ampere altra july Intel Xeon Platinum 8170M testing with a Cisco UCSC-C220-M5SX (C220M5.4.1.3e.0.1210201720 BIOS) and Matrox MGA G200e [Pilot] on Fedora 29 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2109302-IB-2107299IB41&sor&grw .
ampere altra july Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Compiler File-System Screen Resolution 1 2 3 4 5 Intel Xeon Platinum 8170M Ampere Altra ARMv8 Neoverse-N1 @ 3.30GHz (160 Cores) WIWYNN Mt.Jade (1.1.20201019 BIOS) Ampere Computing LLC Device e100 16 x 32 GB DDR4-3200MT/s Samsung M393A4K40DB3-CWE 3841GB Micron_9300_MTFDHAL3T8TDP + 960GB SAMSUNG MZ1LB960HAJQ-00007 ASPEED VE228 Mellanox MT28908 + Intel I210 Ubuntu 20.04 5.11.0-051100-generic-64k (aarch64) GNOME Shell 3.36.4 X Server 1.20.9 GCC 9.3.0 ext4 1920x1080 Intel Xeon Platinum 8170M @ 3.70GHz (26 Cores) Cisco UCSC-C220-M5SX (C220M5.4.1.3e.0.1210201720 BIOS) Intel Sky Lake-E DMI3 Registers 4 x 64 GB DDR4-2666MT/s M386A8K40BM2-CTD 4 x 800GB WUSTR6480ASS200 + 3198GB UCSC-RAID12G-2GB Matrox MGA G200e [Pilot] 5 x Cisco VIC NIC Fedora 29 5.3.11-100.fc29.x86_64 (x86_64) GCC 8.3.1 20190223 xfs 1024x768 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - 1: --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --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 -v - 2: --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --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 -v - 3: --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --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 -v - 4: --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --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 -v - 5: --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --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 -v - Intel Xeon Platinum 8170M: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,lto --enable-libmpx --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-gcc-major-version-only --with-isl --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver Processor Details - 1: Scaling Governor: cppc_cpufreq performance (Boost: Enabled) - 2: Scaling Governor: cppc_cpufreq performance (Boost: Enabled) - 3: Scaling Governor: cppc_cpufreq performance (Boost: Enabled) - 4: Scaling Governor: cppc_cpufreq performance (Boost: Enabled) - 5: Scaling Governor: cppc_cpufreq performance (Boost: Enabled) - Intel Xeon Platinum 8170M: Scaling Governor: intel_pstate performance - CPU Microcode: 0x2006a08 Java Details - 1: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.04) - Intel Xeon Platinum 8170M: OpenJDK Runtime Environment (build 1.8.0_232-b09) Security Details - 1: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 - 2: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 - 3: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 - 4: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 - 5: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 - Intel Xeon Platinum 8170M: SELinux + itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT disabled + mds: Mitigation of Clear buffers; SMT disabled + meltdown: Mitigation of PTI + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW RSB filling + tsx_async_abort: Mitigation of Clear buffers; SMT disabled
ampere altra july renaissance: Scala Dotty renaissance: Rand Forest renaissance: ALS Movie Lens renaissance: Apache Spark ALS renaissance: Apache Spark Bayes tnn: CPU - DenseNet tnn: CPU - MobileNet v2 tnn: CPU - SqueezeNet v2 tnn: CPU - SqueezeNet v1.1 qe: AUSURF112 build-ffmpeg: Time To Compile build-gdb: Time To Compile vpxenc: Speed 0 - Bosphorus 4K vpxenc: Speed 5 - Bosphorus 4K vpxenc: Speed 0 - Bosphorus 1080p vpxenc: Speed 5 - Bosphorus 1080p blosc: blosclz srsran: OFDM_Test srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM srsran: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM srsran: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM rocksdb: Rand Fill rocksdb: Rand Read rocksdb: Update Rand