Ampere Altra System76 Thelio Astra

Benchmarks for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2410198-NE-AMPEREALT58
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

Limit displaying results to tests within:

Timed Code Compilation 4 Tests
C/C++ Compiler Tests 4 Tests
CPU Massive 7 Tests
Creator Workloads 3 Tests
HPC - High Performance Computing 11 Tests
Machine Learning 7 Tests
Molecular Dynamics 2 Tests
MPI Benchmarks 3 Tests
Multi-Core 11 Tests
OpenMPI Tests 3 Tests
Programmer / Developer System Benchmarks 5 Tests
Python Tests 5 Tests
Scientific Computing 3 Tests
Server 2 Tests
Server CPU Tests 6 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
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
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
System76 Thelio Astra
October 17
  12 Hours, 15 Minutes
System76 Thelio Astra Altra
October 18
  13 Hours, 18 Minutes
Invert Hiding All Results Option
  12 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):


Ampere Altra System76 Thelio AstraOpenBenchmarking.orgPhoronix Test SuiteARMv8 Neoverse-N1 @ 3.00GHz (128 Cores)System76 Thelio Astra (3.02 BIOS)Ampere Computing LLC Altra PCI Root Complex A8 x 32GB DDR4-3200MT/s Micron 18ASF4G72PDZ-3G2F11024GB KINGSTON SKC3000S1024GNVIDIA RTX A400/PCIe 4GBNVIDIA Device 2291DELL P2415Q2 x Intel X550 + Intel I210Ubuntu 24.046.8.0-47-generic-64k (aarch64)GNOME Shell 46.0X Server 1.21.1.11NVIDIA 550.107.024.6.0GCC 13.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionAmpere Altra System76 Thelio Astra BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-dIwDw0/gcc-13-13.2.0/debian/tmp-nvptx/usr --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto --without-cuda-driver -v - Scaling Governor: cppc_cpufreq schedutil (Boost: Disabled)- GPU Compute Cores: 768- Python 3.12.3- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of CSV2 BHB + srbds: Not affected + tsx_async_abort: Not affected

System76 Thelio Astra vs. System76 Thelio Astra Altra ComparisonPhoronix Test SuiteBaseline+7.2%+7.2%+14.4%+14.4%+21.6%+21.6%+28.8%+28.8%28.9%5.2%5.1%4.4%4.1%2.2%Read While WritingIP Shapes 1D - CPU8%D.B.s - CPU6.9%ggml-medium.en - 2.S.o.t.URead While WritingFP32MobileNetV3LargeR.R.W.R4.4%CPU - 512 - ResNet-50Rand Read3.8%QS8MobileNetV23.8%Video3.7%FP16MobileNetV13.6%FP16MobileNetV3Small3.3%R.N.N.I - CPU2.9%ggml-small.en - 2.S.o.t.U2.6%DNN - D.N.N2.4%Rand Read2.4%R.R.W.R2.4%Features 2DR.N.N.T - CPU2.1%Object Detection2%SpeedboneDNNoneDNNWhisper.cppRocksDBXNNPACKRocksDBPyTorchRocksDBXNNPACKOpenCVXNNPACKXNNPACKoneDNNWhisper.cppOpenCVSpeedbSpeedbOpenCVoneDNNOpenCVSystem76 Thelio AstraSystem76 Thelio Astra Altra

