 151.6 Min: 50 / Avg: 124.63 / Max: 140.5 Min: 92.2 / Avg: 141.24 / Max: 162.2 Min: 216.4 / Avg: 217.73 / Max: 218.8 Min: 44.2 / Avg: 131.53 / Max: 164.4 Min: 46.9 / Avg: 139.57 / Max: 185.9 Min: 98.5 / Avg: 128.93 / Max: 169.3 Min: 51 / Avg: 155.07 / Max: 243.7 Min: 73 / Avg: 147.4 / Max: 169 Min: 78.7 / Avg: 161.08 / Max: 200.6 Min: 207.8 / Avg: 229.9 / Max: 252.1 Min: 52.5 / Avg: 191.32 / Max: 275.7 Min: 55 / Avg: 190.13 / Max: 258.3
Darktable Test: Server Room - Acceleration: OpenCL OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.4.4 Test: Server Room - Acceleration: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 0.963 1.926 2.889 3.852 4.815 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 1.31 1.10 1.16 1.10 1.03 0.82 0.75 0.81 0.75 4.18 4.28 4.18 4.21 0.74
PlaidML System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 40 80 120 160 200 Min: 43.2 / Avg: 99.8 / Max: 140.7 Min: 48.4 / Avg: 126.46 / Max: 165 Min: 48.1 / Avg: 99.69 / Max: 140.6 Min: 91.7 / Avg: 152.84 / Max: 169.4 Min: 47.2 / Avg: 121.72 / Max: 213.3 Min: 47.3 / Avg: 110.84 / Max: 168.5 Min: 49.9 / Avg: 120.6 / Max: 185.8 Min: 48 / Avg: 132.2 / Max: 198.2 Min: 48.4 / Avg: 137.54 / Max: 235.7 Min: 73.6 / Avg: 119.65 / Max: 155.1 Min: 78.7 / Avg: 135.11 / Max: 174.8 Min: 49.7 / Avg: 124.48 / Max: 221.8 Min: 75.8 / Avg: 156.29 / Max: 240.3 Min: 56 / Avg: 163.54 / Max: 245.3
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Texture Read Bandwidth OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: Texture Read Bandwidth GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 300 600 900 1200 1500 SE +/- 1.03, N = 3 SE +/- 0.82, N = 3 SE +/- 0.80, N = 3 SE +/- 0.28, N = 3 SE +/- 1.91, N = 3 SE +/- 0.24, N = 3 SE +/- 1.24, N = 3 SE +/- 2.94, N = 3 SE +/- 1.02, N = 3 SE +/- 1.47, N = 3 SE +/- 1.57, N = 3 SE +/- 0.86, N = 3 SE +/- 0.60, N = 3 SE +/- 3.52, N = 3 SE +/- 1.03, N = 3 411 447 433 527 596 1024 1077 1121 1173 211 241 355 425 1158 369 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
clpeak System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better clpeak System Power Consumption Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 50 100 150 200 250 Min: 73.3 / Avg: 98.79 / Max: 101.9 Min: 79.3 / Avg: 107.03 / Max: 127.7 Min: 49.2 / Avg: 81.54 / Max: 259 Min: 51.6 / Avg: 87.77 / Max: 273.2
clpeak OpenCL Test: Double-Precision Double OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Double-Precision Double GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 200 400 600 800 1000 SE +/- 0.05, N = 3 SE +/- 0.26, N = 3 SE +/- 0.24, N = 3 SE +/- 0.02, N = 3 SE +/- 0.14, N = 3 SE +/- 0.60, N = 3 SE +/- 0.72, N = 3 SE +/- 0.98, N = 3 SE +/- 1.25, N = 3 SE +/- 0.01, N = 3 SE +/- 0.21, N = 3 SE +/- 1.26, N = 3 SE +/- 1.09, N = 3 SE +/- 1.29, N = 3 SE +/- 1.18, N = 3 151 224 242 297 415 231 266 343 519 392 436 698 833 540 689 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: FFT SP OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: FFT SP GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 300 600 900 1200 1500 SE +/- 2.45, N = 3 SE +/- 8.74, N = 3 SE +/- 1.30, N = 3 SE +/- 1.43, N = 3 SE +/- 2.56, N = 3 SE +/- 10.50, N = 3 SE +/- 46.80, N = 3 SE +/- 6.71, N = 3 SE +/- 11.70, N = 3 SE +/- 0.36, N = 3 SE +/- 1.04, N = 3 SE +/- 1.97, N = 3 SE +/- 0.34, N = 3 SE +/- 2.67, N = 3 SE +/- 2.55, N = 3 297 453 501 575 972 803 988 1083 1445 547 570 927 922 1553 895 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
JuliaGPU System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better JuliaGPU 1.2pts1 System Power Consumption Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 40 80 120 160 200 Min: 57.5 / Avg: 112.76 / Max: 128.1 Min: 42.3 / Avg: 116.82 / Max: 147.4 Min: 47.7 / Avg: 111.88 / Max: 128.2 Min: 42.3 / Avg: 127 / Max: 157.8 Min: 67.7 / Avg: 159.15 / Max: 189.8 Min: 43.5 / Avg: 112.53 / Max: 153.7 Min: 52.9 / Avg: 116.58 / Max: 157.4 Min: 46.4 / Avg: 134.7 / Max: 169 Min: 99.5 / Avg: 147.3 / Max: 199.5 Min: 93.8 / Avg: 132.17 / Max: 160.8 Min: 75.7 / Avg: 142.48 / Max: 179.1 Min: 47.6 / Avg: 160.43 / Max: 218.2 Min: 49.9 / Avg: 71.23 / Max: 89 Min: 51.3 / Avg: 148.68 / Max: 204
LeelaChessZero Backend: OpenCL OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.20.1 Backend: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 700 1400 2100 2800 3500 SE +/- 6.27, N = 3 SE +/- 9.63, N = 3 SE +/- 13.26, N = 3 SE +/- 32.06, N = 3 SE +/- 25.14, N = 3 SE +/- 13.06, N = 3 SE +/- 20.57, N = 3 SE +/- 22.18, N = 3 SE +/- 20.98, N = 3 SE +/- 2.68, N = 3 SE +/- 2.57, N = 3 SE +/- 2.66, N = 3 SE +/- 5.51, N = 3 SE +/- 28.14, N = 3 SE +/- 16.88, N = 5 899 1430 1478 1750 2333 1484 1729 2259 3107 640 683 758 856 3275 1189 1. (CXX) g++ options: -lpthread
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: MD5 Hash OpenBenchmarking.org GHash/s, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: MD5 Hash GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 8 16 24 32 40 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.40, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.35, N = 3 SE +/- 0.02, N = 3 7.28 10.47 11.63 14.19 19.68 15.87 18.42 23.74 35.13 8.05 9.16 12.70 16.39 36.28 12.95 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
cl-mem Benchmark: Read OpenBenchmarking.org GB/s Per Watt, More Is Better cl-mem 2017-01-13 Benchmark: Read GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 0.8145 1.629 2.4435 3.258 4.0725 1.33 1.59 1.69 1.54 2.09 2.34 2.69 2.65 1.12 1.01 0.99 0.75 3.62