rocksdb: Rand Fill Sync rocksdb: Read While Writing rocksdb: Read Rand Write Rand pgbench: 1 - 100 - Read Only pgbench: 1 - 100 - Read Only - Average Latency pgbench: 1 - 250 - Read Only pgbench: 1 - 250 - Read Only - Average Latency pgbench: 1 - 100 - Read Write pgbench: 1 - 100 - Read Write - Average Latency pgbench: 1 - 250 - Read Write pgbench: 1 - 250 - Read Write - Average Latency pgbench: 100 - 100 - Read Only pgbench: 100 - 100 - Read Only - Average Latency pgbench: 100 - 250 - Read Only pgbench: 100 - 250 - Read Only - Average Latency pgbench: 100 - 100 - Read Write pgbench: 100 - 100 - Read Write - Average Latency pgbench: 100 - 250 - Read Write pgbench: 100 - 250 - Read Write - Average Latency 1 2 3 4 5 Intel Xeon Platinum 8170M 1335.1 1100.0 12148.8 2413.1 1191.7 2988.507 321.778 79.287 255.13 466.63 19.347 57.228 1.24 6.35 3.59 11.7 9884 46200000 168.1 60.2 180.5 89.2 190.3 64.7 193.1 98.2 15.4 8.3 15.9 15.3 102317 881850287 83650 75182 4612806 740904 267306 0.854 183024 2.759 1638 61.06 983 254.487 56586 1.768 101602 3.572 11130 8.987 8065 31.02 2724.285 301.444 79.267 254.799 467.91 19.222 67.055 1.44 5.47 3.67 11.54 10400.7 46500000 176.5 61.5 180.7 89.4 190 64.4 192.8 97.7 15.4 8.3 15.9 15.3 89024 878651588 85897 75382 5125113 732841 60927 1.748 177869 2.88 1608 62.196 1088 229.838 75875 1.318 61143 4.715 15832 6.318 8007 31.24 2965.878 308.871 79.236 255.536 466.08 16.61 72.272 1.32 6.23 3.45 11.54 11459.2 46300000 176.1 61.4 179.8 88.9 190.2 64.5 193.3 97.8 15.4 8.3 15.9 15.3 79450 865616372 81501 65153 5973869 719729 168876 1.039 199912 2.542 1632 61.288 1040 240.546 56426 1.773 135601 3.415 15024 6.658 9013 27.758 2674.012 299.064 79.053 253.076 471.45 16.644 60.837 1.41 5.11 3.85 11.6 76856 879053806 88714 63557 5258565 751640 186120 0.962 203064 2.529 1646 60.766 1067 234.379 61952 1.615 105314 3.805 12252 8.164 9088 27.524 899.1 821.8 7622.5 1650.0 901.1 4093.183 398.841 87.319 366.050 598.20 42.799 63.268 4.33 11.94 9.60 22.22 19119.9 111100000 272.7 104.3 273.3 153.1 305.4 114.8 301.8 187.8 97.1 58.0 113.6 80.1 838864 93748137 863673 1280917 2911809 2521651 OpenBenchmarking.org
Renaissance Test: Scala Dotty OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Scala Dotty Intel Xeon Platinum 8170M 1 300 600 900 1200 1500 SE +/- 13.76, N = 15 899.1 1335.1 MIN: 706.07 / MAX: 1446.65 MIN: 1081.25 / MAX: 2177.42
Renaissance Test: Random Forest OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Random Forest Intel Xeon Platinum 8170M 1 200 400 600 800 1000 SE +/- 2.08, N = 3 821.8 1100.0 MIN: 773.05 / MAX: 1004.94 MIN: 827.88 / MAX: 1594.73
Renaissance Test: ALS Movie Lens OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: ALS Movie Lens Intel Xeon Platinum 8170M 1 3K 6K 9K 12K 15K SE +/- 25.56, N = 3 7622.5 12148.8 MIN: 7528.47 / MAX: 8403.08 MIN: 10732.83 / MAX: 16153.94
Renaissance Test: Apache Spark ALS OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark ALS Intel Xeon Platinum 8170M 1 500 1000 1500 2000 2500 SE +/- 6.46, N = 3 1650.0 2413.1 MIN: 1576.06 / MAX: 1834.36 MIN: 2050.8 / MAX: 2851.86
Renaissance Test: Apache Spark Bayes OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark Bayes Intel Xeon Platinum 8170M 1 300 600 900 1200 1500 SE +/- 12.94, N = 3 901.1 1191.7 MIN: 599.97 / MAX: 926.77 MIN: 767.34 / MAX: 1461.79
TNN Target: CPU - Model: DenseNet OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet 5 2 3 1 Intel Xeon Platinum 8170M 900 1800 2700 3600 4500 SE +/- 1.66, N = 3 2674.01 2724.29 2965.88 2988.51 4093.18 MIN: 2641.58 / MAX: 2955.03 MIN: 2654.07 / MAX: 3214.83 MIN: 2829.24 / MAX: 3051.53 MIN: 2907.93 / MAX: 3241.83 MIN: 4022.94 / MAX: 4284.49 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 5 2 3 1 Intel Xeon Platinum 8170M 90 180 270 360 450 SE +/- 0.22, N = 3 299.06 301.44 308.87 321.78 398.84 MIN: 290.92 / MAX: 388.92 MIN: 290.95 / MAX: 391.18 MIN: 290.21 / MAX: 391.89 MIN: 292.06 / MAX: 399.25 MIN: 395.54 / MAX: 418.42 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