Ampere Altra System76 Thelio Astraepoch: Conenumpy: mnn: nasnetmnn: mobilenetV3mnn: squeezenetv1.1mnn: resnet-v2-50blender: Fishy Cat - CPU-Onlymnn: SqueezeNetV1.0mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3opencv: DNN - Deep Neural Networkopencv: Features 2Dwarpx: Plasma Accelerationopencv: Object Detectionopencv: Coreopencv: Image Processingopencv: Stitchingopencv: Videopytorch: CPU - 256 - ResNet-50pytorch: CPU - 512 - ResNet-50whisper-cpp: ggml-base.en - 2016 State of the Unionwhisper-cpp: ggml-small.en - 2016 State of the Unionwhisper-cpp: ggml-medium.en - 2016 State of the Unionxnnpack: FP32MobileNetV1xnnpack: FP32MobileNetV2xnnpack: FP32MobileNetV3Largexnnpack: FP32MobileNetV3Smallxnnpack: FP16MobileNetV1xnnpack: FP16MobileNetV2xnnpack: FP16MobileNetV3Largexnnpack: FP16MobileNetV3Smallxnnpack: QS8MobileNetV2gromacs: MPI CPU - water_GMX50_bareblender: Pabellon Barcelona - CPU-Onlyblender: Barbershop - CPU-Onlyhpcg: 104 104 104 - 60onednn: Convolution Batch Shapes Auto - CPUonednn: Deconvolution Batch shapes_1d - CPUonednn: Deconvolution Batch shapes_3d - CPUonednn: IP Shapes 1D - CPUonednn: IP Shapes 3D - CPUlitert: NASNet Mobilelitert: Mobilenet Quantlitert: SqueezeNetblender: BMW27 - CPU-Onlylitert: Inception V4litert: Inception ResNet V2litert: DeepLab V3litert: Quantized COCO SSD MobileNet v1onednn: Recurrent Neural Network Training - CPUonednn: Recurrent Neural Network Inference - CPUmt-dgemm: Sustained Floating-Point Ratelitert: Mobilenet Floatblender: Classroom - CPU-Onlyminife: Smallcoremark: CoreMark Size 666 - Iterations Per Secondjohn-the-ripper: MD5john-the-ripper: Blowfishjohn-the-ripper: HMAC-SHA512john-the-ripper: bcryptjohn-the-ripper: WPA PSKbuild-llvm: Ninjabuild-llvm: Unix Makefilesbuild-linux-kernel: defconfigbuild-linux-kernel: allmodconfigc-ray: 1080p - 16c-ray: 4K - 16c-ray: 5K - 16build-godot: Time To Compilebuild-nodejs: Time To Compilesrsran: PUSCH Processor Benchmark, Throughput Totalsrsran: PDSCH Processor Benchmark, Throughput Totalspeedb: Read While Writingspeedb: Read Rand Write Randspeedb: Update Randrocksdb: Rand Readrocksdb: Read While Writingrocksdb: Read Rand Write Randrocksdb: Update Randwarpx: Uniform Plasmaspeedb: Rand ReadSystem76 Thelio AstraSystem76 Thelio Astra Altra346.84363.539.9891.5942.37314.10664.484.4012.2201.97619.173588809127047.64528650990331304642068582498341410524.2923.56398.21058550.793151111.580621935259442892689117921033268238122274.497140.33357.6421.42524.8820125.07627.389888.001465.2001625510.31376.462395.2636.0927987.628987.63373.933009.664062.313125.371874.1688971899.8070.5824196.22781173.960094121766710133068362667101387109565260.084416.47682.692318.3076.90426.48047.034228.308510.1371525.513753.31044213211875391739974920603579663143134859921385638.96806852474967015366.8510.0391.5762.35414.31065.084.3942.2421.94219.369602928933347.653420491010361284932103712478491463024.2324.52405.39651564.899791056.782401943261041082705122120933304246023114.574140.21357.0521.41874.9378925.32257.900928.638655.1082525569.71368.652363.3035.8227845.629027.73372.082964.534148.633215.521875.1360771927.0570.5324201.42793203.067052121966710097268879333100940110061257.869415.57883.098318.0326.90226.42746.975229.783511.0511504.813707.113457221116022717466347415689510160082129217821735238.51536585463900465OpenBenchmarking.org

Epoch

OpenBenchmarking.orgSeconds, Fewer Is BetterEpoch 4.19.4Epoch3D Deck: ConeSystem76 Thelio Astra80160240320400SE +/- 1.61, N = 3346.841. (F9X) gfortran options: -O3 -std=f2003 -Jobj -lsdf -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

Epoch3D Deck: Cone

System76 Thelio Astra Altra: The test quit with a non-zero exit status. E: SDF error: SDF_ERR_UNKNOWN

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkSystem76 Thelio Astra AltraSystem76 Thelio Astra80160240320400SE +/- 1.54, N = 3SE +/- 2.61, N = 3366.85363.53

