AMD EPYC 7F72 FSGSBASE benchmarking 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 2006280-NE-AMDEPYC7F90 AMD EPYC 7F72 FSGSBASE Benchmark - Phoronix Test Suite AMD EPYC 7F72 FSGSBASE Benchmark AMD EPYC 7F72 FSGSBASE benchmarking by Michael Larabel for a future article.
HTML result view exported from: https://openbenchmarking.org/result/2006280-NE-AMDEPYC7F90&grw .
AMD EPYC 7F72 FSGSBASE Benchmark Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver Compiler File-System Screen Resolution FSGSBASE Enabled nofsgsbase AMD EPYC 7F72 24-Core @ 3.20GHz (24 Cores / 48 Threads) ASRockRack EPYCD8 (P2.10 BIOS) AMD Starship/Matisse 126GB 3841GB Micron_9300_MTFDHAL3T8TDP ASPEED AMD Starship/Matisse VE228 2 x Intel I350 Ubuntu 20.04 5.8.0-rc1-phx-fsgsbase (x86_64) 20200620 GNOME Shell 3.36.2 X Server 1.20.8 modesetting 1.20.8 GCC 9.3.0 ext4 1920x1080 OpenBenchmarking.org Environment Details - CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native" Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Disk Details - NONE / errors=remount-ro,relatime,rw Processor Details - Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x830101c Java Details - OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-3ubuntu1) Python Details - Python 3.8.2 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + 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 AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
AMD EPYC 7F72 FSGSBASE Benchmark java-gradle-perf: Reactor stress-ng: Atomic stress-ng: SENDFILE stress-ng: CPU Stress stress-ng: Semaphores stress-ng: Socket Activity stress-ng: Context Switching stress-ng: System V Message Passing renaissance: Scala Dotty renaissance: Rand Forest renaissance: Apache Spark ALS renaissance: Apache Spark PageRank renaissance: Twitter HTTP Requests renaissance: In-Memory Database Shootout renaissance: Akka Unbalanced Cobwebbed Tree lammps: Rhodopsin Protein rodinia: OpenMP LavaMD rodinia: OpenMP Myocyte rodinia: OpenMP HotSpot3D rodinia: OpenMP Leukocyte rodinia: OpenMP CFD Solver rodinia: OpenMP Streamcluster wireguard: yafaray: Total Time For Sample Scene blogbench: Read mcperf: Add - 1 mcperf: Get - 1 mcperf: Set - 1 mcperf: Add - 16 mcperf: Add - 32 mcperf: Get - 16 mcperf: Get - 32 mcperf: Set - 16 mcperf: Set - 32 mcperf: Delete - 1 mcperf: Append - 16 mcperf: Append - 32 mcperf: Delete - 16 mcperf: Delete - 32 mcperf: Prepend - 1 mcperf: Replace - 1 mcperf: Prepend - 16 mcperf: Prepend - 32 mcperf: Replace - 16 mcperf: Replace - 32 apache-siege: 10 apache-siege: 100 hbase: Increment - 1 hbase: Increment - 1 hbase: Increment - 32 hbase: Increment - 32 memtier-benchmark: Redis keydb: redis: LPOP redis: GET redis: SET rocksdb: Rand Fill rocksdb: Rand Read rocksdb: Seq Fill rocksdb: Rand Fill Sync rocksdb: Read While Writing leveldb: Hot Read leveldb: Fill Sync leveldb: Fill Sync leveldb: Overwrite leveldb: Overwrite leveldb: Rand Fill leveldb: Rand Fill leveldb: Rand Read leveldb: Seek Rand leveldb: Rand Delete leveldb: Seq Fill leveldb: Seq Fill cassandra: Writes pgbench: Buffer Test - Normal Load - Read Only pgbench: Buffer Test - Normal Load - Read Write pgbench: Buffer Test - Heavy Contention - Read Only pgbench: Buffer Test - Heavy Contention - Read Write mysqlslap: 16 mysqlslap: 32 mysqlslap: 64 FSGSBASE Enabled nofsgsbase 330.676 366333.22 388551.90 9286.92 3429123.46 13018.40 8949772.26 13675928.44 1657.663 1992.139 2139.700 3693.887 3467.122 4990.657 14833.208 14.834 100.415 30.650 96.397 55.064 10.781 14.448 297.668 90.900 1874838 38193.6 58793.5 38872.1 38541.6 39042.2 60417.3 59359.2 38976.7 38898.8 61110.0 40604.2 41153.3 59398.7 59447.2 42415.6 40539.9 40712.5 40864.7 41212.0 41216.7 20529.19 33549.01 7682 129 77797 407 2528818.11 407915.56 2325065.01 2203748.33 1654333.00 765374 110651332 788878 173150 4308730 41.951 11.4 459.890 22.4 236.924 22.3 237.985 42.225 66.178 221.888 23.2 229.018 180025 405682.820374 32504.537022 393719.960705 29160.086403 6446 2871 1265 336.225 365882.92 390724.06 