Apple M1 Pre Xmas

Apple M1 testing with a Apple Mac mini and Apple M1 on macOS 11.1 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 2012212-HA-APPLEM1PR00
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Apple M1
December 20 2020
  3 Hours, 28 Minutes
Apple M1 macOS 11.1
December 21 2020
  3 Hours, 35 Minutes
Apple M1 Silicon
December 21 2020
  3 Hours, 13 Minutes
M1 Apple Silicon
December 21 2020
  3 Hours, 18 Minutes
Invert Behavior (Only Show Selected Data)
  3 Hours, 23 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

Apple M1

Processor: VirtualApple @ 2.40GHz (8 Cores), Motherboard: Apple Mac mini, Memory: 8GB, Disk: 229GB, Graphics: Apple M1, Monitor: DELL P2415Q

OS: macOS 11.0.1, Kernel: 20.1.0 (x86_64), OpenCL: OpenCL 1.2 (Oct 29 2020 19:50:08), Compiler: GCC 12.0.0 + Clang 12.0.0 + Xcode 12.2, File-System: APFS, Screen Resolution: 3840x2160

Environment Notes: XPC_FLAGS=0x0
Python Notes: Python 2.7.16 + Python 3.9.0

Apple M1 macOS 11.1

Apple M1 Silicon

M1 Apple Silicon

Processor: Apple M1 @ 2.40GHz (8 Cores), Motherboard: Apple Mac mini, Memory: 8GB, Disk: 229GB, Graphics: Apple M1, Monitor: DELL P2415Q

OS: macOS 11.1, Kernel: 20.2.0 (x86_64), OpenCL: OpenCL 1.2 (Nov 23 2020 03:06:15), Compiler: GCC 12.0.0 + Clang 12.0.0 + Xcode 12.3, File-System: APFS, Screen Resolution: 3840x2160

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 M1Apple M1 macOS 11.1Apple M1 SiliconM1 Apple SiliconResult OverviewPhoronix Test Suite100%102%104%106%109%simdjsonPHPBenchCompile BenchSQLite SpeedtestTimed MAFFT AlignmentBuild2oneDNNTimed Eigen CompilationWavPack Audio EncodingTimed HMMer SearchMonkey Audio EncodingTimed FFmpeg Compilation

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

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUApple M1 macOS 11.1M1 Apple SiliconApple M1 SiliconApple M114K28K42K56K70KSE +/- 7.91, N = 3SE +/- 10.14, N = 3SE +/- 5.34, N = 3SE +/- 21.39, N = 366787.166775.066773.066741.7MIN: 66762.4MIN: 66747.8MIN: 66750.3MIN: 66688.81. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUApple M1 macOS 11.1Apple M1M1 Apple SiliconApple M1 Silicon14K28K42K56K70KSE +/- 0.74, N = 3SE +/- 3.84, N = 3SE +/- 10.36, N = 3SE +/- 7.66, N = 366776.466775.066767.766761.9MIN: 66764.7MIN: 66758MIN: 66734.8MIN: 66738.21. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUApple M1 SiliconM1 Apple SiliconApple M1 macOS 11.1Apple M114K28K42K56K70KSE +/- 11.24, N = 3SE +/- 7.42, N = 3SE +/- 6.62, N = 3SE +/- 19.96, N = 366778.666773.166764.166744.4MIN: 66747.4MIN: 66750.3MIN: 66743.7MIN: 66686.81. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: LargeRandomApple M1Apple M1 macOS 11.1M1 Apple SiliconApple M1 Silicon0.08550.1710.25650.3420.4275SE +/- 0.01, N = 15SE +/- 0.01, N = 15SE +/- 0.01, N = 12SE +/- 0.01, N = 150.360.370.370.381. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: PartialTweetsApple M1 macOS 11.1M1 Apple SiliconApple M1 SiliconApple M10.13050.2610.39150.5220.6525SE +/- 0.03, N = 12SE +/- 0.02, N = 15SE +/- 0.02, N = 15SE +/- 0.01, N = 150.540.550.560.581. (CXX) g++ options: -O3 -isysroot

Build2

This test profile measures the time to bootstrap/install the build2 C++ build toolchain from source. Build2 is a cross-platform build toolchain for C/C++ code and features Cargo-like features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To CompileApple M1 macOS 11.1M1 Apple SiliconApple M1 SiliconApple M150100150200250SE +/- 1.54, N = 3SE +/- 0.44, N = 3SE +/- 1.06, N = 3SE +/- 1.48, N = 3249.71248.86248.54247.62

