Apple M1 Pre Xmas

Apple M1 testing with a Apple Mac mini and Apple M1 on macOS 11.1 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2012212-HA-APPLEM1PR00&grs&sor.

Apple M1 Pre XmasProcessorMotherboardMemoryDiskGraphicsMonitorOSKernelOpenCLCompilerFile-SystemScreen ResolutionApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple SiliconVirtualApple @ 2.40GHz (8 Cores)Apple Mac mini8GB229GBApple M1DELL P2415QmacOS 11.0.120.1.0 (x86_64)OpenCL 1.2 (Oct 29 2020 19:50:08)GCC 12.0.0 + Clang 12.0.0 + Xcode 12.2APFS3840x2160Apple M1 @ 2.40GHz (8 Cores)macOS 11.120.2.0 (x86_64)OpenCL 1.2 (Nov 23 2020 03:06:15)GCC 12.0.0 + Clang 12.0.0 + Xcode 12.3OpenBenchmarking.orgEnvironment Details- XPC_FLAGS=0x0Python Details- Python 2.7.16 + Python 3.9.0

Apple M1 Pre Xmasphpbench: PHP Benchmark Suitecompilebench: Compileonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUsqlite-speedtest: Timed Time - Size 1,000compilebench: Initial Createmafft: Multiple Sequence Alignment - LSU RNAbuild2: Time To Compileonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUbuild-eigen: Time To Compileonednn: IP Shapes 3D - u8s8f32 - CPUencode-wavpack: WAV To WavPackencode-ape: WAV To APEhmmer: Pfam Database Searchbuild-ffmpeg: Time To Compileonednn: IP Shapes 1D - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUnode-web-tooling: simdjson: DistinctUserIDsimdjson: PartialTweetssimdjson: LargeRandsimdjson: Kostyacompilebench: Read Compiled TreeApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon431919622.23150.11074.610156.9736.238247.62192.981932.211979.850852.04414.160125.49716.380117.086113.90361.5298132.397187.899188.01251.438326.652433946.2134.80633968.966741.733991.766744.466775.012.320.580.580.360.53875.25431056622.45150.03073.444155.6936.564249.71392.359632.017279.575152.23614.209025.49116.367116.976113.90561.4305132.217187.780187.76651.452526.624133986.4134.73133990.966787.133976.466764.166776.40.520.540.370.58908.01436766630.83150.91674.542158.0736.235248.53692.773532.076280.054852.10814.195525.42116.343116.869113.69661.4424132.213187.776187.76551.386526.655833981.9134.73433965.666773.033985.066778.666761.90.620.560.380.63924.44423510615.91153.16074.298157.4236.118248.85792.562432.099579.883552.12614.193225.42016.355116.872113.80761.4357132.240188.031187.75951.395626.622233979.7134.68033967.966775.033972.766773.166767.70.620.550.370.58944.50OpenBenchmarking.org

PHPBench

PHP Benchmark Suite

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteApple M1 SiliconApple M1Apple M1 macOS 11.1M1 Apple Silicon90K180K270K360K450KSE +/- 6690.45, N = 15SE +/- 7279.83, N = 3SE +/- 6274.37, N = 15SE +/- 5509.59, N = 5436766431919431056423510

Compile Bench

Test: Compile

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: CompileApple M1 SiliconApple M1 macOS 11.1Apple M1M1 Apple Silicon140280420560700SE +/- 9.85, N = 3SE +/- 5.60, N = 10SE +/- 6.51, N = 3SE +/- 9.46, N = 3630.83622.45622.23615.91

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUApple M1 macOS 11.1Apple M1Apple M1 SiliconM1 Apple Silicon306090120150SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.46, N = 3SE +/- 1.51, N = 9150.03150.11150.92153.16MIN: 149.83MIN: 149.91MIN: 149.86MIN: 149.821. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

SQLite Speedtest

Timed Time - Size 1,000

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000Apple M1 macOS 11.1M1 Apple SiliconApple M1 SiliconApple M120406080100SE +/- 0.16, N = 3SE +/- 0.49, N = 3SE +/- 0.84, N = 3SE +/- 0.19, N = 373.4474.3074.5474.611. (CC) gcc options: -O2 -lz

Compile Bench

Test: Initial Create

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Initial CreateApple M1 SiliconM1 Apple SiliconApple M1Apple M1 macOS 11.1306090120150SE +/- 2.30, N = 3SE +/- 1.98, N = 3SE +/- 0.93, N = 3SE +/- 2.68, N = 3158.07157.42156.97155.69

Timed MAFFT Alignment

Multiple Sequence Alignment - LSU RNA

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNAM1 Apple SiliconApple M1 SiliconApple M1Apple M1 macOS 11.1816243240SE +/- 0.12, N = 3SE +/- 0.15, N = 3SE +/- 0.50, N = 3SE +/- 0.32, N = 336.1236.2436.2436.561. (CC) gcc options: -std=c99 -O3 -lm -lpthread