9351.58 3435023.37 12997.93 9024332.58 13582744.37 1682.877 2016.819 2141.214 3825.917 3464.373 5089.412 14852.442 14.693 99.965 30.916 96.410 55.354 10.791 14.360 297.736 90.671 1897378 37726.3 58689.9 37959.3 38350.6 38359.4 60813.3 60220.6 38415.9 38593.1 59022.8 40702.0 40882.6 59634.6 60134.1 41401.2 41082.6 40925.2 40593.2 40383.9 40688.9 20215.87 33594.07 7601 130 78493 404 2366095.56 406845.91 1527744.88 1996260.39 1580580.22 774825 110807697 798050 172835 4362967 41.725 11.3 462.619 22.4 237.472 22.3 237.774 41.908 66.748 223.519 23.3 227.779 174383 405095.478499 32344.339219 386767.369484 29332.960870 6438 2871 1263 OpenBenchmarking.org
Java Gradle Build Gradle Build: Reactor OpenBenchmarking.org Seconds, Fewer Is Better Java Gradle Build Gradle Build: Reactor FSGSBASE Enabled nofsgsbase 70 140 210 280 350 SE +/- 2.34, N = 3 SE +/- 5.27, N = 9 330.68 336.23
Stress-NG Test: Atomic OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Atomic FSGSBASE Enabled nofsgsbase 80K 160K 240K 320K 400K SE +/- 893.96, N = 3 SE +/- 1186.10, N = 3 366333.22 365882.92 1. (CC) gcc options: -O3 -march=native -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: SENDFILE FSGSBASE Enabled nofsgsbase 80K 160K 240K 320K 400K SE +/- 2536.04, N = 3 SE +/- 1019.50, N = 3 388551.90 390724.06 1. (CC) gcc options: -O3 -march=native -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Stress FSGSBASE Enabled nofsgsbase 2K 4K 6K 8K 10K SE +/- 108.21, N = 3 SE +/- 72.21, N = 3 9286.92 9351.58 1. (CC) gcc options: -O3 -march=native -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Semaphores FSGSBASE Enabled nofsgsbase 700K 1400K 2100K 2800K 3500K SE +/- 4550.56, N = 3 SE +/- 2201.17, N = 3 3429123.46 3435023.37 1. (CC) gcc options: -O3 -march=native -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Socket Activity FSGSBASE Enabled nofsgsbase 3K 6K 9K 12K 15K SE +/- 37.64, N = 3 SE +/- 62.86, N = 3 13018.40 12997.93 1. (CC) gcc options: -O3 -march=native -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Context Switching FSGSBASE Enabled nofsgsbase 2M 4M 6M 8M 10M SE +/- 85127.62, N = 3 SE +/- 35057.13, N = 3 8949772.26 9024332.58 1. (CC) gcc options: -O3 -march=native -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: System V Message Passing FSGSBASE Enabled nofsgsbase 3M 6M 9M 12M 15M SE +/- 171725.65, N = 15 SE +/- 209569.10, N = 3 13675928.44 13582744.37 1. (CC) gcc options: -O3 -march=native -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Renaissance Test: Scala Dotty OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Scala Dotty FSGSBASE Enabled nofsgsbase 400 800 1200 1600 2000 SE +/- 6.89, N = 5 SE +/- 7.60, N = 5 1657.66 1682.88
Renaissance Test: Random Forest OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Random Forest FSGSBASE Enabled nofsgsbase 400 800 1200 1600 2000 SE +/- 19.44, N = 9 SE +/- 8.81, N = 5 1992.14 2016.82
Renaissance Test: Apache Spark ALS OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Apache Spark ALS FSGSBASE Enabled nofsgsbase 500 1000 1500 2000 2500 SE +/- 20.66, N = 5 SE +/- 24.01, N = 7 2139.70 2141.21
Renaissance Test: Apache Spark PageRank OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Apache Spark PageRank FSGSBASE Enabled nofsgsbase 800 1600 2400 3200 4000 SE +/- 36.87, N = 25 SE +/- 34.88, N = 5 3693.89 3825.92
Renaissance Test: Twitter HTTP Requests OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Twitter HTTP Requests FSGSBASE Enabled nofsgsbase 700 1400 2100 2800 3500 SE +/- 18.86, N = 5 SE +/- 22.53, N = 5 3467.12 3464.37
Renaissance Test: In-Memory Database Shootout OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: In-Memory Database Shootout FSGSBASE Enabled nofsgsbase 1100 2200 3300 4400 5500 SE +/- 47.97, N = 25 SE +/- 33.92, N = 20 4990.66 5089.41
Renaissance Test: Akka Unbalanced Cobwebbed Tree OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Akka Unbalanced Cobwebbed Tree FSGSBASE Enabled nofsgsbase 3K 6K 9K 12K 15K SE +/- 182.78, N = 5 SE +/- 125.71, N = 5 14833.21 14852.44