Mobile Neural Network

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: nasnetSystem76 Thelio AstraSystem76 Thelio Astra Altra3691215SE +/- 0.038, N = 3SE +/- 0.021, N = 39.98910.039MIN: 9.69 / MAX: 11.07MIN: 9.76 / MAX: 11.231. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: mobilenetV3System76 Thelio Astra AltraSystem76 Thelio Astra0.35870.71741.07611.43481.7935SE +/- 0.032, N = 3SE +/- 0.037, N = 31.5761.594MIN: 1.38 / MAX: 2.66MIN: 1.39 / MAX: 2.581. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: squeezenetv1.1System76 Thelio Astra AltraSystem76 Thelio Astra0.53391.06781.60172.13562.6695SE +/- 0.008, N = 3SE +/- 0.004, N = 32.3542.373MIN: 2.18 / MAX: 5.04MIN: 2.25 / MAX: 3.721. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: resnet-v2-50System76 Thelio AstraSystem76 Thelio Astra Altra48121620SE +/- 0.02, N = 3SE +/- 0.35, N = 314.1114.31MIN: 13.69 / MAX: 16.42MIN: 13.48 / MAX: 17.961. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0.2Blend File: Fishy Cat - Compute: CPU-OnlySystem76 Thelio AstraSystem76 Thelio Astra Altra1530456075SE +/- 0.11, N = 3SE +/- 0.27, N = 364.4865.08

Mobile Neural Network

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: SqueezeNetV1.0System76 Thelio Astra AltraSystem76 Thelio Astra0.99021.98042.97063.96084.951SE +/- 0.030, N = 3SE +/- 0.029, N = 34.3944.401MIN: 4.2 / MAX: 6.39MIN: 4.19 / MAX: 6.491. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: MobileNetV2_224System76 Thelio AstraSystem76 Thelio Astra Altra0.50451.0091.51352.0182.5225SE +/- 0.007, N = 3SE +/- 0.014, N = 32.2202.242MIN: 2.13 / MAX: 3.81MIN: 2.13 / MAX: 3.861. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: mobilenet-v1-1.0System76 Thelio Astra AltraSystem76 Thelio Astra0.44460.88921.33381.77842.223SE +/- 0.005, N = 3SE +/- 0.011, N = 31.9421.976MIN: 1.79 / MAX: 3.63MIN: 1.86 / MAX: 3.511. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: inception-v3System76 Thelio AstraSystem76 Thelio Astra Altra510152025SE +/- 0.05, N = 3SE +/- 0.03, N = 319.1719.37MIN: 18.67 / MAX: 21.51MIN: 18.94 / MAX: 21.811. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: DNN - Deep Neural NetworkSystem76 Thelio AstraSystem76 Thelio Astra Altra13K26K39K52K65KSE +/- 1485.93, N = 12SE +/- 717.84, N = 458880602921. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Features 2DSystem76 Thelio Astra AltraSystem76 Thelio Astra20K40K60K80K100KSE +/- 2087.36, N = 12SE +/- 1679.80, N = 1289333912701. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

WarpX

OpenBenchmarking.orgSeconds, Fewer Is BetterWarpX 24.10Input: Plasma AccelerationSystem76 Thelio AstraSystem76 Thelio Astra Altra1122334455SE +/- 0.11, N = 3SE +/- 0.09, N = 347.6547.651. (CXX) g++ options: -O3

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Object DetectionSystem76 Thelio AstraSystem76 Thelio Astra Altra20K40K60K80K100KSE +/- 865.84, N = 7SE +/- 793.40, N = 9990331010361. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: CoreSystem76 Thelio Astra AltraSystem76 Thelio Astra30K60K90K120K150KSE +/- 482.28, N = 3SE +/- 1455.59, N = 41284931304641. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Image ProcessingSystem76 Thelio AstraSystem76 Thelio Astra Altra50K100K150K200K250KSE +/- 2984.28, N = 3SE +/- 1895.00, N = 122068582103711. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: StitchingSystem76 Thelio Astra AltraSystem76 Thelio Astra50K100K150K200K250KSE +/- 1011.33, N = 3SE +/- 2453.89, N = 32478492498341. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: VideoSystem76 Thelio AstraSystem76 Thelio Astra Altra3K6K9K12K15KSE +/- 146.61, N = 15SE +/- 169.59, N = 414105146301. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 256 - Model: ResNet-50System76 Thelio AstraSystem76 Thelio Astra Altra612182430SE +/- 0.06, N = 3SE +/- 0.34, N = 324.2924.23MIN: 11.58 / MAX: 25.7MIN: 11.28 / MAX: 26.16

