ddd

Tests for a future article. Apple M2 testing with a Apple MacBook Air (13 h M2 2022) and llvmpipe on Arch rolling 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 2311232-NE-DDD00616700
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
Performance Per
Dollar
Date
Run
  Test
  Duration
a
November 22 2023
  6 Hours, 46 Minutes
b
November 23 2023
  6 Hours, 47 Minutes
Invert Behavior (Only Show Selected Data)
  6 Hours, 46 Minutes
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):

a

Compiler Notes: --build=aarch64-unknown-linux-gnu --disable-libssp --disable-libstdcxx-pch --disable-multilib --disable-werror --enable-__cxa_atexit --enable-bootstrap --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++ --enable-lto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-unknown-linux-gnu --mandir=/usr/share/man --with-arch=armv8-a --with-linker-hash-style=gnu
Processor Notes: Scaling Governor: apple-cpufreq schedutil (Boost: Enabled)
Java Notes: OpenJDK Runtime Environment (build 11.0.19+7)
Python Notes: Python 3.11.3
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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

b

Processor: Apple M2 @ 2.42GHz (4 Cores / 8 Threads), Motherboard: Apple MacBook Air (13 h M2 2022), Chipset: Apple Silicon, Memory: 8GB, Disk: 251GB APPLE SSD AP0256Z + 2 x 0GB APPLE SSD AP0256Z, Graphics: llvmpipe, Network: Broadcom Device 4433 + Broadcom BRCM4387 Bluetooth

OS: Arch rolling, Kernel: 6.3.0-asahi-13-1-ARCH (aarch64), Desktop: KDE Plasma 5.27.6, Display Server: X Server 1.21.1.8, OpenGL: 4.5 Mesa 23.1.3 (LLVM 15.0.7 128 bits), Compiler: GCC 12.1.0 + Clang 15.0.7, File-System: ext4, Screen Resolution: 2560x1600

dddOpenBenchmarking.orgPhoronix Test SuiteApple M2 @ 2.42GHz (4 Cores / 8 Threads)Apple MacBook Air (13 h M2 2022)Apple Silicon8GB251GB APPLE SSD AP0256Z + 2 x 0GB APPLE SSD AP0256ZllvmpipeBroadcom Device 4433 + Broadcom BRCM4387 BluetoothArch rolling6.3.0-asahi-13-1-ARCH (aarch64)KDE Plasma 5.27.6X Server 1.21.1.84.5 Mesa 23.1.3 (LLVM 15.0.7 128 bits)GCC 12.1.0 + Clang 15.0.7ext42560x1600ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionDdd BenchmarksSystem Logs- --build=aarch64-unknown-linux-gnu --disable-libssp --disable-libstdcxx-pch --disable-multilib --disable-werror --enable-__cxa_atexit --enable-bootstrap --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++ --enable-lto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-unknown-linux-gnu --mandir=/usr/share/man --with-arch=armv8-a --with-linker-hash-style=gnu - Scaling Governor: apple-cpufreq schedutil (Boost: Enabled)- OpenJDK Runtime Environment (build 11.0.19+7)- Python 3.11.3- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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

a vs. b ComparisonPhoronix Test SuiteBaseline+1.2%+1.2%+2.4%+2.4%+3.6%+3.6%+4.8%+4.8%2.1%CPU - 64 - Efficientnet_v2_l4.9%CPU - 64 - ResNet-1522.6%CPU - 256 - ResNet-152PyTorchPyTorchPyTorchab

