starfive2 mnn final SiFive RISC-V testing with a StarFive VisionFive V2 and starfive on Debian via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2403246-NE-STARFIVE278 SiFive RISC-V - starfive - StarFive VisionFive V2 Processor: SiFive RISC-V @ 1.50GHz (4 Cores), Motherboard: StarFive VisionFive V2, Memory: 8GB, Disk: 32GB SD32G, Graphics: starfive
OS: Debian, Kernel: 5.15.0-starfive (riscv64), Display Server: X Server 1.21.1.5, OpenCL: OpenCL 3.0, Vulkan: 1.3.225, Compiler: GCC 12.2.0 + Clang 14.0.6, File-System: ext4, Screen Resolution: 1920x1080
Compiler Notes: --build=riscv64-linux-gnu --disable-libitm --disable-libquadmath --disable-libquadmath-support --disable-multilib --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-shared --enable-threads=posix --host=riscv64-linux-gnu --program-prefix=riscv64-linux-gnu- --target=riscv64-linux-gnu --with-abi=lp64d --with-arch=rv64gc --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto -vProcessor Notes: Scaling Governor: cpufreq-dt ondemand
Mobile Neural Network MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. This MNN test profile is building the OpenMP / CPU threaded version for processor benchmarking and not any GPU-accelerated test. MNN does allow making use of AVX-512 extensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: nasnet SiFive RISC-V - starfive - StarFive VisionFive V2 120 240 360 480 600 SE +/- 0.51, N = 3 538.56 MIN: 536.12 / MAX: 1027.08 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenetV3 SiFive RISC-V - starfive - StarFive VisionFive V2 11 22 33 44 55 SE +/- 0.01, N = 3 49.33 MIN: 49.04 / MAX: 59.84 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: squeezenetv1.1 SiFive RISC-V - starfive - StarFive VisionFive V2 70 140 210 280 350 SE +/- 0.38, N = 3 312.06 MIN: 310.21 / MAX: 448.16 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: resnet-v2-50 SiFive RISC-V - starfive - StarFive VisionFive V2 800 1600 2400 3200 4000 SE +/- 3.90, N = 3 3593.32 MIN: 3579.18 / MAX: 3793.72 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: SqueezeNetV1.0 SiFive RISC-V - starfive - StarFive VisionFive V2 110 220 330 440 550 SE +/- 1.16, N = 3 491.48 MIN: 486.98 / MAX: 638.75 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: MobileNetV2_224 SiFive RISC-V - starfive - StarFive VisionFive V2 50 100 150 200 250 SE +/- 0.49, N = 3 239.95 MIN: 238.8 / MAX: 268.28 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenet-v1-1.0 SiFive RISC-V - starfive - StarFive VisionFive V2 130 260 390 520 650 SE +/- 1.19, N = 3 597.97 MIN: 594.97 / MAX: 1178.43 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: inception-v3 SiFive RISC-V - starfive - StarFive VisionFive V2 1200 2400 3600 4800 6000 SE +/- 7.52, N = 3 5590.17 MIN: 5559.17 / MAX: 10084.82 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
SiFive RISC-V - starfive - StarFive VisionFive V2 Processor: SiFive RISC-V @ 1.50GHz (4 Cores), Motherboard: StarFive VisionFive V2, Memory: 8GB, Disk: 32GB SD32G, Graphics: starfive
OS: Debian, Kernel: 5.15.0-starfive (riscv64), Display Server: X Server 1.21.1.5, OpenCL: OpenCL 3.0, Vulkan: 1.3.225, Compiler: GCC 12.2.0 + Clang 14.0.6, File-System: ext4, Screen Resolution: 1920x1080
Compiler Notes: --build=riscv64-linux-gnu --disable-libitm --disable-libquadmath --disable-libquadmath-support --disable-multilib --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-shared --enable-threads=posix --host=riscv64-linux-gnu --program-prefix=riscv64-linux-gnu- --target=riscv64-linux-gnu --with-abi=lp64d --with-arch=rv64gc --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto -vProcessor Notes: Scaling Governor: cpufreq-dt ondemand
Testing initiated at 23 March 2024 23:38 by user user.