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 512 - Model: ResNet-50System76 Thelio Astra AltraSystem76 Thelio Astra612182430SE +/- 0.33, N = 3SE +/- 0.13, N = 324.5223.56MIN: 12.59 / MAX: 26.37MIN: 11.24 / MAX: 24.94

Whisper.cpp

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.6.2Model: ggml-base.en - Input: 2016 State of the UnionSystem76 Thelio AstraSystem76 Thelio Astra Altra90180270360450SE +/- 2.93, N = 3SE +/- 1.58, N = 3398.21405.401. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -mcpu=native

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.6.2Model: ggml-small.en - Input: 2016 State of the UnionSystem76 Thelio AstraSystem76 Thelio Astra Altra120240360480600SE +/- 24.91, N = 9SE +/- 23.23, N = 9550.79564.901. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -mcpu=native

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.6.2Model: ggml-medium.en - Input: 2016 State of the UnionSystem76 Thelio Astra AltraSystem76 Thelio Astra2004006008001000SE +/- 42.64, N = 9SE +/- 15.29, N = 31056.781111.581. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -mcpu=native

XNNPACK

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV1System76 Thelio AstraSystem76 Thelio Astra Altra400800120016002000SE +/- 22.19, N = 3SE +/- 18.36, N = 3193519431. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV2System76 Thelio AstraSystem76 Thelio Astra Altra6001200180024003000SE +/- 22.61, N = 3SE +/- 26.06, N = 3259426101. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV3LargeSystem76 Thelio Astra AltraSystem76 Thelio Astra9001800270036004500SE +/- 73.96, N = 3SE +/- 50.89, N = 3410842891. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV3SmallSystem76 Thelio AstraSystem76 Thelio Astra Altra6001200180024003000SE +/- 47.96, N = 3SE +/- 12.91, N = 3268927051. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV1System76 Thelio AstraSystem76 Thelio Astra Altra30060090012001500SE +/- 24.09, N = 3SE +/- 23.78, N = 3117912211. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV2System76 Thelio Astra AltraSystem76 Thelio Astra5001000150020002500SE +/- 28.10, N = 3SE +/- 43.27, N = 3209321031. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV3LargeSystem76 Thelio AstraSystem76 Thelio Astra Altra7001400210028003500SE +/- 6.39, N = 3SE +/- 55.56, N = 3326833041. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV3SmallSystem76 Thelio AstraSystem76 Thelio Astra Altra5001000150020002500SE +/- 34.36, N = 3SE +/- 73.70, N = 3238124601. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: QS8MobileNetV2System76 Thelio AstraSystem76 Thelio Astra Altra5001000150020002500SE +/- 11.10, N = 3SE +/- 61.16, N = 3222723111. (CXX) g++ options: -O3 -lrt -lm

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2024Implementation: MPI CPU - Input: water_GMX50_bareSystem76 Thelio Astra AltraSystem76 Thelio Astra1.02922.05843.08764.11685.146SE +/- 0.013, N = 3SE +/- 0.064, N = 34.5744.4971. (CXX) g++ options: -O3 -lm

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0.2Blend File: Pabellon Barcelona - Compute: CPU-OnlySystem76 Thelio Astra AltraSystem76 Thelio Astra306090120150SE +/- 0.36, N = 3SE +/- 0.75, N = 3140.21140.33

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0.2Blend File: Barbershop - Compute: CPU-OnlySystem76 Thelio Astra AltraSystem76 Thelio Astra80160240320400SE +/- 0.30, N = 3SE +/- 0.51, N = 3357.05357.64