dddpytorch: CPU - 64 - Efficientnet_v2_lpytorch: CPU - 64 - ResNet-152pytorch: CPU - 256 - ResNet-152pytorch: CPU - 64 - ResNet-50pytorch: CPU - 256 - Efficientnet_v2_lpytorch: CPU - 1 - ResNet-152ffmpeg: libx264 - Platformpytorch: CPU - 32 - ResNet-50ffmpeg: libx265 - Livepytorch: CPU - 512 - Efficientnet_v2_lffmpeg: libx265 - Platformpytorch: CPU - 16 - ResNet-152pytorch: CPU - 32 - ResNet-152pytorch: CPU - 512 - ResNet-152ffmpeg: libx264 - Video On Demandffmpeg: libx265 - Video On Demandpytorch: CPU - 256 - ResNet-50pytorch: CPU - 1 - ResNet-50ffmpeg: libx264 - Liveffmpeg: libx264 - Uploadpytorch: CPU - 32 - Efficientnet_v2_lpytorch: CPU - 16 - Efficientnet_v2_lpytorch: CPU - 1 - Efficientnet_v2_lpytorch: CPU - 512 - ResNet-50pytorch: CPU - 16 - ResNet-50ffmpeg: libx265 - Uploadjava-scimark2: Compositeab1.512.372.354.831.513.1454.544.8337.091.5120.622.272.332.3554.3620.574.796.31226.5013.921.511.510.574.764.7611.461.442.312.404.751.493.1154.084.7936.791.5020.732.282.342.3654.5120.524.806.32226.8313.941.511.510.574.764.7611.46OpenBenchmarking.org

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_lab0.33980.67961.01941.35921.6991.511.44MIN: 1.38 / MAX: 1.59MIN: 1.31 / MAX: 1.51

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-152ab0.53331.06661.59992.13322.66652.372.31MIN: 1.92 / MAX: 2.49MIN: 1.86 / MAX: 2.48

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-152ab0.541.081.622.162.72.352.40MIN: 1.89 / MAX: 2.52MIN: 1.95 / MAX: 2.52

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-50ab1.08682.17363.26044.34725.4344.834.75MIN: 3.59 / MAX: 5.16MIN: 3.61 / MAX: 5.06

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_lab0.33980.67961.01941.35921.6991.511.49MIN: 1.35 / MAX: 1.59MIN: 1.34 / MAX: 1.57

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-152ab0.70651.4132.11952.8263.53253.143.11MIN: 2.41 / MAX: 3.55MIN: 2.43 / MAX: 3.51

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx264 - Scenario: Platformab122436486054.5454.081. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-50ab1.08682.17363.26044.34725.4344.834.79MIN: 3.68 / MAX: 5.21MIN: 3.7 / MAX: 5.14

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: Liveab91827364537.0936.791. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_lab0.33980.67961.01941.35921.6991.511.50MIN: 0.79 / MAX: 1.6MIN: 1.34 / MAX: 1.58

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: Platformab51015202520.6220.731. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-152ab0.5131.0261.5392.0522.5652.272.28MIN: 1.88 / MAX: 2.4MIN: 1.89 / MAX: 2.43

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-152ab0.52651.0531.57952.1062.63252.332.34MIN: 1.93 / MAX: 2.49MIN: 1.93 / MAX: 2.49

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: ResNet-152ab0.5311.0621.5932.1242.6552.352.36MIN: 1.95 / MAX: 2.53MIN: 0.97 / MAX: 2.47

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx264 - Scenario: Video On Demandab122436486054.3654.511. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: Video On Demandab51015202520.5720.521. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-50ab1.082.163.244.325.44.794.80MIN: 3.46 / MAX: 5.14MIN: 3.73 / MAX: 5.18

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-50ab2468106.316.32MIN: 4.99 / MAX: 6.8MIN: 4.74 / MAX: 6.81

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx264 - Scenario: Liveab50100150200250226.50226.831. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx264 - Scenario: Uploadab4812162013.9213.941. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_lab0.33980.67961.01941.35921.6991.511.51MIN: 1.37 / MAX: 1.6MIN: 1.37 / MAX: 1.58

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_lab0.33980.67961.01941.35921.6991.511.51MIN: 1.37 / MAX: 1.59MIN: 1.35 / MAX: 1.6