Build2

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To CompileApple M1Apple M1 SiliconM1 Apple SiliconApple M1 macOS 11.150100150200250SE +/- 1.48, N = 3SE +/- 1.06, N = 3SE +/- 0.44, N = 3SE +/- 1.54, N = 3247.62248.54248.86249.71

oneDNN

Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUApple M1 macOS 11.1M1 Apple SiliconApple M1 SiliconApple M120406080100SE +/- 0.09, N = 3SE +/- 0.01, N = 3SE +/- 0.37, N = 3SE +/- 0.60, N = 392.3692.5692.7792.98MIN: 92.13MIN: 92.43MIN: 92.14MIN: 92.221. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

oneDNN

Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUApple M1 macOS 11.1Apple M1 SiliconM1 Apple SiliconApple M1714212835SE +/- 0.11, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 332.0232.0832.1032.21MIN: 30.81MIN: 30.83MIN: 30.82MIN: 30.911. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUApple M1 macOS 11.1Apple M1M1 Apple SiliconApple M1 Silicon20406080100SE +/- 0.01, N = 3SE +/- 0.17, N = 3SE +/- 0.15, N = 3SE +/- 0.04, N = 379.5879.8579.8880.05MIN: 79.45MIN: 79.52MIN: 79.48MIN: 79.881. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

Timed Eigen Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Eigen Compilation 3.3.9Time To CompileApple M1Apple M1 SiliconM1 Apple SiliconApple M1 macOS 11.11224364860SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 352.0452.1152.1352.24

oneDNN

Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUApple M1M1 Apple SiliconApple M1 SiliconApple M1 macOS 11.148121620SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 314.1614.1914.2014.21MIN: 14.09MIN: 14.1MIN: 14.13MIN: 14.131. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

WavPack Audio Encoding

WAV To WavPack

OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.3WAV To WavPackM1 Apple SiliconApple M1 SiliconApple M1 macOS 11.1Apple M1612182430SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.07, N = 5SE +/- 0.06, N = 525.4225.4225.4925.501. (CXX) g++ options: -isysroot

Monkey Audio Encoding

WAV To APE

OpenBenchmarking.orgSeconds, Fewer Is BetterMonkey Audio Encoding 3.99.6WAV To APEApple M1 SiliconM1 Apple SiliconApple M1 macOS 11.1Apple M148121620SE +/- 0.04, N = 5SE +/- 0.03, N = 5SE +/- 0.04, N = 5SE +/- 0.04, N = 516.3416.3616.3716.381. (CXX) g++ options: -O3 -pedantic -isysroot

Timed HMMer Search

Pfam Database Search

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.1Pfam Database SearchApple M1 SiliconM1 Apple SiliconApple M1 macOS 11.1Apple M1306090120150SE +/- 0.13, N = 3SE +/- 0.14, N = 3SE +/- 0.24, N = 3SE +/- 0.24, N = 3116.87116.87116.98117.091. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm

Timed FFmpeg Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.2.2Time To CompileApple M1 SiliconM1 Apple SiliconApple M1Apple M1 macOS 11.1306090120150SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3113.70113.81113.90113.91

oneDNN

Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUApple M1 macOS 11.1M1 Apple SiliconApple M1 SiliconApple M11428425670SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 361.4361.4461.4461.53MIN: 61.33MIN: 61.3MIN: 61.34MIN: 61.241. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUApple M1 SiliconApple M1 macOS 11.1M1 Apple SiliconApple M1306090120150SE +/- 0.07, N = 3SE +/- 0.00, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 3132.21132.22132.24132.40MIN: 131.99MIN: 132.04MIN: 132.02MIN: 132.031. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUApple M1 SiliconApple M1 macOS 11.1Apple M1M1 Apple Silicon4080120160200SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.23, N = 3187.78187.78187.90188.03MIN: 187.51MIN: 187.48MIN: 187.6MIN: 187.511. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUM1 Apple SiliconApple M1 SiliconApple M1 macOS 11.1Apple M14080120160200SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3187.76187.77187.77188.01MIN: 186.77MIN: 186.84MIN: 186.81MIN: 1871. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUApple M1 SiliconM1 Apple SiliconApple M1Apple M1 macOS 11.11224364860SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 351.3951.4051.4451.45MIN: 51.15MIN: 51.12MIN: 51.16MIN: 51.191. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUM1 Apple SiliconApple M1 macOS 11.1Apple M1Apple M1 Silicon612182430SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 326.6226.6226.6526.66MIN: 26.35MIN: 26.31MIN: 26.4MIN: 26.371. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUApple M1M1 Apple SiliconApple M1 SiliconApple M1 macOS 11.17K14K21K28K35KSE +/- 8.37, N = 3SE +/- 6.94, N = 3SE +/- 9.75, N = 3SE +/- 6.04, N = 333946.233979.733981.933986.4MIN: 33913.1MIN: 33958MIN: 33958.6MIN: 33970.91. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUM1 Apple SiliconApple M1 macOS 11.1Apple M1 SiliconApple M1306090120150SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 3134.68134.73134.73134.81MIN: 134.52MIN: 134.57MIN: 134.61MIN: 134.621. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUApple M1 SiliconM1 Apple SiliconApple M1Apple M1 macOS 11.17K14K21K28K35KSE +/- 4.92, N = 3SE +/- 11.75, N = 3SE +/- 7.00, N = 3SE +/- 6.95, N = 333965.633967.933968.933990.9MIN: 33949.9MIN: 33947.4MIN: 33955MIN: 33970.61. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

