Cavium ThunderX 96-Core vs. Raptor Talos II POWER9

Tests being worked on by Michael Larabel 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 1803280-AR-TALOSARM280
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

Limit displaying results to tests within:

C/C++ Compiler Tests 8 Tests
CPU Massive 11 Tests
Creator Workloads 4 Tests
Cryptography 2 Tests
Encoding 2 Tests
HPC - High Performance Computing 4 Tests
Multi-Core 8 Tests
OpenCL 2 Tests
Programmer / Developer System Benchmarks 2 Tests
Python 2 Tests
Renderers 2 Tests
Server CPU Tests 9 Tests
Single-Threaded 2 Tests
Common Workstation Benchmarks 2 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

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable

Multi-Way Comparison

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
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Cavium ThunderX 96-Core
February 26 2018
 
Raptor Talos 2
March 28 2018
 
Invert Hiding All Results Option
 
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):


Cavium ThunderX 96-Core vs. Raptor Talos II POWER9ProcessorMotherboardMemoryDiskGraphicsNetworkAudioOSKernelDisplay DriverCompilerFile-SystemScreen ResolutionCavium ThunderX 96-CoreRaptor Talos 2Cavium ThunderX (96 Cores)FOXCONN C2U4N_MB (G31FB18A BIOS)4 x 32 GB DDR4-2133MHz 36ASF4G72PZ-2G3B1250GB Samsung SSD 850ASPEED ASPEED FamilyCavium THUNDERX Interface + Cavium THUNDERX BGXUbuntu 16.044.10.0-38-generic (aarch64)modesetting 1.18.4GCC 5.4.0 20160609ext4800x600POWER9 altivec supported @ 3.80GHz (64 Cores)PowerNV T2P9D01 REV 1.00262144MB500GB MAXTOR STM350063AMD Radeon Pro WX 7100 8192MBAMD EllesmereBroadcom Limited NetXtreme BCM5719 Gigabit PCIeDebian testing4.16.0-rc4 (ppc64le) 20180307amdgpu 1.4.0GCC 7.3.01024x768OpenBenchmarking.orgCompiler Details- Cavium ThunderX 96-Core: --build=aarch64-linux-gnu --disable-browser-plugin --disable-libquadmath --disable-werror --enable-checking=release --enable-clocale=gnu --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,ada,c++,java,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --target=aarch64-linux-gnu --with-arch-directory=aarch64 --with-default-libstdcxx-abi=new -v - Raptor Talos 2: --build=powerpc64le-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-multilib --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-secureplt --enable-shared --enable-targets=powerpcle-linux --enable-threads=posix --host=powerpc64le-linux-gnu --program-prefix=powerpc64le-linux-gnu- --target=powerpc64le-linux-gnu --with-cpu=power8 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-long-double-128 -v Python Details- Cavium ThunderX 96-Core: Python 2.7.12 + Python 3.5.2- Raptor Talos 2: Python 2.7.14+ + Python 3.6.5rc1Processor Details- Raptor Talos 2: Scaling Governor: powernv-cpufreq ondemand

Cavium ThunderX 96-Core vs. Raptor Talos 2 ComparisonPhoronix Test SuiteBaseline+390.1%+390.1%+780.2%+780.2%+1170.3%+1170.3%496.3%466.7%245.2%200.2%181.5%152.8%139.6%80.8%73.8%73.1%56.4%8%M.S.A2048 x 2048 - Total TimeTime To CompileWAV To MP3T.F.A.T.TT.F.A.T.TThroughput1560.3%Total TimeH.2.V.EOpenMP LavaMDC.S.TBlowfish11.9%OpenMP CUTCPTimed MAFFT AlignmentScikit-LearnAOBenchTimed Linux Kernel CompilationLAME MP3 EncodingPyBenchPyBenchJava JMHC-Rayx264Rodinia7-Zip CompressionJohn The RipperParboilCavium ThunderX 96-CoreRaptor Talos 2