High Performance Conjugate Gradient

HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 104 104 104 - RT: 60System76 Thelio AstraSystem76 Thelio Astra Altra510152025SE +/- 0.01, N = 3SE +/- 0.00, N = 321.4321.421. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Convolution Batch Shapes Auto - Engine: CPUSystem76 Thelio AstraSystem76 Thelio Astra Altra1.1112.2223.3334.4445.555SE +/- 0.02318, N = 7SE +/- 0.03469, N = 124.882014.93789MIN: 4.04MIN: 4.071. (CXX) g++ options: -O3 -march=native -fopenmp -mcpu=generic -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Deconvolution Batch shapes_1d - Engine: CPUSystem76 Thelio AstraSystem76 Thelio Astra Altra612182430SE +/- 0.04, N = 3SE +/- 0.23, N = 725.0825.32MIN: 20.08MIN: 19.771. (CXX) g++ options: -O3 -march=native -fopenmp -mcpu=generic -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Deconvolution Batch shapes_3d - Engine: CPUSystem76 Thelio AstraSystem76 Thelio Astra Altra246810SE +/- 0.45769, N = 15SE +/- 0.29556, N = 157.389887.90092MIN: 3MIN: 2.991. (CXX) g++ options: -O3 -march=native -fopenmp -mcpu=generic -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: IP Shapes 1D - Engine: CPUSystem76 Thelio AstraSystem76 Thelio Astra Altra246810SE +/- 0.10253, N = 15SE +/- 0.07882, N = 158.001468.63865MIN: 3.75MIN: 3.441. (CXX) g++ options: -O3 -march=native -fopenmp -mcpu=generic -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: IP Shapes 3D - Engine: CPUSystem76 Thelio Astra AltraSystem76 Thelio Astra1.172.343.514.685.85SE +/- 0.12533, N = 15SE +/- 0.13331, N = 155.108255.20016MIN: 1.97MIN: 1.961. (CXX) g++ options: -O3 -march=native -fopenmp -mcpu=generic -fPIC -pie -ldl -lpthread

LiteRT

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: NASNet MobileSystem76 Thelio AstraSystem76 Thelio Astra Altra5K10K15K20K25KSE +/- 11.69, N = 3SE +/- 247.26, N = 325510.325569.7

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Mobilenet QuantSystem76 Thelio Astra AltraSystem76 Thelio Astra30060090012001500SE +/- 9.82, N = 3SE +/- 14.30, N = 41368.651376.46

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: SqueezeNetSystem76 Thelio Astra AltraSystem76 Thelio Astra5001000150020002500SE +/- 5.44, N = 3SE +/- 21.43, N = 32363.302395.26

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0.2Blend File: BMW27 - Compute: CPU-OnlySystem76 Thelio Astra AltraSystem76 Thelio Astra816243240SE +/- 0.15, N = 3SE +/- 0.35, N = 335.8236.09

LiteRT

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Inception V4System76 Thelio Astra AltraSystem76 Thelio Astra6K12K18K24K30KSE +/- 149.53, N = 3SE +/- 145.12, N = 327845.627987.6

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Inception ResNet V2System76 Thelio AstraSystem76 Thelio Astra Altra6K12K18K24K30KSE +/- 78.11, N = 3SE +/- 184.20, N = 328987.629027.7

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: DeepLab V3System76 Thelio Astra AltraSystem76 Thelio Astra7001400210028003500SE +/- 20.38, N = 3SE +/- 31.60, N = 33372.083373.93

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Quantized COCO SSD MobileNet v1System76 Thelio Astra AltraSystem76 Thelio Astra6001200180024003000SE +/- 17.01, N = 3SE +/- 2.79, N = 32964.533009.66

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Recurrent Neural Network Training - Engine: CPUSystem76 Thelio AstraSystem76 Thelio Astra Altra9001800270036004500SE +/- 7.41, N = 3SE +/- 13.08, N = 34062.314148.63MIN: 3598.84MIN: 3579.881. (CXX) g++ options: -O3 -march=native -fopenmp -mcpu=generic -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Recurrent Neural Network Inference - Engine: CPUSystem76 Thelio AstraSystem76 Thelio Astra Altra7001400210028003500SE +/- 21.23, N = 15SE +/- 30.66, N = 33125.373215.52MIN: 2673.31MIN: 2717.061. (CXX) g++ options: -O3 -march=native -fopenmp -mcpu=generic -fPIC -pie -ldl -lpthread

