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&grr&rdt.

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 Xmasonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUsimdjson: LargeRandsimdjson: PartialTweetsbuild2: Time To Compileonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUsimdjson: Kostyasimdjson: DistinctUserIDphpbench: PHP Benchmark Suitehmmer: Pfam Database Searchbuild-ffmpeg: Time To Compilesqlite-speedtest: Timed Time - Size 1,000compilebench: Compilenode-web-tooling: build-eigen: Time To Compileencode-wavpack: WAV To WavPackmafft: Multiple Sequence Alignment - LSU RNAonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUencode-ape: WAV To APEonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUcompilebench: Read Compiled Treecompilebench: Initial CreateApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon66741.766775.066744.40.360.58247.62133991.733946.233968.90.530.58431919117.086113.90374.610622.2312.3252.04425.49736.238150.11016.380132.39761.529892.981926.652451.438314.160132.2119188.01279.8508187.899134.806875.25156.9766787.166776.466764.10.370.54249.71333976.433986.433990.90.580.52431056116.976113.90573.444622.4552.23625.49136.564150.03016.367132.21761.430592.359626.624151.452514.209032.0172187.76679.5751187.780134.731908.01155.6966773.066761.966778.60.380.56248.53633985.033981.933965.60.630.62436766116.869113.69674.542630.8352.10825.42136.235150.91616.343132.21361.442492.773526.655851.386514.195532.0762187.76580.0548187.776134.734924.44158.0766775.066767.766773.10.370.55248.85733972.733979.733967.90.580.62423510116.872113.80774.298615.9152.12625.42036.118153.16016.355132.24061.435792.562426.622251.395614.193232.0995187.75979.8835188.031134.680944.50157.42OpenBenchmarking.org

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 macOS 11.1Apple M1 SiliconM1 Apple Silicon14K28K42K56K70KSE +/- 21.39, N = 3SE +/- 7.91, N = 3SE +/- 5.34, N = 3SE +/- 10.14, N = 366741.766787.166773.066775.0MIN: 66688.8MIN: 66762.4MIN: 66750.3MIN: 66747.81. (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 M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon14K28K42K56K70KSE +/- 3.84, N = 3SE +/- 0.74, N = 3SE +/- 7.66, N = 3SE +/- 10.36, N = 366775.066776.466761.966767.7MIN: 66758MIN: 66764.7MIN: 66738.2MIN: 66734.81. (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 11.1Apple M1 SiliconM1 Apple Silicon14K28K42K56K70KSE +/- 19.96, N = 3SE +/- 6.62, N = 3SE +/- 11.24, N = 3SE +/- 7.42, N = 366744.466764.166778.666773.1MIN: 66686.8MIN: 66743.7MIN: 66747.4MIN: 66750.31. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

simdjson

Throughput Test: LargeRandom

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: LargeRandomApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon0.08550.1710.25650.3420.4275SE +/- 0.01, N = 15SE +/- 0.01, N = 15SE +/- 0.01, N = 15SE +/- 0.01, N = 120.360.370.380.371. (CXX) g++ options: -O3 -isysroot

simdjson

Throughput Test: PartialTweets

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: PartialTweetsApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon0.13050.2610.39150.5220.6525SE +/- 0.01, N = 15SE +/- 0.03, N = 12SE +/- 0.02, N = 15SE +/- 0.02, N = 150.580.540.560.551. (CXX) g++ options: -O3 -isysroot

Build2

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To CompileApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon50100150200250SE +/- 1.48, N = 3SE +/- 1.54, N = 3SE +/- 1.06, N = 3SE +/- 0.44, N = 3247.62249.71248.54248.86

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: CPUApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon7K14K21K28K35KSE +/- 3.96, N = 3SE +/- 9.46, N = 3SE +/- 9.30, N = 3SE +/- 13.52, N = 333991.733976.433985.033972.7MIN: 33978.7MIN: 33952.6MIN: 33959.5MIN: 33948.81. (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 M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon7K14K21K28K35KSE +/- 8.37, N = 3SE +/- 6.04, N = 3SE +/- 9.75, N = 3SE +/- 6.94, N = 333946.233986.433981.933979.7MIN: 33913.1MIN: 33970.9MIN: 33958.6MIN: 339581. (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 M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon7K14K21K28K35KSE +/- 7.00, N = 3SE +/- 6.95, N = 3SE +/- 4.92, N = 3SE +/- 11.75, N = 333968.933990.933965.633967.9MIN: 33955MIN: 33970.6MIN: 33949.9MIN: 33947.41. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

simdjson

Throughput Test: Kostya

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: KostyaApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon0.14180.28360.42540.56720.709SE +/- 0.03, N = 12SE +/- 0.03, N = 12SE +/- 0.01, N = 3SE +/- 0.03, N = 150.530.580.630.581. (CXX) g++ options: -O3 -isysroot

simdjson

Throughput Test: DistinctUserID

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: DistinctUserIDApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon0.13950.2790.41850.5580.6975SE +/- 0.01, N = 15SE +/- 0.03, N = 12SE +/- 0.00, N = 3SE +/- 0.00, N = 30.580.520.620.621. (CXX) g++ options: -O3 -isysroot