Cavium ThunderX 96-Core vs. Raptor Talos II POWER9parboil: OpenMP CUTCProdinia: OpenMP LavaMDmafft: Multiple Sequence Alignmentjohn-the-ripper: Blowfishx264: H.264 Video Encodingcompress-7zip: Compress Speed Testbuild-linux-kernel: Time To Compilec-ray: Total Timeencode-mp3: WAV To MP3openssl: RSA 4096-bit Performancejava-jmh: Throughputpybench: Total For Average Test Timespybench: Total For Average Test Timesscikit-learn: aobench: 2048 x 2048 - Total TimeCavium ThunderX 96-CoreRaptor Talos 210.2166.5517.652874924.7751487218.938.37212.6057909467457.1411425116451473.95235.319.4538.452.962569343.058051072.944.6375.532096.973487917744.8145204860260.1168.16OpenBenchmarking.org

Parboil

The Parboil Benchmarks from the IMPACT Research Group at University of Illinois are a set of throughput computing applications for looking at computing architecture and compilers. Parboil test-cases support OpenMP, OpenCL, and CUDA multi-processing environments. However, at this time the test profile is just making use of the OpenMP and OpenCL test workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP CUTCPCavium ThunderX 96-CoreRaptor Talos 23691215SE +/- 0.05, N = 3SE +/- 0.11, N = 310.219.451. (CXX) g++ options: -lm -lpthread -lgomp -ffast-math -fopenmp
OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP CUTCPCavium ThunderX 96-CoreRaptor Talos 23691215Min: 10.12 / Avg: 10.21 / Max: 10.27Min: 9.25 / Avg: 9.45 / Max: 9.631. (CXX) g++ options: -lm -lpthread -lgomp -ffast-math -fopenmp

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes the OpenCL and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP LavaMDCavium ThunderX 96-CoreRaptor Talos 21530456075SE +/- 0.71, N = 3SE +/- 0.03, N = 366.5538.451. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP LavaMDCavium ThunderX 96-CoreRaptor Talos 21326395265Min: 65.16 / Avg: 66.55 / Max: 67.49Min: 38.42 / Avg: 38.45 / Max: 38.521. (CXX) g++ options: -O2 -lOpenCL

Timed MAFFT Alignment

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 6.864Multiple Sequence AlignmentCavium ThunderX 96-CoreRaptor Talos 248121620SE +/- 0.76, N = 6SE +/- 0.15, N = 617.652.961. (CC) gcc options: -O3 -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 6.864Multiple Sequence AlignmentCavium ThunderX 96-CoreRaptor Talos 248121620Min: 15.58 / Avg: 17.65 / Max: 19.87Min: 2.56 / Avg: 2.96 / Max: 3.421. (CC) gcc options: -O3 -lm -lpthread

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 1.8.0Test: BlowfishCavium ThunderX 96-CoreRaptor Talos 26K12K18K24K30KSE +/- 25.67, N = 3SE +/- 17.33, N = 328749256931. (CC) gcc options: -fopenmp
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.8.0Test: BlowfishCavium ThunderX 96-CoreRaptor Talos 25K10K15K20K25KMin: 28723 / Avg: 28748.67 / Max: 28800Min: 25676 / Avg: 25693.33 / Max: 257281. (CC) gcc options: -fopenmp

x264

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2018-02-05H.264 Video EncodingCavium ThunderX 96-CoreRaptor Talos 21020304050SE +/- 0.08, N = 3SE +/- 0.15, N = 324.7743.05-O3 -ffast-math -maltivec -mabi=altivec -mvsx -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize1. (CC) gcc options: -ldl -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2018-02-05H.264 Video EncodingCavium ThunderX 96-CoreRaptor Talos 2918273645Min: 24.67 / Avg: 24.77 / Max: 24.93Min: 42.85 / Avg: 43.05 / Max: 43.351. (CC) gcc options: -ldl -lm -lpthread

7-Zip Compression

This is a test of 7-Zip using p7zip with its integrated benchmark feature. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 9.20.1Compress Speed TestCavium ThunderX 96-CoreRaptor Talos 220K40K60K80K100KSE +/- 676.12, N = 3SE +/- 550.50, N = 351487805101. (CXX) g++ options: -pipe -lpthread
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 9.20.1Compress Speed TestCavium ThunderX 96-CoreRaptor Talos 214K28K42K56K70KMin: 50143 / Avg: 51487.33 / Max: 52286Min: 79575 / Avg: 80510.33 / Max: 814811. (CXX) g++ options: -pipe -lpthread