TNN Target: CPU - Model: SqueezeNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 5 3 2 1 Intel Xeon Platinum 8170M 20 40 60 80 100 SE +/- 0.05, N = 3 79.05 79.24 79.27 79.29 87.32 MIN: 78.75 / MAX: 79.49 MIN: 79.05 / MAX: 79.6 MIN: 79.06 / MAX: 79.63 MIN: 79.07 / MAX: 79.67 MIN: 85.96 / MAX: 90.79 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 5 2 1 3 Intel Xeon Platinum 8170M 80 160 240 320 400 SE +/- 0.34, N = 3 253.08 254.80 255.13 255.54 366.05 MIN: 252.6 / MAX: 253.89 MIN: 253.9 / MAX: 255.46 MIN: 253.97 / MAX: 256.37 MIN: 255.05 / MAX: 256.26 MIN: 363.22 / MAX: 394.93 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
Quantum ESPRESSO Input: AUSURF112 OpenBenchmarking.org Seconds, Fewer Is Better Quantum ESPRESSO 6.8 Input: AUSURF112 3 1 2 5 Intel Xeon Platinum 8170M 130 260 390 520 650 SE +/- 0.36, N = 3 466.08 466.63 467.91 471.45 598.20 1. (F9X) gfortran options: -ldevXlib -lopenblas -lFoX_dom -lFoX_sax -lFoX_wxml -lFoX_common -lFoX_utils -lFoX_fsys -lfftw3 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
Timed FFmpeg Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed FFmpeg Compilation 4.4 Time To Compile 3 5 2 1 Intel Xeon Platinum 8170M 10 20 30 40 50 SE +/- 0.01, N = 3 16.61 16.64 19.22 19.35 42.80
Timed GDB GNU Debugger Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GDB GNU Debugger Compilation 10.2 Time To Compile 1 5 Intel Xeon Platinum 8170M 2 3 16 32 48 64 80 SE +/- 0.03, N = 3 57.23 60.84 63.27 67.06 72.27
VP9 libvpx Encoding Speed: Speed 0 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 0 - Input: Bosphorus 4K Intel Xeon Platinum 8170M 2 5 3 1 0.9743 1.9486 2.9229 3.8972 4.8715 SE +/- 0.04, N = 3 4.33 1.44 1.41 1.32 1.24 -m64 -march=armv8-a -march=armv8-a -march=armv8-a -march=armv8-a 1. (CXX) g++ options: -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
VP9 libvpx Encoding Speed: Speed 5 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 5 - Input: Bosphorus 4K Intel Xeon Platinum 8170M 1 3 2 5 3 6 9 12 15 SE +/- 0.01, N = 3 11.94 6.35 6.23 5.47 5.11 -m64 -march=armv8-a -march=armv8-a -march=armv8-a -march=armv8-a 1. (CXX) g++ options: -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
VP9 libvpx Encoding Speed: Speed 0 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 0 - Input: Bosphorus 1080p Intel Xeon Platinum 8170M 5 2 1 3 3 6 9 12 15 SE +/- 0.01, N = 3 9.60 3.85 3.67 3.59 3.45 -m64 -march=armv8-a -march=armv8-a -march=armv8-a -march=armv8-a 1. (CXX) g++ options: -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
VP9 libvpx Encoding Speed: Speed 5 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 5 - Input: Bosphorus 1080p Intel Xeon Platinum 8170M 1 5 3 2 5 10 15 20 25 SE +/- 0.01, N = 3 22.22 11.70 11.60 11.54 11.54 -m64 -march=armv8-a -march=armv8-a -march=armv8-a -march=armv8-a 1. (CXX) g++ options: -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
C-Blosc Compressor: blosclz OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.0 Compressor: blosclz Intel Xeon Platinum 8170M 3 2 1 4K 8K 12K 16K 20K SE +/- 11.84, N = 3 19119.9 11459.2 10400.7 9884.0 1. (CC) gcc options: -std=gnu99 -O3 -pthread -lrt -lm
srsRAN Test: OFDM_Test OpenBenchmarking.org Samples / Second, More Is Better srsRAN 21.04 Test: OFDM_Test Intel Xeon Platinum 8170M 2 3 1 20M 40M 60M 80M 100M SE +/- 1331665.62, N = 3 111100000 46500000 46300000 46200000 -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -mavx512f -mavx512cd -mavx512bw -mavx512dq -lbladeRF -lbladeRF -lbladeRF 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lm -lfftw3f
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM Intel Xeon Platinum 8170M 2 3 1 60 120 180 240 300 SE +/- 0.65, N = 3 272.7 176.5 176.1 168.1 -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -mavx512f -mavx512cd -mavx512bw -mavx512dq -lbladeRF -lbladeRF -lbladeRF 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lm -lfftw3f