ACES DGEMM

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateSystem76 Thelio Astra AltraSystem76 Thelio Astra400800120016002000SE +/- 4.30, N = 3SE +/- 3.52, N = 31875.141874.171. (CC) gcc options: -ffast-math -O3 -fopenmp -lopenblas

LiteRT

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Mobilenet FloatSystem76 Thelio AstraSystem76 Thelio Astra Altra400800120016002000SE +/- 20.31, N = 3SE +/- 12.15, N = 31899.801927.05

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0.2Blend File: Classroom - Compute: CPU-OnlySystem76 Thelio Astra AltraSystem76 Thelio Astra1632486480SE +/- 0.16, N = 3SE +/- 0.24, N = 370.5370.58

miniFE

MiniFE Finite Element is an application for unstructured implicit finite element codes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgCG Mflops, More Is BetterminiFE 2.2Problem Size: SmallSystem76 Thelio Astra AltraSystem76 Thelio Astra5K10K15K20K25KSE +/- 20.09, N = 4SE +/- 10.46, N = 424201.424196.21. (CXX) g++ options: -O3 -fopenmp -lmpi_cxx -lmpi

Coremark

This is a test of EEMBC CoreMark processor benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondSystem76 Thelio Astra AltraSystem76 Thelio Astra600K1200K1800K2400K3000KSE +/- 1584.02, N = 3SE +/- 7741.41, N = 32793203.072781173.961. (CC) gcc options: -O2 -lrt" -lrt

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: MD5System76 Thelio Astra AltraSystem76 Thelio Astra300K600K900K1200K1500KSE +/- 5174.72, N = 3SE +/- 3929.94, N = 3121966712176671. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishSystem76 Thelio AstraSystem76 Thelio Astra Altra20K40K60K80K100KSE +/- 264.10, N = 3SE +/- 126.74, N = 31013301009721. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: HMAC-SHA512System76 Thelio Astra AltraSystem76 Thelio Astra15M30M45M60M75MSE +/- 457404.76, N = 3SE +/- 967418.00, N = 1568879333683626671. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: bcryptSystem76 Thelio AstraSystem76 Thelio Astra Altra20K40K60K80K100KSE +/- 94.05, N = 3SE +/- 259.62, N = 31013871009401. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: WPA PSKSystem76 Thelio Astra AltraSystem76 Thelio Astra20K40K60K80K100KSE +/- 612.62, N = 3SE +/- 738.00, N = 31100611095651. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

Timed LLVM Compilation

This test times how long it takes to compile/build the LLVM compiler stack. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: NinjaSystem76 Thelio Astra AltraSystem76 Thelio Astra60120180240300SE +/- 0.98, N = 3SE +/- 1.59, N = 3257.87260.08

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Unix MakefilesSystem76 Thelio Astra AltraSystem76 Thelio Astra90180270360450SE +/- 0.62, N = 3SE +/- 1.95, N = 3415.58416.48

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: defconfigSystem76 Thelio AstraSystem76 Thelio Astra Altra20406080100SE +/- 0.99, N = 4SE +/- 1.14, N = 382.6983.10

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: allmodconfigSystem76 Thelio Astra AltraSystem76 Thelio Astra70140210280350SE +/- 1.44, N = 3SE +/- 1.44, N = 3318.03318.31

C-Ray

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 2.0Resolution: 1080p - Rays Per Pixel: 16System76 Thelio Astra AltraSystem76 Thelio Astra246810SE +/- 0.001, N = 6SE +/- 0.002, N = 66.9026.9041. (CC) gcc options: -lpthread -lm

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 2.0Resolution: 4K - Rays Per Pixel: 16System76 Thelio Astra AltraSystem76 Thelio Astra612182430SE +/- 0.02, N = 3SE +/- 0.03, N = 326.4326.481. (CC) gcc options: -lpthread -lm