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUApple M1Apple M1 SiliconApple M1 macOS 11.1M1 Apple Silicon7K14K21K28K35KSE +/- 3.96, N = 3SE +/- 9.30, N = 3SE +/- 9.46, N = 3SE +/- 13.52, N = 333991.733985.033976.433972.7MIN: 33978.7MIN: 33959.5MIN: 33952.6MIN: 33948.81. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUApple M1 macOS 11.1Apple M1 SiliconM1 Apple SiliconApple M17K14K21K28K35KSE +/- 6.04, N = 3SE +/- 9.75, N = 3SE +/- 6.94, N = 3SE +/- 8.37, N = 333986.433981.933979.733946.2MIN: 33970.9MIN: 33958.6MIN: 33958MIN: 33913.11. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUApple M1 macOS 11.1Apple M1M1 Apple SiliconApple M1 Silicon7K14K21K28K35KSE +/- 6.95, N = 3SE +/- 7.00, N = 3SE +/- 11.75, N = 3SE +/- 4.92, N = 333990.933968.933967.933965.6MIN: 33970.6MIN: 33955MIN: 33947.4MIN: 33949.91. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: KostyaApple M1Apple M1 macOS 11.1M1 Apple SiliconApple M1 Silicon0.14180.28360.42540.56720.709SE +/- 0.03, N = 12SE +/- 0.03, N = 12SE +/- 0.03, N = 15SE +/- 0.01, N = 30.530.580.580.631. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: DistinctUserIDApple M1 macOS 11.1Apple M1Apple M1 SiliconM1 Apple Silicon0.13950.2790.41850.5580.6975SE +/- 0.03, N = 12SE +/- 0.01, N = 15SE +/- 0.00, N = 3SE +/- 0.00, N = 30.520.580.620.621. (CXX) g++ options: -O3 -isysroot

PHPBench

PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteM1 Apple SiliconApple M1 macOS 11.1Apple M1Apple M1 Silicon90K180K270K360K450KSE +/- 5509.59, N = 5SE +/- 6274.37, N = 15SE +/- 7279.83, N = 3SE +/- 6690.45, N = 15423510431056431919436766

Timed HMMer Search

This test searches through the Pfam database of profile hidden markov models. The search finds the domain structure of Drosophila Sevenless protein. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.1Pfam Database SearchApple M1Apple M1 macOS 11.1M1 Apple SiliconApple M1 Silicon306090120150SE +/- 0.24, N = 3SE +/- 0.24, N = 3SE +/- 0.14, N = 3SE +/- 0.13, N = 3117.09116.98116.87116.871. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm

Timed FFmpeg Compilation

This test times how long it takes to build the FFmpeg multimedia library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.2.2Time To CompileApple M1 macOS 11.1Apple M1M1 Apple SiliconApple M1 Silicon306090120150SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3113.91113.90113.81113.70

SQLite Speedtest

This is a benchmark of SQLite's speedtest1 benchmark program with an increased problem size of 1,000. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000Apple M1Apple M1 SiliconM1 Apple SiliconApple M1 macOS 11.120406080100SE +/- 0.19, N = 3SE +/- 0.84, N = 3SE +/- 0.49, N = 3SE +/- 0.16, N = 374.6174.5474.3073.441. (CC) gcc options: -O2 -lz

Compile Bench

Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: CompileM1 Apple SiliconApple M1Apple M1 macOS 11.1Apple M1 Silicon140280420560700SE +/- 9.46, N = 3SE +/- 6.51, N = 3SE +/- 5.60, N = 10SE +/- 9.85, N = 3615.91622.23622.45630.83

Node.js V8 Web Tooling Benchmark

Running the V8 project's Web-Tooling-Benchmark under Node.js. The Web-Tooling-Benchmark stresses JavaScript-related workloads common to web developers like Babel and TypeScript and Babylon. This test profile can test the system's JavaScript performance with Node.js. Learn more via the OpenBenchmarking.org test page.

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

Timed Eigen Compilation

This test times how long it takes to build all Eigen examples. The Eigen examples are compiled serially. Eigen is a C++ template library for linear algebra. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Eigen Compilation 3.3.9Time To CompileApple M1 macOS 11.1M1 Apple SiliconApple M1 SiliconApple M11224364860SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 352.2452.1352.1152.04

WavPack Audio Encoding

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

This test performs an alignment of 100 pyruvate decarboxylase sequences. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNAApple M1 macOS 11.1Apple M1Apple M1 SiliconM1 Apple Silicon816243240SE +/- 0.32, N = 3SE +/- 0.50, N = 3SE +/- 0.15, N = 3SE +/- 0.12, N = 336.5636.2436.2436.121. (CC) gcc options: -std=c99 -O3 -lm -lpthread

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUM1 Apple SiliconApple M1 SiliconApple M1Apple M1 macOS 11.1306090120150SE +/- 1.51, N = 9SE +/- 0.46, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3153.16150.92150.11150.03MIN: 149.82MIN: 149.86MIN: 149.91MIN: 149.831. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

Monkey Audio Encoding

This test times how long it takes to encode a sample WAV file to Monkey's Audio APE format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMonkey Audio Encoding 3.99.6WAV To APEApple M1Apple M1 macOS 11.1M1 Apple SiliconApple M1 Silicon48121620SE +/- 0.04, N = 5SE +/- 0.04, N = 5SE +/- 0.03, N = 5SE +/- 0.04, N = 516.3816.3716.3616.341. (CXX) g++ options: -O3 -pedantic -isysroot