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM Intel Xeon Platinum 8170M 2 3 1 20 40 60 80 100 SE +/- 0.35, N = 3 104.3 61.5 61.4 60.2 -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -mavx512f -mavx512cd -mavx512bw -mavx512dq -lbladeRF -lbladeRF -lbladeRF 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lm -lfftw3f
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM Intel Xeon Platinum 8170M 2 1 3 60 120 180 240 300 SE +/- 0.70, N = 3 273.3 180.7 180.5 179.8 -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -mavx512f -mavx512cd -mavx512bw -mavx512dq -lbladeRF -lbladeRF -lbladeRF 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lm -lfftw3f
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM Intel Xeon Platinum 8170M 2 1 3 30 60 90 120 150 SE +/- 0.15, N = 3 153.1 89.4 89.2 88.9 -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -mavx512f -mavx512cd -mavx512bw -mavx512dq -lbladeRF -lbladeRF -lbladeRF 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lm -lfftw3f
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM Intel Xeon Platinum 8170M 1 3 2 70 140 210 280 350 SE +/- 0.96, N = 3 305.4 190.3 190.2 190.0 -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -mavx512f -mavx512cd -mavx512bw -mavx512dq -lbladeRF -lbladeRF -lbladeRF 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lm -lfftw3f
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM Intel Xeon Platinum 8170M 1 3 2 30 60 90 120 150 SE +/- 0.17, N = 3 114.8 64.7 64.5 64.4 -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -mavx512f -mavx512cd -mavx512bw -mavx512dq -lbladeRF -lbladeRF -lbladeRF 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lm -lfftw3f
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM Intel Xeon Platinum 8170M 3 1 2 70 140 210 280 350 SE +/- 0.70, N = 3 301.8 193.3 193.1 192.8 -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -mavx512f -mavx512cd -mavx512bw -mavx512dq -lbladeRF -lbladeRF -lbladeRF 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lm -lfftw3f
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM Intel Xeon Platinum 8170M 1 3 2 40 80 120 160 200 SE +/- 0.64, N = 3 187.8 98.2 97.8 97.7 -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -mavx512f -mavx512cd -mavx512bw -mavx512dq -lbladeRF -lbladeRF -lbladeRF 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lm -lfftw3f
srsRAN Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM Intel Xeon Platinum 8170M 3 2 1 20 40 60 80 100 SE +/- 0.31, N = 3 97.1 15.4 15.4 15.4 -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -mavx512f -mavx512cd -mavx512bw -mavx512dq -lbladeRF -lbladeRF -lbladeRF 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lm -lfftw3f
srsRAN Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM Intel Xeon Platinum 8170M 3 2 1 13 26 39 52 65 SE +/- 0.50, N = 3 58.0 8.3 8.3 8.3 -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -mavx512f -mavx512cd -mavx512bw -mavx512dq -lbladeRF -lbladeRF -lbladeRF 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lm -lfftw3f
srsRAN Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM Intel Xeon Platinum 8170M 3 2 1 30 60 90 120 150 SE +/- 0.35, N = 3 113.6 15.9 15.9 15.9 -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -mavx512f -mavx512cd -mavx512bw -mavx512dq -lbladeRF -lbladeRF -lbladeRF 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lm -lfftw3f
srsRAN Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM Intel Xeon Platinum 8170M 3 2 1 20 40 60 80 100 SE +/- 0.47, N = 3 80.1 15.3 15.3 15.3 -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -mavx512f -mavx512cd -mavx512bw -mavx512dq -lbladeRF -lbladeRF -lbladeRF 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lm -lfftw3f