PlaidML System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 40 80 120 160 200 Min: 42.1 / Avg: 107.84 / Max: 141.6 Min: 42.8 / Avg: 91.98 / Max: 117.4 Min: 48.7 / Avg: 98.18 / Max: 132.6 Min: 43.7 / Avg: 93.48 / Max: 127.3 Min: 91.6 / Avg: 149.17 / Max: 203.2 Min: 45.5 / Avg: 121.65 / Max: 166.1 Min: 46 / Avg: 93.68 / Max: 129.3 Min: 56.3 / Avg: 130.87 / Max: 184.7 Min: 48.4 / Avg: 94.48 / Max: 113.3 Min: 75.6 / Avg: 109.4 / Max: 179 Min: 82.3 / Avg: 126.56 / Max: 194.9 Min: 49.6 / Avg: 92.35 / Max: 157.7 Min: 54 / Avg: 69.27 / Max: 82.4 Min: 52.9 / Avg: 110.8 / Max: 140.2
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Texture Read Bandwidth OpenBenchmarking.org GB/s Per Watt, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: Texture Read Bandwidth GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 2 4 6 8 10 3.90 3.42 3.54 3.91 3.30 6.43 6.88 5.97 4.98 1.61 1.50 2.04 1.86 4.73
PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 60 120 180 240 300 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 SE +/- 0.16, N = 3 SE +/- 0.27, N = 3 SE +/- 0.17, N = 3 SE +/- 0.36, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.18, N = 3 SE +/- 0.11, N = 3 SE +/- 0.72, N = 3 SE +/- 0.04, N = 3 94.08 129.00 131.00 143.00 189.00 150.00 189.00 203.00 273.00 65.18 68.69 120.44 137.62 289.00 120.11
PlaidML FP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 60 120 180 240 300 SE +/- 0.03, N = 3 SE +/- 0.12, N = 3 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 SE +/- 0.32, N = 3 SE +/- 0.15, N = 3 SE +/- 0.26, N = 3 SE +/- 0.32, N = 3 SE +/- 0.20, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.43, N = 3 SE +/- 0.55, N = 3 94.62 126.00 128.00 139.00 194.00 148.00 179.00 192.00 250.00 60.98 64.04 106.66 119.99 264.00 108.36
PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 120 240 360 480 600 SE +/- 0.11, N = 3 SE +/- 0.45, N = 3 SE +/- 0.24, N = 3 SE +/- 0.41, N = 3 SE +/- 0.55, N = 3 SE +/- 0.26, N = 3 SE +/- 0.33, N = 3 SE +/- 0.45, N = 3 SE +/- 0.31, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 2.52, N = 3 SE +/- 1.40, N = 3 SE +/- 1.67, N = 3 SE +/- 0.31, N = 3 194 257 262 292 339 309 376 400 537 133 142 228 270 556 262
clpeak System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better clpeak System Power Consumption Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 30 60 90 120 150 Min: 69.4 / Avg: 100.72 / Max: 186.8 Min: 76.7 / Avg: 105.71 / Max: 119.2 Min: 47.8 / Avg: 76.77 / Max: 77.8 Min: 49.5 / Avg: 80.89 / Max: 182.7
Darktable System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Darktable 2.4.4 System Power Consumption Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 40 80 120 160 200 Min: 74.4 / Avg: 164 / Max: 184.5 Min: 80.8 / Avg: 170.15 / Max: 205 Min: 118.8 / Avg: 139.2 / Max: 147 Min: 52.7 / Avg: 132.86 / Max: 151.4
Darktable System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Darktable 2.4.4 System Power Consumption Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 30 60 90 120 150 Min: 73 / Avg: 131.16 / Max: 186.9 Min: 79.3 / Avg: 145.78 / Max: 178.8 Min: 48.4 / Avg: 110.52 / Max: 178.2 Min: 127.1 / Avg: 138.95 / Max: 150.8
PlaidML FP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCL OpenBenchmarking.org Examples Per Second Per Watt, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 0.3375 0.675 1.0125 1.35 1.6875 0.72 0.92 1.02 0.80 1.08 1.08 1.27 1.21 1.38 0.41 0.39 0.70 0.55 1.50
PlaidML FP16: No - Mode: Training - Network: Mobilenet - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Training - Network: Mobilenet - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 40 80 120 160 200 SE +/- 0.03, N = 3 SE +/- 0.15, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.18, N = 3 SE +/- 0.11, N = 3 SE +/- 0.18, N = 3 SE +/- 0.21, N = 3 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.17, N = 3 SE +/- 0.19, N = 3 SE +/- 0.10, N = 3 86.94 107.00 103.00 103.00 125.00 113.00 132.00 133.00 156.00 42.04 45.61 71.23 74.31 160.00 75.09
Darktable System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Darktable 2.4.4 System Power Consumption Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 30 60 90 120 150 Min: 71.4 / Avg: 101.98 / Max: 180.7 Min: 77.5 / Avg: 115.43 / Max: 145.8 Min: 48.3 / Avg: 83.05 / Max: 115.5 Min: 159.8 / Avg: 170.75 / Max: 181.7
LuxMark OpenCL Device: GPU - Scene: Luxball HDR OpenBenchmarking.org Score, More Is Better LuxMark 3.1 OpenCL Device: GPU - Scene: Luxball HDR GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 10K 20K 30K 40K 50K SE +/- 46.58, N = 3 SE +/- 1.33, N = 3 SE +/- 14.90, N = 3 SE +/- 42.00, N = 3 SE +/- 8.33, N = 3 SE +/- 31.58, N = 3 SE +/- 107.00, N = 3 SE +/- 25.12, N = 3 SE +/- 155.67, N = 3 SE +/- 17.84, N = 3 SE +/- 74.83, N = 3 SE +/- 65.67, N = 3 SE +/- 583.87, N = 3 SE +/- 103.04, N = 3 SE +/- 124.42, N = 3 12256 17287 16776 13803 21682 21356 29532 29146 42787 15271 17221 31079 32565 46022 28140
cl-mem Benchmark: Read OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Read GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 120 240 360 480 600 SE +/- 0.17, N = 3 SE +/- 0.09, N = 3 SE +/- 0.27, N = 3 SE +/- 0.18, N = 3 SE +/- 0.52, N = 3 SE +/- 0.15, N = 3 SE +/- 1.98, N = 3 SE +/- 1.81, N = 3 SE +/- 0.50, N = 3 SE +/- 0.15, N = 3 SE +/- 0.58, N = 3 SE +/- 0.06, N = 3 SE +/- 0.18, N = 3 SE +/- 0.38, N = 3 SE +/- 0.54, N = 3 153 205 205 229 337 296 392 392 544 162 178 151 159 565 340 1. (CC) gcc options: -O2 -flto -lOpenCL