LAMMPS Molecular Dynamics Simulator Model: Rhodopsin Protein OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 9Jan2020 Model: Rhodopsin Protein FSGSBASE Enabled nofsgsbase 4 8 12 16 20 SE +/- 0.22, N = 3 SE +/- 0.18, N = 3 14.83 14.69 1. (CXX) g++ options: -O3 -march=native -rdynamic -ljpeg -lpng -lz -lfftw3 -lm
Rodinia Test: OpenMP LavaMD OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP LavaMD FSGSBASE Enabled nofsgsbase 20 40 60 80 100 SE +/- 1.29, N = 5 SE +/- 1.68, N = 3 100.42 99.97 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP Myocyte OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Myocyte FSGSBASE Enabled nofsgsbase 7 14 21 28 35 SE +/- 0.41, N = 3 SE +/- 0.06, N = 3 30.65 30.92 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP HotSpot3D OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP HotSpot3D FSGSBASE Enabled nofsgsbase 20 40 60 80 100 SE +/- 0.54, N = 3 SE +/- 0.33, N = 3 96.40 96.41 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP Leukocyte OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Leukocyte FSGSBASE Enabled nofsgsbase 12 24 36 48 60 SE +/- 0.20, N = 3 SE +/- 0.41, N = 3 55.06 55.35 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP CFD Solver OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP CFD Solver FSGSBASE Enabled nofsgsbase 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 10.78 10.79 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP Streamcluster OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Streamcluster FSGSBASE Enabled nofsgsbase 4 8 12 16 20 SE +/- 0.09, N = 3 SE +/- 0.05, N = 3 14.45 14.36 1. (CXX) g++ options: -O2 -lOpenCL
WireGuard + Linux Networking Stack Stress Test OpenBenchmarking.org Seconds, Fewer Is Better WireGuard + Linux Networking Stack Stress Test FSGSBASE Enabled nofsgsbase 60 120 180 240 300 SE +/- 0.68, N = 3 SE +/- 0.46, N = 3 297.67 297.74
YafaRay Total Time For Sample Scene OpenBenchmarking.org Seconds, Fewer Is Better YafaRay 3.4.1 Total Time For Sample Scene FSGSBASE Enabled nofsgsbase 20 40 60 80 100 SE +/- 0.91, N = 3 SE +/- 0.48, N = 3 90.90 90.67 1. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lpthread
BlogBench Test: Read OpenBenchmarking.org Final Score, More Is Better BlogBench 1.1 Test: Read FSGSBASE Enabled nofsgsbase 400K 800K 1200K 1600K 2000K SE +/- 13162.10, N = 3 SE +/- 17404.38, N = 3 1874838 1897378 1. (CC) gcc options: -O3 -march=native -pthread
Memcached mcperf Method: Add - Connections: 1 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Add - Connections: 1 FSGSBASE Enabled nofsgsbase 8K 16K 24K 32K 40K SE +/- 617.61, N = 3 SE +/- 477.28, N = 3 38193.6 37726.3 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Memcached mcperf Method: Get - Connections: 1 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Get - Connections: 1 FSGSBASE Enabled nofsgsbase 13K 26K 39K 52K 65K SE +/- 645.43, N = 15 SE +/- 752.29, N = 3 58793.5 58689.9 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Memcached mcperf Method: Set - Connections: 1 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Set - Connections: 1 FSGSBASE Enabled nofsgsbase 8K 16K 24K 32K 40K SE +/- 633.69, N = 3 SE +/- 264.79, N = 3 38872.1 37959.3 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Memcached mcperf Method: Add - Connections: 16 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Add - Connections: 16 FSGSBASE Enabled nofsgsbase 8K 16K 24K 32K 40K SE +/- 384.94, N = 3 SE +/- 228.64, N = 3 38541.6 38350.6 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Memcached mcperf Method: Add - Connections: 32 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Add - Connections: 32 FSGSBASE Enabled nofsgsbase 8K 16K 24K 32K 40K SE +/- 73.79, N = 3 SE +/- 23.77, N = 3 39042.2 38359.4 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Memcached mcperf Method: Get - Connections: 16 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Get - Connections: 16 FSGSBASE Enabled nofsgsbase 