apple m1 onnx and others

Apple M1 testing with a Apple Mac mini (M1 2020) and llvmpipe on Arch Linux ARM via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2203269-NE-APPLEM1ON41.

apple m1 onnx and othersProcessorMotherboardMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionABCDApple M1 @ 2.06GHz (4 Cores / 8 Threads)Apple Mac mini (M1 2020)8GB251GB APPLE SSD AP0256Q + 2 x 0GB APPLE SSD AP0256QllvmpipeBroadcom NetXtreme BCM57762 PCIe + Broadcom BRCM4378 + Broadcom Device 5f69Arch Linux ARM5.17.0-rc7-asahi-next-20220310-5-1-ARCH (aarch64)KDE Plasma 5.24.3X Server 1.21.1.34.5 Mesa 21.3.7 (LLVM 13.0.1 128 bits)GCC 11.2.0 + Clang 13.0.1ext41920x1080OpenBenchmarking.orgCompiler Details- --build=aarch64-unknown-linux-gnu --disable-libssp --disable-libstdcxx-pch --disable-multilib --disable-werror --enable-__cxa_atexit --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-fix-cortex-a53-835769 --enable-fix-cortex-a53-843419 --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=c,c++,fortran,go,lto,objc,obj-c++,d --enable-lto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-unknown-linux-gnu --mandir=/usr/share/man --with-arch=armv8-a --with-isl --with-linker-hash-style=gnu Processor Details- Scaling Governor: apple-cpufreq schedutilPython Details- Python 3.10.3Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected

apple m1 onnx and othersspeedtest-cli: Internet Download Speedspeedtest-cli: Internet Upload Speedspeedtest-cli: Internet Latencyperf-bench: Epoll Waitperf-bench: Futex Hashperf-bench: Memcpy 1MBperf-bench: Memset 1MBperf-bench: Sched Pipeperf-bench: Futex Lock-Piperf-bench: Syscall Basiconnx: GPT-2 - CPUonnx: yolov4 - CPUonnx: bertsquad-12 - CPUonnx: fcn-resnet101-11 - CPUonnx: ArcFace ResNet-100 - CPUonnx: super-resolution-10 - CPUABCD334.359.8415.98197591350354749.20047476.69262783165163984620983942232311375732522308.289.8215.19395606349814956.52368375.00848767730165084712333966232311375762523325.49.4116.33996455332347258.66378374.7607667044316138334987397523131137571252087.976.2916.50996342331781564.08008277.09866383180162884765963984232310375722525OpenBenchmarking.org

speedtest-cli

Internet Download Speed

OpenBenchmarking.orgMbit/s, More Is Betterspeedtest-cli 2.1.3Internet Download SpeedABCD70140210280350334.35308.28325.4087.97

speedtest-cli

Internet Upload Speed

OpenBenchmarking.orgMbit/s, More Is Betterspeedtest-cli 2.1.3Internet Upload SpeedABCD36912159.849.829.416.29

speedtest-cli

Internet Latency

OpenBenchmarking.orgms, Fewer Is Betterspeedtest-cli 2.1.3Internet LatencyABCD4812162015.9815.1916.3416.51

perf-bench

Benchmark: Epoll Wait

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Epoll WaitABCD20K40K60K80K100K975919560696455963421. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-aarch64 -lunwind -Xlinker -lpthread -lrt -lm -ldl -lelf -ldebuginfod -ldw -lcrypto -lslang -lpython3.10 -lcrypt -lutil -lbfd -lopcodes -liberty -lz -llzma -lzstd -lcap -lnuma

perf-bench

Benchmark: Futex Hash

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Futex HashABCD800K1600K2400K3200K4000K35035473498149332347233178151. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-aarch64 -lunwind -Xlinker -lpthread -lrt -lm -ldl -lelf -ldebuginfod -ldw -lcrypto -lslang -lpython3.10 -lcrypt -lutil -lbfd -lopcodes -liberty -lz -llzma -lzstd -lcap -lnuma

perf-bench

Benchmark: Memcpy 1MB

OpenBenchmarking.orgGB/sec, More Is Betterperf-benchBenchmark: Memcpy 1MBABCD142842567049.2056.5258.6664.081. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-aarch64 -lunwind -Xlinker -lpthread -lrt -lm -ldl -lelf -ldebuginfod -ldw -lcrypto -lslang -lpython3.10 -lcrypt -lutil -lbfd -lopcodes -liberty -lz -llzma -lzstd -lcap -lnuma

perf-bench

Benchmark: Memset 1MB

OpenBenchmarking.orgGB/sec, More Is Betterperf-benchBenchmark: Memset 1MBABCD2040608010076.6975.0174.7677.101. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-aarch64 -lunwind -Xlinker -lpthread -lrt -lm -ldl -lelf -ldebuginfod -ldw -lcrypto -lslang -lpython3.10 -lcrypt -lutil -lbfd -lopcodes -liberty -lz -llzma -lzstd -lcap -lnuma

perf-bench

Benchmark: Sched Pipe

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Sched PipeABCD20K40K60K80K100K831656773070443831801. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-aarch64 -lunwind -Xlinker -lpthread -lrt -lm -ldl -lelf -ldebuginfod -ldw -lcrypto -lslang -lpython3.10 -lcrypt -lutil -lbfd -lopcodes -liberty -lz -llzma -lzstd -lcap -lnuma

perf-bench

Benchmark: Futex Lock-Pi

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Futex Lock-PiABCD40080012001600200016391650161316281. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-aarch64 -lunwind -Xlinker -lpthread -lrt -lm -ldl -lelf -ldebuginfod -ldw -lcrypto -lslang -lpython3.10 -lcrypt -lutil -lbfd -lopcodes -liberty -lz -llzma -lzstd -lcap -lnuma

perf-bench

Benchmark: Syscall Basic

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Syscall BasicABCD2M4M6M8M10M84620988471233833498784765961. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-aarch64 -lunwind -Xlinker -lpthread -lrt -lm -ldl -lelf -ldebuginfod -ldw -lcrypto -lslang -lpython3.10 -lcrypt -lutil -lbfd -lopcodes -liberty -lz -llzma -lzstd -lcap -lnuma

ONNX Runtime

Model: GPT-2 - Device: CPU

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPUABCD900180027003600450039423966397539841. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: yolov4 - Device: CPU

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: yolov4 - Device: CPUABCD501001502002502322322312321. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: bertsquad-12 - Device: CPU

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPUABCD701402102803503113113113101. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: fcn-resnet101-11 - Device: CPU

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPUABCD918273645373737371. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: ArcFace ResNet-100 - Device: CPU

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPUABCD1202403604806005735765715721. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: super-resolution-10 - Device: CPU

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPUABCD500100015002000250025222523252025251. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt


Phoronix Test Suite v10.8.4