PlaidML FP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 100 200 300 400 500 SE +/- 0.17, N = 3 SE +/- 0.38, N = 3 SE +/- 0.16, N = 3 SE +/- 0.24, N = 3 SE +/- 0.34, N = 3 SE +/- 0.26, N = 3 SE +/- 0.76, N = 3 SE +/- 0.40, N = 3 SE +/- 1.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.13, N = 3 SE +/- 1.16, N = 3 SE +/- 2.54, N = 3 183 237 237 264 334 282 333 354 458 128 137 195 213 474 215
clpeak OpenCL Test: Global Memory Bandwidth OpenBenchmarking.org GBPS, More Is Better clpeak OpenCL Test: Global Memory Bandwidth GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 110 220 330 440 550 SE +/- 0.95, N = 3 SE +/- 0.02, N = 3 SE +/- 0.22, N = 3 SE +/- 0.05, N = 3 SE +/- 0.68, N = 3 SE +/- 0.19, N = 3 SE +/- 2.69, N = 3 SE +/- 0.37, N = 3 SE +/- 0.48, N = 3 SE +/- 1.46, N = 3 SE +/- 1.82, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 1.70, N = 3 SE +/- 0.34, N = 3 145 196 197 222 329 276 365 368 505 206 217 317 362 525 318 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
clpeak OpenCL Test: Transfer Bandwidth enqueueWriteBuffer OpenBenchmarking.org GBPS, More Is Better clpeak OpenCL Test: Transfer Bandwidth enqueueWriteBuffer GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 10 20 30 40 50 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.22, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.42, N = 3 12.54 12.60 12.55 12.59 12.57 12.60 12.48 12.52 12.59 44.97 44.19 44.97 44.31 12.58 37.97 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL OpenBenchmarking.org Examples Per Second Per Watt, More Is Better PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 0.6998 1.3996 2.0994 2.7992 3.499 1.59 1.77 1.94 1.92 1.82 2.30 2.44 2.51 3.11 0.92 0.88 1.51 1.52 2.86
cl-mem Benchmark: Write OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Write GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 110 220 330 440 550 SE +/- 0.19, N = 3 SE +/- 0.07, N = 3 SE +/- 0.30, N = 3 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 SE +/- 0.95, N = 3 SE +/- 0.59, N = 3 SE +/- 0.73, N = 3 SE +/- 1.92, N = 3 SE +/- 0.33, N = 3 SE +/- 0.10, N = 3 SE +/- 0.32, N = 3 SE +/- 11.23, N = 3 SE +/- 2.45, N = 3 SE +/- 0.27, N = 3 139 192 190 216 336 245 313 323 439 179 185 305 356 489 325 1. (CC) gcc options: -O2 -flto -lOpenCL
cl-mem Benchmark: Copy OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Copy GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 100 200 300 400 500 SE +/- 0.15, N = 3 SE +/- 0.07, N = 3 SE +/- 0.29, N = 3 SE +/- 0.06, N = 3 SE +/- 0.17, N = 3 SE +/- 0.18, N = 3 SE +/- 0.18, N = 3 SE +/- 0.35, N = 3 SE +/- 0.23, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.20, N = 3 SE +/- 0.06, N = 3 SE +/- 0.64, N = 3 SE +/- 0.12, N = 3 138 187 187 209 317 247 330 327 454 184 193 204 222 483 309 1. (CC) gcc options: -O2 -flto -lOpenCL
PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL OpenBenchmarking.org Examples Per Second Per Watt, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 0.2903 0.5806 0.8709 1.1612 1.4515 0.65 0.79 0.89 0.79 0.82 0.90 1.03 1.08 1.28 0.40 0.37 0.64 0.64 1.29
PlaidML FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 130 260 390 520 650 SE +/- 0.33, N = 3 SE +/- 0.21, N = 3 SE +/- 0.19, N = 3 SE +/- 0.45, N = 3 SE +/- 0.59, N = 3 SE +/- 0.31, N = 3 SE +/- 0.60, N = 3 SE +/- 1.09, N = 3 SE +/- 2.13, N = 3 SE +/- 0.23, N = 3 SE +/- 0.63, N = 3 SE +/- 0.20, N = 3 SE +/- 1.42, N = 3 SE +/- 0.76, N = 3 SE +/- 0.46, N = 3 180 228 224 259 330 347 382 457 605 193 218 263 279 610 270
PlaidML FP16: No - Mode: Training - Network: Mobilenet - Device: OpenCL OpenBenchmarking.org Examples Per Second Per Watt, More Is Better PlaidML FP16: No - Mode: Training - Network: Mobilenet - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 0.2543 0.5086 0.7629 1.0172 1.2715 0.87 0.85 1.03 0.67 1.03 1.02 1.09 1.01 1.13 0.35 0.34 0.57 0.48 0.98
PlaidML FP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 50 100 150 200 250 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.18, N = 3 SE +/- 0.08, N = 3 SE +/- 0.28, N = 3 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 SE +/- 0.13, N = 3 SE +/- 0.38, N = 3 SE +/- 0.11, N = 3 SE +/- 0.06, N = 3 SE +/- 0.00, N = 3 SE +/- 0.40, N = 3 SE +/- 0.53, N = 3 SE +/- 0.24, N = 3 86.11 116.00 118.00 133.00 167.00 133.00 156.00 172.00 225.00 69.05 75.41 106.65 119.06 229.00 138.74
PlaidML FP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCL OpenBenchmarking.org Examples Per Second Per Watt, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 0.6638 1.3276 1.9914 2.6552 3.319 1.49 1.76 2.08 1.62 1.78 1.96 2.51 2.39 2.95 0.91 0.89 1.38 1.24 2.92
PlaidML FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL OpenBenchmarking.org Examples Per Second Per Watt, More Is Better PlaidML FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 3 6 9 12 15 7.72 7.12 8.06 5.42 7.02 9.00 8.70 10.67 8.45 3.62 3.29 5.82 7.47 6.67
PlaidML FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 300 600 900 1200 1500 SE +/- 3.04, N = 3 SE +/- 1.02, N = 3 SE +/- 0.31, N = 3 SE +/- 0.61, N = 3 SE +/- 4.51, N = 3 SE +/- 1.86, N = 3 SE +/- 1.43, N = 3 SE +/- 0.31, N = 3 SE +/- 1.39, N = 3 SE +/- 0.26, N = 3 SE +/- 0.24, N = 3 SE +/- 9.70, N = 3 SE +/- 7.40, N = 3 SE +/- 3.01, N = 3 SE +/- 2.78, N = 3 592 764 755 801 883 863 1008 1045 1291 414 453 720 835 1336 781
JuliaGPU OpenCL Device: GPU OpenBenchmarking.org Samples/sec Per Watt, More Is Better JuliaGPU 1.2pts1 OpenCL Device: GPU GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 1.1M 2.2M 3.3M 4.4M 5.5M 1629857 1867592 1980229 1882924 1666119 2236054 2279065 2070002 2042921 2141832 2124046 2159676 5140282 2042478
