POWER9 Blackbird

POWER9 testing with a PowerNV C1P9S01 REV 1.01 and ASPEED on Ubuntu 19.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/1906220-HV-POWER9BLA18&grw.

POWER9 BlackbirdProcessorMotherboardMemoryDiskGraphicsNetworkOSKernelCompilerFile-SystemScreen ResolutionPOWER9POWER9 @ 3.80GHz (4 Cores / 16 Threads)PowerNV C1P9S01 REV 1.01131072MB1024GB SAMSUNG MZVLB1T0HALR-000L7ASPEED3 x Broadcom NetXtreme BCM5719 PCIeUbuntu 19.045.0.0-13-generic (ppc64le)GCC 8.3.0ext41024x768OpenBenchmarking.org- --build=powerpc64le-linux-gnu --disable-libphobos --disable-multilib --disable-werror --enable-bootstrap --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 - SMT (threads per core): 4- OpenJDK Runtime Environment (build 11.0.3+7-Ubuntu-1ubuntu219.04.1) - l1tf: Not affected + meltdown: Mitigation of RFI Flush L1D private per thread + spec_store_bypass: Mitigation of Kernel entry/exit barrier (eieio) + spectre_v1: Mitigation of __user pointer sanitization ori31 speculation barrier enabled + spectre_v2: Mitigation of Indirect branch cache disabled

POWER9 Blackbirdcore-latency: Average Latency Between CPU Coresrenaissance: Scala Dottyrenaissance: Twitter Finaglerenaissance: Apache Spark ALSrenaissance: Apache Spark Bayesrenaissance: Savina Reactors.IOrenaissance: Apache Spark PageRankrenaissance: Akka Unbalanced Cobwebbed TreePOWER9220.5411710.8311272.989190.2411327.7241176.2142394.9626068.04OpenBenchmarking.org

Core-Latency

Average Latency Between CPU Cores

OpenBenchmarking.orgns, Fewer Is BetterCore-LatencyAverage Latency Between CPU CoresPOWER950100150200250220.54MIN: 121.88 / MAX: 308.671. (CXX) g++ options: -std=c++11 -pthread -O3

Renaissance

Test: Scala Dotty

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Scala DottyPOWER93K6K9K12K15KSE +/- 72.37, N = 811710.83

Renaissance

Test: Twitter Finagle

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Twitter FinaglePOWER92K4K6K8K10KSE +/- 47.85, N = 811272.98

Renaissance

Test: Apache Spark ALS

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Apache Spark ALSPOWER92K4K6K8K10KSE +/- 33.88, N = 89190.24

Renaissance

Test: Apache Spark Bayes

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Apache Spark BayesPOWER92K4K6K8K10KSE +/- 79.72, N = 4011327.72

Renaissance

Test: Savina Reactors.IO

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Savina Reactors.IOPOWER99K18K27K36K45KSE +/- 334.50, N = 841176.21

Renaissance

Test: Apache Spark PageRank

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Apache Spark PageRankPOWER99K18K27K36K45KSE +/- 248.17, N = 842394.96

Renaissance

Test: Akka Unbalanced Cobwebbed Tree

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Akka Unbalanced Cobwebbed TreePOWER96K12K18K24K30KSE +/- 176.16, N = 4026068.04

Phoronix Test Suite v10.8.5