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 2.0Resolution: 5K - Rays Per Pixel: 16System76 Thelio Astra AltraSystem76 Thelio Astra1122334455SE +/- 0.02, N = 3SE +/- 0.04, N = 346.9847.031. (CC) gcc options: -lpthread -lm

Timed Godot Game Engine Compilation

This test times how long it takes to compile the Godot Game Engine. Godot is a popular, open-source, cross-platform 2D/3D game engine and is built using the SCons build system and targeting the X11 platform. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 4.0Time To CompileSystem76 Thelio AstraSystem76 Thelio Astra Altra50100150200250SE +/- 0.16, N = 3SE +/- 0.85, N = 3228.31229.78

Timed Node.js Compilation

This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 21.7.2Time To CompileSystem76 Thelio AstraSystem76 Thelio Astra Altra110220330440550SE +/- 0.54, N = 3SE +/- 1.15, N = 3510.14511.05

srsRAN Project

srsRAN Project is a complete ORAN-native 5G RAN solution created by Software Radio Systems (SRS). The srsRAN Project radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PUSCH Processor Benchmark, Throughput TotalSystem76 Thelio AstraSystem76 Thelio Astra Altra30060090012001500SE +/- 10.69, N = 3SE +/- 3.59, N = 31525.51504.8MIN: 901.4 / MAX: 1546.9MIN: 885.6 / MAX: 15121. (CXX) g++ options: -O3 -fno-trapping-math -fno-math-errno -ldl

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PDSCH Processor Benchmark, Throughput TotalSystem76 Thelio AstraSystem76 Thelio Astra Altra3K6K9K12K15KSE +/- 46.37, N = 3SE +/- 72.39, N = 313753.313707.11. (CXX) g++ options: -O3 -fno-trapping-math -fno-math-errno -ldl

Speedb

Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read While WritingSystem76 Thelio Astra AltraSystem76 Thelio Astra3M6M9M12M15MSE +/- 753903.88, N = 15SE +/- 164058.99, N = 1513457221104421321. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read Random Write RandomSystem76 Thelio AstraSystem76 Thelio Astra Altra300K600K900K1200K1500KSE +/- 8893.20, N = 11SE +/- 7547.70, N = 3118753911602271. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Update RandomSystem76 Thelio Astra AltraSystem76 Thelio Astra40K80K120K160K200KSE +/- 1456.90, N = 3SE +/- 356.29, N = 31746631739971. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

RocksDB

This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random ReadSystem76 Thelio AstraSystem76 Thelio Astra Altra110M220M330M440M550MSE +/- 3764966.49, N = 15SE +/- 6329660.21, N = 34920603574741568951. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read While WritingSystem76 Thelio Astra AltraSystem76 Thelio Astra2M4M6M8M10MSE +/- 84686.88, N = 3SE +/- 70965.71, N = 31016008296631431. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read Random Write RandomSystem76 Thelio AstraSystem76 Thelio Astra Altra300K600K900K1200K1500KSE +/- 12803.99, N = 3SE +/- 9460.89, N = 3134859912921781. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Update RandomSystem76 Thelio Astra AltraSystem76 Thelio Astra50K100K150K200K250KSE +/- 1778.60, N = 3SE +/- 1913.79, N = 152173522138561. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

WarpX

OpenBenchmarking.orgSeconds, Fewer Is BetterWarpX 24.10Input: Uniform PlasmaSystem76 Thelio Astra AltraSystem76 Thelio Astra918273645SE +/- 0.31, N = 3SE +/- 0.32, N = 938.5238.971. (CXX) g++ options: -O3

Speedb

Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random ReadSystem76 Thelio AstraSystem76 Thelio Astra Altra100M200M300M400M500MSE +/- 4696121.03, N = 15SE +/- 4679221.79, N = 154749670154639004651. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringSystem76 Thelio AstraSystem76 Thelio Astra Altra50100150200250Min: 23.31 / Avg: 74.86 / Max: 250.59Min: 23.78 / Avg: 138.85 / Max: 252.32