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.13Time To CompileCavium ThunderX 96-CoreRaptor Talos 250100150200250SE +/- 3.36, N = 3SE +/- 1.24, N = 3218.9372.94
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.13Time To CompileCavium ThunderX 96-CoreRaptor Talos 24080120160200Min: 213.92 / Avg: 218.93 / Max: 225.32Min: 70.94 / Avg: 72.94 / Max: 75.21

C-Ray

This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total TimeCavium ThunderX 96-CoreRaptor Talos 2246810SE +/- 0.08, N = 3SE +/- 0.00, N = 38.374.631. (CC) gcc options: -lm -lpthread -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total TimeCavium ThunderX 96-CoreRaptor Talos 23691215Min: 8.2 / Avg: 8.37 / Max: 8.45Min: 4.63 / Avg: 4.63 / Max: 4.631. (CC) gcc options: -lm -lpthread -O3

LAME MP3 Encoding

LAME is an MP3 encoder licensed under the LGPL. This test measures the time required to encode a WAV file to MP3 format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3Cavium ThunderX 96-CoreRaptor Talos 250100150200250SE +/- 0.19, N = 3SE +/- 0.22, N = 3212.6075.53-lncurses1. (CC) gcc options: -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3Cavium ThunderX 96-CoreRaptor Talos 24080120160200Min: 212.39 / Avg: 212.6 / Max: 212.98Min: 75.29 / Avg: 75.53 / Max: 75.961. (CC) gcc options: -lm

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test measures the RSA 4096-bit performance of OpenSSL. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.0fRSA 4096-bit PerformanceRaptor Talos 25001000150020002500SE +/- 5.80, N = 32096.971. (CC) gcc options: -O3 -pthread -m64 -lssl -lcrypto -ldl

Java JMH

This test runs the stock benchmark of the Java JMH benchmark via Maven. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/s, More Is BetterJava JMHThroughputCavium ThunderX 96-CoreRaptor Talos 212000M24000M36000M48000M60000M57909467457.143487917744.81

PyBench

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2008-08-14Total For Average Test TimesCavium ThunderX 96-CoreRaptor Talos 22K4K6K8K10KSE +/- 21.88, N = 3SE +/- 2.19, N = 3114254520
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2008-08-14Total For Average Test TimesCavium ThunderX 96-CoreRaptor Talos 22K4K6K8K10KMin: 11391 / Avg: 11425.33 / Max: 11466Min: 4517 / Avg: 4519.67 / Max: 4524

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesCavium ThunderX 96-CoreRaptor Talos 22K4K6K8K10KSE +/- 38.30, N = 3SE +/- 0.67, N = 3116454860
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesCavium ThunderX 96-CoreRaptor Talos 22K4K6K8K10KMin: 11601 / Avg: 11644.67 / Max: 11721Min: 4859 / Avg: 4859.67 / Max: 4861

Scikit-Learn

Scikit-learn is a Python module for machine learning Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.17.1Cavium ThunderX 96-CoreRaptor Talos 230060090012001500SE +/- 0.22, N = 3SE +/- 3.04, N = 31473.95260.11
OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.17.1Cavium ThunderX 96-CoreRaptor Talos 230060090012001500Min: 1473.6 / Avg: 1473.95 / Max: 1474.36Min: 255.32 / Avg: 260.11 / Max: 265.75

AOBench

OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total TimeCavium ThunderX 96-CoreRaptor Talos 250100150200250SE +/- 0.03, N = 3SE +/- 0.19, N = 3235.3168.161. (CC) gcc options: -lm -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total TimeCavium ThunderX 96-CoreRaptor Talos 24080120160200Min: 235.28 / Avg: 235.31 / Max: 235.37Min: 67.96 / Avg: 68.16 / Max: 68.541. (CC) gcc options: -lm -O3