oneDNN

Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUApple M1Apple M1 SiliconM1 Apple SiliconApple M1 macOS 11.114K28K42K56K70KSE +/- 21.39, N = 3SE +/- 5.34, N = 3SE +/- 10.14, N = 3SE +/- 7.91, N = 366741.766773.066775.066787.1MIN: 66688.8MIN: 66750.3MIN: 66747.8MIN: 66762.41. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUM1 Apple SiliconApple M1 macOS 11.1Apple M1 SiliconApple M17K14K21K28K35KSE +/- 13.52, N = 3SE +/- 9.46, N = 3SE +/- 9.30, N = 3SE +/- 3.96, N = 333972.733976.433985.033991.7MIN: 33948.8MIN: 33952.6MIN: 33959.5MIN: 33978.71. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

oneDNN

Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUApple M1Apple M1 macOS 11.1M1 Apple SiliconApple M1 Silicon14K28K42K56K70KSE +/- 19.96, N = 3SE +/- 6.62, N = 3SE +/- 7.42, N = 3SE +/- 11.24, N = 366744.466764.166773.166778.6MIN: 66686.8MIN: 66743.7MIN: 66750.3MIN: 66747.41. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

oneDNN

Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUApple M1 SiliconM1 Apple SiliconApple M1Apple M1 macOS 11.114K28K42K56K70KSE +/- 7.66, N = 3SE +/- 10.36, N = 3SE +/- 3.84, N = 3SE +/- 0.74, N = 366761.966767.766775.066776.4MIN: 66738.2MIN: 66734.8MIN: 66758MIN: 66764.71. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

Node.js V8 Web Tooling Benchmark

OpenBenchmarking.orgruns/s, More Is BetterNode.js V8 Web Tooling BenchmarkApple M13691215SE +/- 0.08, N = 312.321. Nodejs v15.4.0

simdjson

Throughput Test: DistinctUserID

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: DistinctUserIDM1 Apple SiliconApple M1 SiliconApple M1Apple M1 macOS 11.10.13950.2790.41850.5580.6975SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 15SE +/- 0.03, N = 120.620.620.580.521. (CXX) g++ options: -O3 -isysroot

simdjson

Throughput Test: PartialTweets

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: PartialTweetsApple M1Apple M1 SiliconM1 Apple SiliconApple M1 macOS 11.10.13050.2610.39150.5220.6525SE +/- 0.01, N = 15SE +/- 0.02, N = 15SE +/- 0.02, N = 15SE +/- 0.03, N = 120.580.560.550.541. (CXX) g++ options: -O3 -isysroot

simdjson

Throughput Test: LargeRandom

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: LargeRandomApple M1 SiliconM1 Apple SiliconApple M1 macOS 11.1Apple M10.08550.1710.25650.3420.4275SE +/- 0.01, N = 15SE +/- 0.01, N = 12SE +/- 0.01, N = 15SE +/- 0.01, N = 150.380.370.370.361. (CXX) g++ options: -O3 -isysroot

simdjson

Throughput Test: Kostya

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: KostyaApple M1 SiliconM1 Apple SiliconApple M1 macOS 11.1Apple M10.14180.28360.42540.56720.709SE +/- 0.01, N = 3SE +/- 0.03, N = 15SE +/- 0.03, N = 12SE +/- 0.03, N = 120.630.580.580.531. (CXX) g++ options: -O3 -isysroot

Compile Bench

Test: Read Compiled Tree

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Read Compiled TreeM1 Apple SiliconApple M1 SiliconApple M1 macOS 11.1Apple M12004006008001000SE +/- 13.69, N = 3SE +/- 17.74, N = 3SE +/- 25.92, N = 3SE +/- 70.83, N = 3944.50924.44908.01875.25

Phoronix Test Suite v10.8.5