Facebook RocksDB Test: Random Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Fill Intel Xeon Platinum 8170M 1 2 3 5 200K 400K 600K 800K 1000K SE +/- 9234.74, N = 3 838864 102317 89024 79450 76856 -O2 -lgflags 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Read 1 5 2 3 Intel Xeon Platinum 8170M 200M 400M 600M 800M 1000M SE +/- 216972.40, N = 3 881850287 879053806 878651588 865616372 93748137 -lpthread -lpthread -lpthread -lpthread 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
Facebook RocksDB Test: Update Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Update Random Intel Xeon Platinum 8170M 5 2 1 3 200K 400K 600K 800K 1000K SE +/- 7994.29, N = 3 863673 88714 85897 83650 81501 -O2 -lgflags 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
Facebook RocksDB Test: Random Fill Sync OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Fill Sync Intel Xeon Platinum 8170M 2 1 3 5 300K 600K 900K 1200K 1500K SE +/- 9469.89, N = 3 1280917 75382 75182 65153 63557 -O2 -lgflags 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
Facebook RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read While Writing 3 5 2 1 Intel Xeon Platinum 8170M 1.3M 2.6M 3.9M 5.2M 6.5M SE +/- 19177.94, N = 3 5973869 5258565 5125113 4612806 2911809 -lpthread -lpthread -lpthread -lpthread -O2 -lgflags 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
Facebook RocksDB Test: Read Random Write Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read Random Write Random Intel Xeon Platinum 8170M 5 1 2 3 500K 1000K 1500K 2000K 2500K SE +/- 14415.29, N = 3 2521651 751640 740904 732841 719729 -O2 -lgflags -lpthread -lpthread -lpthread -lpthread 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
PostgreSQL pgbench Scaling Factor: 1 - Clients: 100 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Only 1 5 3 2 60K 120K 180K 240K 300K 267306 186120 168876 60927 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 100 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Only - Average Latency 1 5 3 2 0.3933 0.7866 1.1799 1.5732 1.9665 0.854 0.962 1.039 1.748 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 250 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 250 - Mode: Read Only 5 3 1 2 40K 80K 120K 160K 200K 203064 199912 183024 177869 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 250 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 250 - Mode: Read Only - Average Latency 5 3 1 2 0.648 1.296 1.944 2.592 3.24 2.529 2.542 2.759 2.880 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 100 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Write 5 1 3 2 400 800 1200 1600 2000 1646 1638 1632 1608 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 100 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Write - Average Latency 5 1 3 2 14 28 42 56 70 60.77 61.06 61.29 62.20 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 250 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 250 - Mode: Read Write 2 5 3 1 200 400 600 800 1000 1088 1067 1040 983 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 250 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 250 - Mode: Read Write - Average Latency 2 5 3 1 60 120 180 240 300 229.84 234.38 240.55 254.49 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only 2 5 1 3 16K 32K 48K 64K 80K 75875 61952 56586 56426 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency 2 5 1 3 0.3989 0.7978 1.1967 1.5956 1.9945 1.318 1.615 1.768 1.773 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only 3 5 1 2 30K 60K 90K 120K 150K 135601 105314 101602 61143 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency 3 1 5 2 1.0609 2.1218 3.1827 4.2436 5.3045 3.415 3.572 3.805 4.715 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write 2 3 5 1 3K 6K 9K 12K 15K 15832 15024 12252 11130 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency 2 3 5 1 3 6 9 12 15 6.318 6.658 8.164 8.987 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write 5 3 1 2 2K 4K 6K 8K 10K 9088 9013 8065 8007 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency 5 3 1 2 7 14 21 28 35 27.52 27.76 31.02 31.24 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Phoronix Test Suite v10.8.4