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_lab0.12830.25660.38490.51320.64150.570.57MIN: 0.32 / MAX: 1.03MIN: 0.34 / MAX: 1.04

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: ResNet-50ab1.0712.1423.2134.2845.3554.764.76MIN: 3.66 / MAX: 5.19MIN: 3.77 / MAX: 5.11

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-50ab1.0712.1423.2134.2845.3554.764.76MIN: 3.56 / MAX: 5.13MIN: 3.76 / MAX: 5.1

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: Uploadab369121511.4611.461. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

Timed FFmpeg Compilation

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

Time To Compile

a: The test quit with a non-zero exit status. E: build-ffmpeg: line 2: cd: ffmpeg-6.1: No such file or directory

b: The test quit with a non-zero exit status. E: build-ffmpeg: line 2: cd: ffmpeg-6.1: No such file or directory

Java SciMark

This test runs the Java version of SciMark 2, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

Computational Test: Jacobi Successive Over-Relaxation

a: The test quit with a non-zero exit status.

b: The test quit with a non-zero exit status.

Computational Test: Dense LU Matrix Factorization

a: The test quit with a non-zero exit status.

b: The test quit with a non-zero exit status.

Computational Test: Sparse Matrix Multiply

a: The test quit with a non-zero exit status.

b: The test quit with a non-zero exit status.

Computational Test: Fast Fourier Transform

a: The test quit with a non-zero exit status.

b: The test quit with a non-zero exit status.

Computational Test: Monte Carlo

a: The test quit with a non-zero exit status.

b: The test quit with a non-zero exit status.

Computational Test: Composite

a: The test quit with a non-zero exit status. E: Error: Unable to access jarfile scimark-2.2.jar

b: The test quit with a non-zero exit status. E: Error: Unable to access jarfile scimark-2.2.jar

a

Compiler Notes: --build=aarch64-unknown-linux-gnu --disable-libssp --disable-libstdcxx-pch --disable-multilib --disable-werror --enable-__cxa_atexit --enable-bootstrap --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++ --enable-lto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-unknown-linux-gnu --mandir=/usr/share/man --with-arch=armv8-a --with-linker-hash-style=gnu
Processor Notes: Scaling Governor: apple-cpufreq schedutil (Boost: Enabled)
Java Notes: OpenJDK Runtime Environment (build 11.0.19+7)
Python Notes: Python 3.11.3
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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

Testing initiated at 22 November 2023 20:32 by user phoronix.

b

Processor: Apple M2 @ 2.42GHz (4 Cores / 8 Threads), Motherboard: Apple MacBook Air (13 h M2 2022), Chipset: Apple Silicon, Memory: 8GB, Disk: 251GB APPLE SSD AP0256Z + 2 x 0GB APPLE SSD AP0256Z, Graphics: llvmpipe, Network: Broadcom Device 4433 + Broadcom BRCM4387 Bluetooth

OS: Arch rolling, Kernel: 6.3.0-asahi-13-1-ARCH (aarch64), Desktop: KDE Plasma 5.27.6, Display Server: X Server 1.21.1.8, OpenGL: 4.5 Mesa 23.1.3 (LLVM 15.0.7 128 bits), Compiler: GCC 12.1.0 + Clang 15.0.7, File-System: ext4, Screen Resolution: 2560x1600

Compiler Notes: --build=aarch64-unknown-linux-gnu --disable-libssp --disable-libstdcxx-pch --disable-multilib --disable-werror --enable-__cxa_atexit --enable-bootstrap --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++ --enable-lto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-unknown-linux-gnu --mandir=/usr/share/man --with-arch=armv8-a --with-linker-hash-style=gnu
Processor Notes: Scaling Governor: apple-cpufreq schedutil (Boost: Enabled)
Java Notes: OpenJDK Runtime Environment (build 11.0.19+7)
Python Notes: Python 3.11.3
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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

Testing initiated at 23 November 2023 10:54 by user phoronix.