LuxMark GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better LuxMark 3.1 GPU Temperature Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 16 32 48 64 80 Min: 43 / Avg: 58.4 / Max: 61 Min: 54 / Avg: 67.07 / Max: 70 Min: 41 / Avg: 48.91 / Max: 51 Min: 49 / Avg: 64.55 / Max: 67 Min: 56 / Avg: 72.55 / Max: 75 Min: 49 / Avg: 63.65 / Max: 67 Min: 47 / Avg: 67.5 / Max: 72 Min: 48 / Avg: 75.04 / Max: 79 Min: 49 / Avg: 69.88 / Max: 74 Min: 29 / Avg: 55.16 / Max: 60 Min: 44 / Avg: 65.27 / Max: 73 Min: 44 / Avg: 69.66 / Max: 74 Min: 43 / Avg: 79.26 / Max: 86 Min: 44 / Avg: 71.96 / Max: 78
PlaidML FP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCL OpenBenchmarking.org Examples Per Second Per Watt, More Is Better PlaidML FP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 0.2723 0.5446 0.8169 1.0892 1.3615 0.61 0.74 0.83 0.79 0.81 0.84 0.98 1.03 1.21 0.44 0.42 0.62 0.69 1.19
SHOC Scalable HeterOgeneous Computing System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 System Power Consumption Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 30 60 90 120 150 Min: 80.6 / Avg: 100.5 / Max: 136 Min: 47.7 / Avg: 48.75 / Max: 49.8 Min: 50.5 / Avg: 65.45 / Max: 80.4
PlaidML FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL OpenBenchmarking.org Examples Per Second Per Watt, More Is Better PlaidML FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 0.7718 1.5436 2.3154 3.0872 3.859 1.28 1.46 1.76 1.47 1.70 2.76 3.02 3.37 3.05 1.41 1.22 1.81 1.32 3.43
PlaidML FP16: Yes - Mode: Inference - Network: Inception V3 - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: Inception V3 - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 50 100 150 200 250 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 SE +/- 0.30, N = 3 SE +/- 0.07, N = 3 SE +/- 0.58, N = 3 SE +/- 0.44, N = 3 SE +/- 0.18, N = 3 SE +/- 0.40, N = 3 SE +/- 0.48, N = 3 SE +/- 0.04, N = 3 SE +/- 0.11, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 1.30, N = 3 SE +/- 0.34, N = 3 88.85 117.00 120.00 132.00 167.00 134.00 157.00 168.00 211.00 76.59 82.71 109.03 120.03 215.00 116.49
LeelaChessZero GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better LeelaChessZero 0.20.1 GPU Temperature Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 14 28 42 56 70 Min: 38 / Avg: 51.69 / Max: 59 Min: 35 / Avg: 46.2 / Max: 55 Min: 46 / Avg: 50.13 / Max: 53 Min: 32 / Avg: 40.8 / Max: 58 Min: 41 / Avg: 51.43 / Max: 61 Min: 39 / Avg: 50.33 / Max: 58 Min: 33 / Avg: 44.86 / Max: 52 Min: 57 / Avg: 66.29 / Max: 73 Min: 50 / Avg: 55.6 / Max: 60 Min: 27 / Avg: 45.13 / Max: 61 Min: 37 / Avg: 50.65 / Max: 67 Min: 28 / Avg: 41.93 / Max: 60 Min: 46 / Avg: 64.5 / Max: 72 Min: 34 / Avg: 36.91 / Max: 47
PlaidML FP16: Yes - Mode: Inference - Network: Inception V3 - Device: OpenCL OpenBenchmarking.org Examples Per Second Per Watt, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: Inception V3 - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 0.288 0.576 0.864 1.152 1.44 0.67 0.76 0.90 0.78 0.82 0.92 1.07 1.08 1.12 0.52 0.51 0.74 0.66 1.28
clpeak OpenCL Test: Single-Precision Float OpenBenchmarking.org GFLOPS Per Watt, More Is Better clpeak OpenCL Test: Single-Precision Float RX 580 RX 590 RX Vega 56 RX Vega 64 30 60 90 120 150 61.58 66.87 135.00 154.00
cl-mem Benchmark: Write OpenBenchmarking.org GB/s Per Watt, More Is Better cl-mem 2017-01-13 Benchmark: Write GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 0.6368 1.2736 1.9104 2.5472 3.184 1.42 1.40 1.52 1.53 1.54 1.87 2.25 2.50 2.83 1.21 1.15 1.33 1.86 2.57
cl-mem Benchmark: Copy OpenBenchmarking.org GB/s Per Watt, More Is Better cl-mem 2017-01-13 Benchmark: Copy GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2080 RX 580 RX 590 RX Vega 56 RX Vega 64 0.5198 1.0396 1.5594 2.0792 2.599 1.28 1.41 1.65 1.76 2.27 2.22 2.31 1.30 0.97 1.00 1.12
clpeak System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better clpeak System Power Consumption Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 20 40 60 80 100 Min: 69.7 / Avg: 98.35 / Max: 99.6 Min: 78.8 / Avg: 105.05 / Max: 110.8 Min: 47.4 / Avg: 76.29 / Max: 77.6 Min: 59.1 / Avg: 78.52 / Max: 79.5
clpeak System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better clpeak System Power Consumption Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 20 40 60 80 100 Min: 70.1 / Avg: 99 / Max: 100.8 Min: 78.6 / Avg: 105.13 / Max: 109.6 Min: 48.2 / Avg: 76.77 / Max: 79.1 Min: 51.4 / Avg: 79.27 / Max: 81.1
PlaidML GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better PlaidML GPU Temperature Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 14 28 42 56 70 Min: 43 / Avg: 51.9 / Max: 59 Min: 49 / Avg: 56.06 / Max: 63 Min: 41 / Avg: 45.18 / Max: 50 Min: 52 / Avg: 58.85 / Max: 65 Min: 53 / Avg: 60.07 / Max: 67 Min: 43 / Avg: 50.75 / Max: 59 Min: 42 / Avg: 48.87 / Max: 56 Min: 53 / Avg: 59.79 / Max: 68 Min: 46 / Avg: 51 / Max: 57 Min: 31 / Avg: 42.94 / Max: 51 Min: 42 / Avg: 53.46 / Max: 61 Min: 52 / Avg: 59.68 / Max: 69 Min: 55 / Avg: 63.35 / Max: 70 Min: 42 / Avg: 47.33 / Max: 54
clpeak System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better clpeak System Power Consumption Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 20 40 60 80 100 Min: 69.5 / Avg: 98.49 / Max: 101 Min: 78.6 / Avg: 105.05 / Max: 110.7 Min: 73.9 / Avg: 77.01 / Max: 77.7 Min: 49.9 / Avg: 78.27 / Max: 81
PlaidML GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better PlaidML GPU Temperature Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 13 26 39 52 65 Min: 41 / Avg: 47.52 / Max: 54 Min: 51 / Avg: 56.59 / Max: 60 Min: 38 / Avg: 42.62 / Max: 46 Min: 60 / Avg: 61.64 / Max: 63 Min: 44 / Avg: 53.18 / Max: 61 Min: 43 / Avg: 48.84 / Max: 55 Min: 42 / Avg: 47.65 / Max: 53 Min: 52 / Avg: 58.56 / Max: 66 Min: 44 / Avg: 48.59 / Max: 53 Min: 30 / Avg: 37.96 / Max: 46 Min: 42 / Avg: 49 / Max: 56 Min: 40 / Avg: 49.89 / Max: 64 Min: 45 / Avg: 55.21 / Max: 65 Min: 43 / Avg: 48.07 / Max: 53