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUApple M1M1 Apple SiliconApple M1 macOS 11.1Apple M1 Silicon306090120150SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.00, N = 3SE +/- 0.07, N = 3132.40132.24132.22132.21MIN: 132.03MIN: 132.02MIN: 132.04MIN: 131.991. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUApple M1Apple M1 SiliconM1 Apple SiliconApple M1 macOS 11.11428425670SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 361.5361.4461.4461.43MIN: 61.24MIN: 61.34MIN: 61.3MIN: 61.331. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUApple M1Apple M1 SiliconM1 Apple SiliconApple M1 macOS 11.120406080100SE +/- 0.60, N = 3SE +/- 0.37, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 392.9892.7792.5692.36MIN: 92.22MIN: 92.14MIN: 92.43MIN: 92.131. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUApple M1 SiliconApple M1Apple M1 macOS 11.1M1 Apple Silicon612182430SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 326.6626.6526.6226.62MIN: 26.37MIN: 26.4MIN: 26.31MIN: 26.351. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUApple M1 macOS 11.1Apple M1M1 Apple SiliconApple M1 Silicon1224364860SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 351.4551.4451.4051.39MIN: 51.19MIN: 51.16MIN: 51.12MIN: 51.151. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUApple M1 macOS 11.1Apple M1 SiliconM1 Apple SiliconApple M148121620SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 314.2114.2014.1914.16MIN: 14.13MIN: 14.13MIN: 14.1MIN: 14.091. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUApple M1M1 Apple SiliconApple M1 SiliconApple M1 macOS 11.1714212835SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.11, N = 332.2132.1032.0832.02MIN: 30.91MIN: 30.82MIN: 30.83MIN: 30.811. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUApple M1 SiliconM1 Apple SiliconApple M1Apple M1 macOS 11.120406080100SE +/- 0.04, N = 3SE +/- 0.15, N = 3SE +/- 0.17, N = 3SE +/- 0.01, N = 380.0579.8879.8579.58MIN: 79.88MIN: 79.48MIN: 79.52MIN: 79.451. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUM1 Apple SiliconApple M1Apple M1 macOS 11.1Apple M1 Silicon4080120160200SE +/- 0.23, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3188.03187.90187.78187.78MIN: 187.51MIN: 187.6MIN: 187.48MIN: 187.511. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUApple M1Apple M1 SiliconApple M1 macOS 11.1M1 Apple Silicon306090120150SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3134.81134.73134.73134.68MIN: 134.62MIN: 134.61MIN: 134.57MIN: 134.521. (CXX) g++ options: -O3 -std=c++11 -msse4.1 -fPIC -isysroot

Compile Bench

Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.

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

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Initial CreateApple M1 macOS 11.1Apple M1M1 Apple SiliconApple M1 Silicon306090120150SE +/- 2.68, N = 3SE +/- 0.93, N = 3SE +/- 1.98, N = 3SE +/- 2.30, N = 3155.69156.97157.42158.07

Apple M1

Processor: VirtualApple @ 2.40GHz (8 Cores), Motherboard: Apple Mac mini, Memory: 8GB, Disk: 229GB, Graphics: Apple M1, Monitor: DELL P2415Q

OS: macOS 11.0.1, Kernel: 20.1.0 (x86_64), OpenCL: OpenCL 1.2 (Oct 29 2020 19:50:08), Compiler: GCC 12.0.0 + Clang 12.0.0 + Xcode 12.2, File-System: APFS, Screen Resolution: 3840x2160

Environment Notes: XPC_FLAGS=0x0
Python Notes: Python 2.7.16 + Python 3.9.0

Testing initiated at 20 December 2020 14:49 by user michaellarabel.

Apple M1 macOS 11.1

Environment Notes: XPC_FLAGS=0x0
Python Notes: Python 2.7.16 + Python 3.9.0

Testing initiated at 21 December 2020 06:46 by user michaellarabel.

Apple M1 Silicon

Environment Notes: XPC_FLAGS=0x0
Python Notes: Python 2.7.16 + Python 3.9.0

Testing initiated at 21 December 2020 10:38 by user michaellarabel.

M1 Apple Silicon

Processor: Apple M1 @ 2.40GHz (8 Cores), Motherboard: Apple Mac mini, Memory: 8GB, Disk: 229GB, Graphics: Apple M1, Monitor: DELL P2415Q

OS: macOS 11.1, Kernel: 20.2.0 (x86_64), OpenCL: OpenCL 1.2 (Nov 23 2020 03:06:15), Compiler: GCC 12.0.0 + Clang 12.0.0 + Xcode 12.3, File-System: APFS, Screen Resolution: 3840x2160

Environment Notes: XPC_FLAGS=0x0
Python Notes: Python 2.7.16 + Python 3.9.0

Testing initiated at 21 December 2020 14:07 by user michaellarabel.