CPU Temperature Monitor

OpenBenchmarking.orgCelsiusCPU Temperature MonitorPhoronix Test Suite System MonitoringSystem76 Thelio AstraSystem76 Thelio Astra Altra1530456075Min: 43 / Avg: 51.78 / Max: 77Min: 43 / Avg: 61.05 / Max: 77

GPU Temperature Monitor

OpenBenchmarking.orgCelsiusGPU Temperature MonitorPhoronix Test Suite System MonitoringSystem76 Thelio AstraSystem76 Thelio Astra Altra918273645Min: 34 / Avg: 36.14 / Max: 41Min: 34 / Avg: 36.77 / Max: 42

Drive Temperature (nvme0n1) Monitor

OpenBenchmarking.orgCelsiusDrive Temperature (nvme0n1) MonitorPhoronix Test Suite System MonitoringSystem76 Thelio Astra AltraSystem76 Thelio Astra816243240Min: 24.85 / Avg: 27.9 / Max: 39.85Min: 25.85 / Avg: 30.48 / Max: 38.85

Meta Performance Per Watts

OpenBenchmarking.orgPerformance Per Watts, More Is BetterMeta Performance Per WattsPerformance Per WattsSystem76 Thelio Astra Altra16K32K48K64K80K73720.34

87 Results Shown

Epoch
Numpy Benchmark
Mobile Neural Network:
  nasnet
  mobilenetV3
  squeezenetv1.1
  resnet-v2-50
Blender
Mobile Neural Network:
  SqueezeNetV1.0
  MobileNetV2_224
  mobilenet-v1-1.0
  inception-v3
OpenCV:
  DNN - Deep Neural Network
  Features 2D
WarpX
OpenCV:
  Object Detection
  Core
  Image Processing
  Stitching
  Video
PyTorch:
  CPU - 256 - ResNet-50
  CPU - 512 - ResNet-50
Whisper.cpp:
  ggml-base.en - 2016 State of the Union
  ggml-small.en - 2016 State of the Union
  ggml-medium.en - 2016 State of the Union
XNNPACK:
  FP32MobileNetV1
  FP32MobileNetV2
  FP32MobileNetV3Large
  FP32MobileNetV3Small
  FP16MobileNetV1
  FP16MobileNetV2
  FP16MobileNetV3Large
  FP16MobileNetV3Small
  QS8MobileNetV2
GROMACS
Blender:
  Pabellon Barcelona - CPU-Only
  Barbershop - CPU-Only
High Performance Conjugate Gradient
oneDNN:
  Convolution Batch Shapes Auto - CPU
  Deconvolution Batch shapes_1d - CPU
  Deconvolution Batch shapes_3d - CPU
  IP Shapes 1D - CPU
  IP Shapes 3D - CPU
LiteRT:
  NASNet Mobile
  Mobilenet Quant
  SqueezeNet
Blender
LiteRT:
  Inception V4
  Inception ResNet V2
  DeepLab V3
  Quantized COCO SSD MobileNet v1
oneDNN:
  Recurrent Neural Network Training - CPU
  Recurrent Neural Network Inference - CPU
ACES DGEMM
LiteRT
Blender
miniFE
Coremark
John The Ripper:
  MD5
  Blowfish
  HMAC-SHA512
  bcrypt
  WPA PSK
Timed LLVM Compilation:
  Ninja
  Unix Makefiles
Timed Linux Kernel Compilation:
  defconfig
  allmodconfig
C-Ray:
  1080p - 16
  4K - 16
  5K - 16
Timed Godot Game Engine Compilation
Timed Node.js Compilation
srsRAN Project:
  PUSCH Processor Benchmark, Throughput Total
  PDSCH Processor Benchmark, Throughput Total
Speedb:
  Read While Writing
  Read Rand Write Rand
  Update Rand
RocksDB:
  Rand Read
  Read While Writing
  Read Rand Write Rand
  Update Rand
WarpX
Speedb
CPU Power Consumption Monitor:
  Phoronix Test Suite System Monitoring:
    Watts
    Celsius
    Celsius
    Celsius
  Performance Per Watts:
    Performance Per Watts