PlaidML FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL OpenBenchmarking.org Examples Per Second Per Watt, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 3 6 9 12 15 5.12 7.22 6.57 7.34 5.19 6.41 8.87 6.82 10.28 5.14 4.74 6.23 8.48 8.82
SHOC Scalable HeterOgeneous Computing GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 GPU Temperature Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 13 26 39 52 65 Min: 46 / Avg: 48.5 / Max: 49 Min: 57 / Avg: 57.33 / Max: 58 Min: 42 / Avg: 42.6 / Max: 43 Min: 54 / Avg: 55.54 / Max: 57 Min: 56 / Avg: 59.67 / Max: 61 Min: 48 / Avg: 54.5 / Max: 56 Min: 52 / Avg: 54.2 / Max: 56 Min: 57 / Avg: 63.86 / Max: 67 Min: 59 / Avg: 62 / Max: 65 Min: 31 / Avg: 41.38 / Max: 45 Min: 35 / Avg: 43.11 / Max: 47 Min: 38 / Avg: 46.29 / Max: 52 Min: 49 / Avg: 59.89 / Max: 65 Min: 55 / Avg: 63.4 / Max: 66
PlaidML GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better PlaidML GPU Temperature Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 14 28 42 56 70 Min: 45 / Avg: 52 / Max: 57 Min: 48 / Avg: 54.81 / Max: 60 Min: 43 / Avg: 45.94 / Max: 49 Min: 51 / Avg: 57.64 / Max: 63 Min: 55 / Avg: 59.71 / Max: 66 Min: 43 / Avg: 49.73 / Max: 56 Min: 42 / Avg: 48.08 / Max: 55 Min: 56 / Avg: 61.08 / Max: 66 Min: 49 / Avg: 52.45 / Max: 57 Min: 33 / Avg: 42.3 / Max: 50 Min: 40 / Avg: 50.41 / Max: 60 Min: 39 / Avg: 50.92 / Max: 65 Min: 47 / Avg: 59.05 / Max: 70 Min: 39 / Avg: 44.46 / Max: 52
SHOC Scalable HeterOgeneous Computing System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 System Power Consumption Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 20 40 60 80 100 Min: 81.9 / Avg: 92.65 / Max: 103.4 Min: 49 / Avg: 65 / Max: 81 Min: 51.7 / Avg: 64.95 / Max: 78.2
PlaidML GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better PlaidML GPU Temperature Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 13 26 39 52 65 Min: 44 / Avg: 52.44 / Max: 59 Min: 58 / Avg: 61.79 / Max: 65 Min: 43 / Avg: 47.13 / Max: 50 Min: 58 / Avg: 63.21 / Max: 68 Min: 60 / Avg: 64.36 / Max: 69 Min: 40 / Avg: 48.69 / Max: 56 Min: 49 / Avg: 54.67 / Max: 60 Min: 57 / Avg: 63.18 / Max: 68 Min: 52 / Avg: 54.78 / Max: 59 Min: 33 / Avg: 45.16 / Max: 54 Min: 44 / Avg: 55.88 / Max: 64 Min: 50 / Avg: 58.4 / Max: 68 Min: 50 / Avg: 59.52 / Max: 69 Min: 51 / Avg: 55.27 / Max: 60
clpeak OpenCL Test: Integer Compute INT OpenBenchmarking.org GIOPS Per Watt, More Is Better clpeak OpenCL Test: Integer Compute INT RX 580 RX 590 RX Vega 56 RX Vega 64 6 12 18 24 30 11.44 12.09 22.43 23.68
clpeak GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better clpeak GPU Temperature Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 13 26 39 52 65 Min: 32 / Avg: 39.04 / Max: 50 Min: 36 / Avg: 41.8 / Max: 54 Min: 35 / Avg: 42.72 / Max: 57 Min: 36 / Avg: 47.48 / Max: 66
clpeak OpenCL Test: Global Memory Bandwidth OpenBenchmarking.org GBPS Per Watt, More Is Better clpeak OpenCL Test: Global Memory Bandwidth RX 580 RX 590 RX Vega 56 RX Vega 64 0.9293 1.8586 2.7879 3.7172 4.6465 2.08 2.02 3.89 4.13
PlaidML GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better PlaidML GPU Temperature Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 14 28 42 56 70 Min: 52 / Avg: 58.35 / Max: 62 Min: 56 / Avg: 62.15 / Max: 66 Min: 43 / Avg: 47.69 / Max: 50 Min: 59 / Avg: 64.36 / Max: 68 Min: 61 / Avg: 65.7 / Max: 70 Min: 46 / Avg: 55.73 / Max: 61 Min: 47 / Avg: 54.45 / Max: 60 Min: 56 / Avg: 63.5 / Max: 70 Min: 49 / Avg: 54.38 / Max: 59 Min: 35 / Avg: 47.27 / Max: 53 Min: 43 / Avg: 54.21 / Max: 59 Min: 51 / Avg: 59.53 / Max: 66 Min: 50 / Avg: 60.38 / Max: 68 Min: 50 / Avg: 55.25 / Max: 61
JuliaGPU OpenCL Device: GPU OpenBenchmarking.org Samples/sec, More Is Better JuliaGPU 1.2pts1 OpenCL Device: GPU GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 80M 160M 240M 320M 400M SE +/- 513835.53, N = 3 SE +/- 621591.58, N = 3 SE +/- 297139.02, N = 3 SE +/- 121634.53, N = 3 SE +/- 720633.38, N = 3 SE +/- 815068.63, N = 3 SE +/- 333271.02, N = 3 SE +/- 1536969.33, N = 3 SE +/- 1417039.09, N = 3 SE +/- 570650.48, N = 3 SE +/- 366170.21, N = 3 SE +/- 834530.58, N = 3 SE +/- 419189.48, N = 3 SE +/- 908628.37, N = 3 SE +/- 7293118.99, N = 12 183782626 218172062 221548016 239131324 265162875 251611989 265682046 278829238 300922241 283078851 302623440 346484064 366159438 303665447 312792565 1. (CC) gcc options: -O3 -march=native -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL -lm
PlaidML FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 200 400 600 800 1000 SE +/- 0.87, N = 3 SE +/- 4.06, N = 3 SE +/- 3.15, N = 3 SE +/- 5.02, N = 3 SE +/- 3.70, N = 3 SE +/- 1.27, N = 3 SE +/- 1.07, N = 3 SE +/- 1.63, N = 3 SE +/- 2.70, N = 3 SE +/- 1.03, N = 3 SE +/- 1.00, N = 3 SE +/- 6.73, N = 3 SE +/- 9.53, N = 3 SE +/- 3.45, N = 3 SE +/- 5.20, N = 3 552 664 645 686 774 779 830 893 971 563 599 575 587 977 498
PlaidML GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better PlaidML GPU Temperature Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 13 26 39 52 65 Min: 47 / Avg: 50.92 / Max: 55 Min: 54 / Avg: 57.18 / Max: 61 Min: 43 / Avg: 45.8 / Max: 48 Min: 58 / Avg: 60 / Max: 63 Min: 59 / Avg: 61.1 / Max: 64 Min: 46 / Avg: 50.9 / Max: 56 Min: 46 / Avg: 48.78 / Max: 53 Min: 58 / Avg: 61.6 / Max: 65 Min: 49 / Avg: 51.2 / Max: 55 Min: 35 / Avg: 41.89 / Max: 48 Min: 44 / Avg: 51.33 / Max: 58 Min: 52 / Avg: 59.73 / Max: 67 Min: 52 / Avg: 59.71 / Max: 67 Min: 44 / Avg: 46.33 / Max: 52