PHPBench

PHP Benchmark Suite

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon90K180K270K360K450KSE +/- 7279.83, N = 3SE +/- 6274.37, N = 15SE +/- 6690.45, N = 15SE +/- 5509.59, N = 5431919431056436766423510

Timed HMMer Search

Pfam Database Search

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.1Pfam Database SearchApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon306090120150SE +/- 0.24, N = 3SE +/- 0.24, N = 3SE +/- 0.13, N = 3SE +/- 0.14, N = 3117.09116.98116.87116.871. (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 M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon306090120150SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3113.90113.91113.70113.81

SQLite Speedtest

Timed Time - Size 1,000

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000Apple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon20406080100SE +/- 0.19, N = 3SE +/- 0.16, N = 3SE +/- 0.84, N = 3SE +/- 0.49, N = 374.6173.4474.5474.301. (CC) gcc options: -O2 -lz

Compile Bench

Test: Compile

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: CompileApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon140280420560700SE +/- 6.51, N = 3SE +/- 5.60, N = 10SE +/- 9.85, N = 3SE +/- 9.46, N = 3622.23622.45630.83615.91

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

Timed Eigen Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Eigen Compilation 3.3.9Time To CompileApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon1224364860SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 352.0452.2452.1152.13

WavPack Audio Encoding

WAV To WavPack

OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.3WAV To WavPackApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon612182430SE +/- 0.06, N = 5SE +/- 0.07, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 525.5025.4925.4225.421. (CXX) g++ options: -isysroot

Timed MAFFT Alignment

Multiple Sequence Alignment - LSU RNA

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNAApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon816243240SE +/- 0.50, N = 3SE +/- 0.32, N = 3SE +/- 0.15, N = 3SE +/- 0.12, N = 336.2436.5636.2436.121. (CC) gcc options: -std=c99 -O3 -lm -lpthread

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 M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon306090120150SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.46, N = 3SE +/- 1.51, N = 9150.11150.03150.92153.16MIN: 149.91MIN: 149.83MIN: 149.86MIN: 149.821. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

Monkey Audio Encoding

WAV To APE

OpenBenchmarking.orgSeconds, Fewer Is BetterMonkey Audio Encoding 3.99.6WAV To APEApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon48121620SE +/- 0.04, N = 5SE +/- 0.04, N = 5SE +/- 0.04, N = 5SE +/- 0.03, N = 516.3816.3716.3416.361. (CXX) g++ options: -O3 -pedantic -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 M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon306090120150SE +/- 0.09, N = 3SE +/- 0.00, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3132.40132.22132.21132.24MIN: 132.03MIN: 132.04MIN: 131.99MIN: 132.021. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

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 M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon1428425670SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 361.5361.4361.4461.44MIN: 61.24MIN: 61.33MIN: 61.34MIN: 61.31. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

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 M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon20406080100SE +/- 0.60, N = 3SE +/- 0.09, N = 3SE +/- 0.37, N = 3SE +/- 0.01, N = 392.9892.3692.7792.56MIN: 92.22MIN: 92.13MIN: 92.14MIN: 92.431. (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: CPUApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon612182430SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 326.6526.6226.6626.62MIN: 26.4MIN: 26.31MIN: 26.37MIN: 26.351. (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 M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon1224364860SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 351.4451.4551.3951.40MIN: 51.16MIN: 51.19MIN: 51.15MIN: 51.121. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

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 M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon48121620SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 314.1614.2114.2014.19MIN: 14.09MIN: 14.13MIN: 14.13MIN: 14.11. (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 M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon714212835SE +/- 0.03, N = 3SE +/- 0.11, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 332.2132.0232.0832.10MIN: 30.91MIN: 30.81MIN: 30.83MIN: 30.821. (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: CPUApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon4080120160200SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3188.01187.77187.77187.76MIN: 187MIN: 186.81MIN: 186.84MIN: 186.771. (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 M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon20406080100SE +/- 0.17, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.15, N = 379.8579.5880.0579.88MIN: 79.52MIN: 79.45MIN: 79.88MIN: 79.481. (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 M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon4080120160200SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.23, N = 3187.90187.78187.78188.03MIN: 187.6MIN: 187.48MIN: 187.51MIN: 187.511. (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: CPUApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon306090120150SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3134.81134.73134.73134.68MIN: 134.62MIN: 134.57MIN: 134.61MIN: 134.521. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

Compile Bench

Test: Read Compiled Tree

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Read Compiled TreeApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon2004006008001000SE +/- 70.83, N = 3SE +/- 25.92, N = 3SE +/- 17.74, N = 3SE +/- 13.69, N = 3875.25908.01924.44944.50

Compile Bench

Test: Initial Create

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Initial CreateApple M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple Silicon306090120150SE +/- 0.93, N = 3SE +/- 2.68, N = 3SE +/- 2.30, N = 3SE +/- 1.98, N = 3156.97155.69158.07157.42

Phoronix Test Suite v10.8.5