PlaidML FP16: No - Mode: Training - Network: IMDB LSTM - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Training - Network: IMDB LSTM - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 50 100 150 200 250 SE +/- 0.17, N = 3 SE +/- 0.50, N = 3 SE +/- 0.03, N = 3 SE +/- 0.60, N = 3 SE +/- 0.49, N = 3 SE +/- 0.38, N = 3 SE +/- 0.82, N = 3 SE +/- 0.27, N = 3 SE +/- 0.72, N = 3 SE +/- 0.25, N = 3 SE +/- 0.19, N = 3 SE +/- 0.24, N = 3 SE +/- 0.19, N = 3 SE +/- 0.96, N = 3 SE +/- 0.57, N = 3 134 156 153 167 187 188 198 216 246 130 144 178 184 244 159
Darktable System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Darktable 2.4.4 System Power Consumption Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 20 40 60 80 100 Min: 77.8 / Avg: 77.9 / Max: 78 Min: 48 / Avg: 51.55 / Max: 55.1 Min: 50.3 / Avg: 70.55 / Max: 90.8
PlaidML GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better PlaidML GPU Temperature Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 13 26 39 52 65 Min: 44 / Avg: 49.23 / Max: 54 Min: 51 / Avg: 55.42 / Max: 59 Min: 39 / Avg: 42.75 / Max: 45 Min: 53 / Avg: 57.58 / Max: 61 Min: 59 / Avg: 61.75 / Max: 63 Min: 40 / Avg: 45 / Max: 50 Min: 41 / Avg: 45.18 / Max: 49 Min: 50 / Avg: 54.64 / Max: 59 Min: 52 / Avg: 53.5 / Max: 56 Min: 34 / Avg: 42.71 / Max: 48 Min: 46 / Avg: 53.31 / Max: 59 Min: 49 / Avg: 56.67 / Max: 63 Min: 51 / Avg: 58.38 / Max: 64 Min: 52 / Avg: 53.8 / Max: 56
clpeak OpenCL Test: Double-Precision Double OpenBenchmarking.org GFLOPS Per Watt, More Is Better clpeak OpenCL Test: Double-Precision Double RX 580 RX 590 RX Vega 56 RX Vega 64 2 4 6 8 10 3.35 3.50 6.22 6.24
PlaidML GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better PlaidML GPU Temperature Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 13 26 39 52 65 Min: 41 / Avg: 45.25 / Max: 47 Min: 59 / Avg: 60.33 / Max: 61 Min: 48 / Avg: 48 / Max: 48 Min: 62 / Avg: 62 / Max: 62 Min: 63 / Avg: 64 / Max: 65 Min: 39 / Avg: 44.25 / Max: 48 Min: 55 / Avg: 55 / Max: 55 Min: 66 / Avg: 66 / Max: 66 Min: 54 / Avg: 55.67 / Max: 58 Min: 36 / Avg: 40.83 / Max: 46 Min: 47 / Avg: 51.5 / Max: 56 Min: 51 / Avg: 52.8 / Max: 57 Min: 54 / Avg: 55.6 / Max: 59 Min: 55 / Avg: 55 / Max: 55
PlaidML FP16: No - Mode: Training - Network: IMDB LSTM - Device: OpenCL OpenBenchmarking.org Examples Per Second Per Watt, More Is Better PlaidML FP16: No - Mode: Training - Network: IMDB LSTM - Device: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 0.3645 0.729 1.0935 1.458 1.8225 1.08 1.14 1.24 1.14 1.14 1.62 1.56 1.56 1.54 0.89 0.95 1.07 1.11 1.60
PlaidML GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better PlaidML GPU Temperature Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 13 26 39 52 65 Min: 52 / Avg: 56.5 / Max: 59 Min: 55 / Avg: 60 / Max: 64 Min: 43 / Avg: 45.83 / Max: 48 Min: 58 / Avg: 62 / Max: 65 Min: 59 / Avg: 63 / Max: 66 Min: 46 / Avg: 51.8 / Max: 55 Min: 51 / Avg: 53.25 / Max: 55 Min: 58 / Avg: 61.5 / Max: 64 Min: 50 / Avg: 51.33 / Max: 53 Min: 37 / Avg: 45.13 / Max: 49 Min: 47 / Avg: 53.5 / Max: 58 Min: 52 / Avg: 59.67 / Max: 64 Min: 52 / Avg: 59.71 / Max: 65 Min: 51 / Avg: 54 / Max: 58
PlaidML GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better PlaidML GPU Temperature Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 13 26 39 52 65 Min: 50 / Avg: 54.8 / Max: 58 Min: 56 / Avg: 59.9 / Max: 64 Min: 44 / Avg: 46.22 / Max: 48 Min: 60 / Avg: 62.5 / Max: 65 Min: 61 / Avg: 63.11 / Max: 66 Min: 46 / Avg: 50.11 / Max: 56 Min: 50 / Avg: 53.44 / Max: 58 Min: 59 / Avg: 62.38 / Max: 66 Min: 51 / Avg: 53.29 / Max: 57 Min: 37 / Avg: 44.64 / Max: 50 Min: 47 / Avg: 54.23 / Max: 60 Min: 49 / Avg: 55.36 / Max: 63 Min: 48 / Avg: 54.5 / Max: 60 Min: 52 / Avg: 54.86 / Max: 58
LuxMark OpenCL Device: GPU - Scene: Luxball HDR OpenBenchmarking.org Score Per Watt, More Is Better LuxMark 3.1 OpenCL Device: GPU - Scene: Luxball HDR GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 30 60 90 120 150 85.53 98.48 114.16 79.42 89.34 110.80 131.09 123.99 133.42 80.53 78.90 120.58 98.89 137.54
Darktable Test: Server Rack - Acceleration: OpenCL OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.4.4 Test: Server Rack - Acceleration: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 0.0383 0.0766 0.1149 0.1532 0.1915 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.13 0.12 0.13 0.13 0.12 0.11 0.10 0.11 0.10 0.17 0.17 0.17 0.17 0.10
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Triad OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: Triad GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.21, N = 3 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 11.93 12.19 12.19 12.30 12.51 12.43 12.57 12.57 12.68 9.10 9.36 7.55 7.54 12.68 12.44 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
clpeak GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better clpeak GPU Temperature Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 11 22 33 44 55 Min: 34 / Avg: 37.71 / Max: 50 Min: 38 / Avg: 41.36 / Max: 56 Min: 40 / Avg: 43.74 / Max: 49 Min: 42 / Avg: 46.65 / Max: 57
PlaidML GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better PlaidML GPU Temperature Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 12 24 36 48 60 Min: 49 / Avg: 50 / Max: 51 Min: 47 / Avg: 49.5 / Max: 51 Min: 46 / Avg: 47 / Max: 48 Min: 47 / Avg: 49.75 / Max: 51 Min: 56 / Avg: 56.67 / Max: 57 Min: 46 / Avg: 47.75 / Max: 50 Min: 45 / Avg: 46.75 / Max: 48 Min: 61 / Avg: 61.67 / Max: 62 Min: 52 / Avg: 52.5 / Max: 53 Min: 38 / Avg: 42 / Max: 47 Min: 45 / Avg: 48.88 / Max: 53 Min: 40 / Avg: 42.75 / Max: 46 Min: 49 / Avg: 50.83 / Max: 54 Min: 41 / Avg: 41.5 / Max: 42
JuliaGPU GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better JuliaGPU 1.2pts1 GPU Temperature Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 11 22 33 44 55 Min: 46 / Avg: 47.2 / Max: 49 Min: 53 / Avg: 54.4 / Max: 56 Min: 38 / Avg: 40.6 / Max: 42 Min: 51 / Avg: 52.5 / Max: 54 Min: 52 / Avg: 54.6 / Max: 57 Min: 43 / Avg: 47.5 / Max: 50 Min: 46 / Avg: 47 / Max: 48 Min: 53 / Avg: 54.5 / Max: 56 Min: 48 / Avg: 51.25 / Max: 53 Min: 36 / Avg: 42.75 / Max: 46 Min: 45 / Avg: 48 / Max: 49 Min: 40 / Avg: 42.67 / Max: 45 Min: 50 / Avg: 52.33 / Max: 55 Min: 49 / Avg: 52.5 / Max: 54
clpeak GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better clpeak GPU Temperature Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 10 20 30 40 50 Min: 31 / Avg: 33.28 / Max: 41 Min: 37 / Avg: 39.72 / Max: 48 Min: 39 / Avg: 41.36 / Max: 48 Min: 41 / Avg: 43.79 / Max: 49
Darktable GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Darktable 2.4.4 GPU Temperature Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 10 20 30 40 50 Min: 33 / Avg: 35 / Max: 39 Min: 39 / Avg: 41.7 / Max: 45 Min: 42 / Avg: 43.78 / Max: 49 Min: 44 / Avg: 46.5 / Max: 52
SHOC Scalable HeterOgeneous Computing GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 GPU Temperature Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 11 22 33 44 55 Min: 35 / Avg: 42 / Max: 49 Min: 39 / Avg: 44.67 / Max: 55 Min: 38 / Avg: 39.5 / Max: 41
cl-mem GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better cl-mem 2017-01-13 GPU Temperature Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 12 24 36 48 60 Min: 48 / Avg: 51.14 / Max: 52 Min: 55 / Avg: 57.17 / Max: 58 Min: 43 / Avg: 44 / Max: 45 Min: 56 / Avg: 57 / Max: 58 Min: 60 / Avg: 60.67 / Max: 61 Min: 49 / Avg: 54 / Max: 56 Min: 50 / Avg: 53.67 / Max: 56 Min: 62 / Avg: 62 / Max: 62 Min: 56 / Avg: 58.33 / Max: 61 Min: 41 / Avg: 46.8 / Max: 49 Min: 53 / Avg: 55.5 / Max: 57 Min: 48 / Avg: 55.2 / Max: 60 Min: 58 / Avg: 59.8 / Max: 62 Min: 60 / Avg: 61 / Max: 62
cl-mem GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better cl-mem 2017-01-13 GPU Temperature Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 13 26 39 52 65 Min: 53 / Avg: 53 / Max: 53 Min: 60 / Avg: 60.6 / Max: 61 Min: 43 / Avg: 44.83 / Max: 46 Min: 60 / Avg: 60.2 / Max: 61 Min: 64 / Avg: 64 / Max: 64 Min: 55 / Avg: 56 / Max: 57 Min: 54 / Avg: 55.33 / Max: 56 Min: 61 / Avg: 63.75 / Max: 65 Min: 61 / Avg: 62 / Max: 63 Min: 49 / Avg: 49.6 / Max: 50 Min: 56 / Avg: 59.5 / Max: 62 Min: 51 / Avg: 58.6 / Max: 62 Min: 59 / Avg: 62.4 / Max: 65 Min: 59 / Avg: 63 / Max: 65
clpeak GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better clpeak GPU Temperature Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 10 20 30 40 50 Min: 32 / Avg: 33.27 / Max: 37 Min: 35 / Avg: 37.05 / Max: 40 Min: 35 / Avg: 38.05 / Max: 43 Min: 36 / Avg: 40.64 / Max: 48
clpeak GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better clpeak GPU Temperature Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 10 20 30 40 50 Min: 32 / Avg: 32.71 / Max: 45 Min: 36 / Avg: 37.43 / Max: 48 Min: 36 / Avg: 37.93 / Max: 40 Min: 38 / Avg: 40.13 / Max: 43
clpeak OpenCL Test: Transfer Bandwidth enqueueReadBuffer OpenBenchmarking.org GBPS, More Is Better clpeak OpenCL Test: Transfer Bandwidth enqueueReadBuffer GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 4 8 12 16 20 SE +/- 0.09, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.09, N = 3 SE +/- 0.01, N = 3 SE +/- 0.33, N = 3 SE +/- 0.08, N = 3 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.13, N = 3 11.15 11.33 11.15 11.34 11.29 11.29 11.25 11.13 11.29 15.84 15.92 16.63 16.22 11.16 15.79 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
cl-mem GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better cl-mem 2017-01-13 GPU Temperature Monitor GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 14 28 42 56 70 Min: 54 / Avg: 55.88 / Max: 57 Min: 64 / Avg: 64.8 / Max: 66 Min: 47 / Avg: 47 / Max: 47 Min: 63 / Avg: 64.17 / Max: 65 Min: 68 / Avg: 68.33 / Max: 69 Min: 56 / Avg: 58.5 / Max: 60 Min: 60 / Avg: 62 / Max: 63 Min: 67 / Avg: 68.67 / Max: 70 Min: 66 / Avg: 67 / Max: 68 Min: 47 / Avg: 52 / Max: 53 Min: 59 / Avg: 64 / Max: 66 Min: 64 / Avg: 66 / Max: 68 Min: 61 / Avg: 66.4 / Max: 69 Min: 66 / Avg: 68.33 / Max: 70
Darktable Test: Masskrug - Acceleration: OpenCL OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.4.4 Test: Masskrug - Acceleration: OpenCL GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX 1.2263 2.4526 3.6789 4.9052 6.1315 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 4.17 3.92 4.01 3.97 3.87 3.82 3.68 3.78 3.69 5.30 5.45 5.28 5.32 3.69
clpeak OpenCL Test: Transfer Bandwidth enqueueReadBuffer OpenBenchmarking.org GBPS Per Watt, More Is Better clpeak OpenCL Test: Transfer Bandwidth enqueueReadBuffer RX 580 RX 590 RX Vega 56 RX Vega 64 0.0495 0.099 0.1485 0.198 0.2475 0.16 0.15 0.22 0.21
Darktable GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Darktable 2.4.4 GPU Temperature Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 9 18 27 36 45 Min: 30 / Avg: 30.8 / Max: 31 Min: 38 / Avg: 38.25 / Max: 39 Min: 41 / Avg: 41.4 / Max: 42 Min: 42 / Avg: 42.67 / Max: 43
clpeak OpenCL Test: Transfer Bandwidth enqueueWriteBuffer OpenBenchmarking.org GBPS Per Watt, More Is Better clpeak OpenCL Test: Transfer Bandwidth enqueueWriteBuffer RX 580 RX 590 RX Vega 56 RX Vega 64 0.1328 0.2656 0.3984 0.5312 0.664 0.45 0.42 0.59 0.56
Darktable GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Darktable 2.4.4 GPU Temperature Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 9 18 27 36 45 Min: 30 / Avg: 30 / Max: 30 Min: 37 / Avg: 37.67 / Max: 38 Min: 40 / Avg: 40.25 / Max: 41 Min: 42 / Avg: 42 / Max: 42
Darktable GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Darktable 2.4.4 GPU Temperature Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 9 18 27 36 45
SHOC Scalable HeterOgeneous Computing GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 GPU Temperature Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 10 20 30 40 50 Min: 37 / Avg: 37 / Max: 37 Min: 40 / Avg: 41 / Max: 42 Min: 42 / Avg: 42.5 / Max: 43 Min: 49 / Avg: 49.5 / Max: 50
clpeak GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better clpeak GPU Temperature Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 8 16 24 32 40 Min: 31 / Avg: 31.03 / Max: 32 Min: 35 / Avg: 35.11 / Max: 38 Min: 32 / Avg: 32.61 / Max: 34 Min: 32 / Avg: 32.11 / Max: 33
SHOC Scalable HeterOgeneous Computing GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 GPU Temperature Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 9 18 27 36 45 Min: 39 / Avg: 40.5 / Max: 42 Min: 39 / Avg: 39.5 / Max: 40
clpeak GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better clpeak GPU Temperature Monitor RX 580 RX 590 RX Vega 56 RX Vega 64 8 16 24 32 40 Min: 31 / Avg: 31.18 / Max: 32 Min: 35 / Avg: 35.21 / Max: 36 Min: 33 / Avg: 33.73 / Max: 35 Min: 32 / Avg: 33.85 / Max: 36
Darktable Test: Server Rack - Acceleration: OpenCL OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Server Rack - Acceleration: OpenCL amdocl 0.0203 0.0406 0.0609 0.0812 0.1015 SE +/- 0.00, N = 3 0.09
Darktable Test: Server Room - Acceleration: OpenCL OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Server Room - Acceleration: OpenCL amdocl 0.1688 0.3376 0.5064 0.6752 0.844 SE +/- 0.01, N = 3 0.75
Darktable Test: Masskrug - Acceleration: OpenCL OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Masskrug - Acceleration: OpenCL amdocl 1.0823 2.1646 3.2469 4.3292 5.4115 SE +/- 0.06, N = 3 4.81
Darktable Test: Boat - Acceleration: OpenCL OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Boat - Acceleration: OpenCL amdocl 0.612 1.224 1.836 2.448 3.06 SE +/- 0.01, N = 3 2.72
System Power Consumption Monitor Phoronix Test Suite System Monitoring OpenBenchmarking.org Watts System Power Consumption Monitor Phoronix Test Suite System Monitoring RX 580 RX 590 RX Vega 56 RX Vega 64 50 100 150 200 250 Min: 69 / Avg: 125.65 / Max: 229.5 Min: 75 / Avg: 138.2 / Max: 253.3 Min: 47.1 / Avg: 125.63 / Max: 271.3 Min: 49.7 / Avg: 129.09 / Max: 305.4
GPU Temperature Monitor Phoronix Test Suite System Monitoring OpenBenchmarking.org Celsius GPU Temperature Monitor Phoronix Test Suite System Monitoring RX 580 RX 590 RX Vega 56 RX Vega 64 14 28 42 56 70 Min: 26 / Avg: 39.71 / Max: 61 Min: 35 / Avg: 46.18 / Max: 73 Min: 28 / Avg: 47.45 / Max: 74 Min: 45 / Avg: 52.93 / Max: 65
System Power Consumption Monitor Phoronix Test Suite System Monitoring OpenBenchmarking.org Watts System Power Consumption Monitor Phoronix Test Suite System Monitoring GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti TITAN RTX 70 140 210 280 350 Min: 42.3 / Avg: 142.19 / Max: 280.5 Min: 47.2 / Avg: 123.43 / Max: 255.8 Min: 40.2 / Avg: 143.79 / Max: 318.2 Min: 47.2 / Avg: 198.85 / Max: 370.3 Min: 42.5 / Avg: 144.37 / Max: 300.1 Min: 43.9 / Avg: 160.13 / Max: 317.6 Min: 46 / Avg: 176.62 / Max: 334.5 Min: 47.2 / Avg: 220.83 / Max: 367.7 Min: 49.4 / Avg: 228.34 / Max: 363.1
GPU Temperature Monitor Phoronix Test Suite System Monitoring OpenBenchmarking.org Celsius GPU Temperature Monitor Phoronix Test Suite System Monitoring GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti TITAN RTX 16 32 48 64 80 Min: 32 / Avg: 61.66 / Max: 76 Min: 38 / Avg: 45.88 / Max: 53 Min: 31 / Avg: 60.14 / Max: 74 Min: 39 / Avg: 66.36 / Max: 82 Min: 37 / Avg: 55.81 / Max: 70 Min: 32 / Avg: 56.83 / Max: 74 Min: 48 / Avg: 67.06 / Max: 83 Min: 43 / Avg: 61.88 / Max: 77 Min: 33 / Avg: 62.56 / Max: 79
clpeak OpenCL Test: Integer Compute INT OpenBenchmarking.org GIOPS, More Is Better clpeak OpenCL Test: Integer Compute INT GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 3K 6K 9K 12K 15K SE +/- 38.63, N = 3 SE +/- 21.00, N = 3 SE +/- 6.17, N = 3 SE +/- 25.25, N = 3 SE +/- 76.28, N = 3 SE +/- 444.77, N = 3 SE +/- 498.12, N = 3 SE +/- 679.58, N = 3 SE +/- 517.75, N = 3 SE +/- 0.02, N = 3 SE +/- 6.53, N = 3 SE +/- 1.32, N = 3 SE +/- 3.01, N = 3 SE +/- 1004.15, N = 3 SE +/- 5.46, N = 3 1252 1681 2068 2398 3263 6705 7780 9952 14906 1252 1416 1997 2479 14848 1961 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
clpeak OpenCL Test: Single-Precision Float OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Single-Precision Float GTX 1060 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2060 RTX 2070 RTX 2080 RTX 2080 Ti RX 580 RX 590 RX Vega 56 RX Vega 64 TITAN RTX amdocl 4K 8K 12K 16K 20K SE +/- 3.56, N = 3 SE +/- 393.27, N = 3 SE +/- 14.43, N = 3 SE +/- 396.02, N = 3 SE +/- 782.31, N = 3 SE +/- 657.16, N = 3 SE +/- 495.99, N = 3 SE +/- 732.21, N = 3 SE +/- 1065.18, N = 3 SE +/- 1.21, N = 3 SE +/- 15.75, N = 3 SE +/- 38.50, N = 3 SE +/- 41.13, N = 3 SE +/- 688.69, N = 3 SE +/- 10.63, N = 3 4239 5878 6776 7934 10853 6630 7968 10270 15352 6202 7069 10357 12469 16386 10591 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
Phoronix Test Suite v10.8.4