13K 26K 39K 52K 65K SE +/- 340.39, N = 3 SE +/- 437.44, N = 3 60417.3 60813.3 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Memcached mcperf Method: Get - Connections: 32 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Get - Connections: 32 FSGSBASE Enabled nofsgsbase 13K 26K 39K 52K 65K SE +/- 352.41, N = 3 SE +/- 830.62, N = 3 59359.2 60220.6 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Memcached mcperf Method: Set - Connections: 16 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Set - Connections: 16 FSGSBASE Enabled nofsgsbase 8K 16K 24K 32K 40K SE +/- 86.79, N = 3 SE +/- 307.49, N = 3 38976.7 38415.9 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Memcached mcperf Method: Set - Connections: 32 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Set - Connections: 32 FSGSBASE Enabled nofsgsbase 8K 16K 24K 32K 40K SE +/- 301.85, N = 3 SE +/- 78.19, N = 3 38898.8 38593.1 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Memcached mcperf Method: Delete - Connections: 1 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Delete - Connections: 1 FSGSBASE Enabled nofsgsbase 13K 26K 39K 52K 65K SE +/- 488.89, N = 15 SE +/- 652.01, N = 15 61110.0 59022.8 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Memcached mcperf Method: Append - Connections: 16 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Append - Connections: 16 FSGSBASE Enabled nofsgsbase 9K 18K 27K 36K 45K SE +/- 146.11, N = 3 SE +/- 268.54, N = 3 40604.2 40702.0 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Memcached mcperf Method: Append - Connections: 32 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Append - Connections: 32 FSGSBASE Enabled nofsgsbase 9K 18K 27K 36K 45K SE +/- 216.37, N = 3 SE +/- 211.16, N = 3 41153.3 40882.6 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Memcached mcperf Method: Delete - Connections: 16 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Delete - Connections: 16 FSGSBASE Enabled nofsgsbase 13K 26K 39K 52K 65K SE +/- 469.76, N = 3 SE +/- 443.85, N = 3 59398.7 59634.6 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Memcached mcperf Method: Delete - Connections: 32 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Delete - Connections: 32 FSGSBASE Enabled nofsgsbase 13K 26K 39K 52K 65K SE +/- 428.90, N = 3 SE +/- 521.80, N = 3 59447.2 60134.1 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Memcached mcperf Method: Prepend - Connections: 1 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Prepend - Connections: 1 FSGSBASE Enabled nofsgsbase 9K 18K 27K 36K 45K SE +/- 684.22, N = 3 SE +/- 919.03, N = 12 42415.6 41401.2 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Memcached mcperf Method: Replace - Connections: 1 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Replace - Connections: 1 FSGSBASE Enabled nofsgsbase 9K 18K 27K 36K 45K SE +/- 378.27, N = 15 SE +/- 346.98, N = 15 40539.9 41082.6 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Memcached mcperf Method: Prepend - Connections: 16 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Prepend - Connections: 16 FSGSBASE Enabled nofsgsbase 9K 18K 27K 36K 45K SE +/- 436.56, N = 3 SE +/- 158.27, N = 3 40712.5 40925.2 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Memcached mcperf Method: Prepend - Connections: 32 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Prepend - Connections: 32 FSGSBASE Enabled nofsgsbase 9K 18K 27K 36K 45K SE +/- 152.31, N = 3 SE +/- 141.03, N = 3 40864.7 40593.2 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Memcached mcperf Method: Replace - Connections: 16 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Replace - Connections: 16 FSGSBASE Enabled nofsgsbase 9K 18K 27K 36K 45K SE +/- 200.19, N = 3 SE +/- 215.15, N = 3 41212.0 40383.9 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Memcached mcperf Method: Replace - Connections: 32 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Replace - Connections: 32 FSGSBASE Enabled nofsgsbase 9K 18K 27K 36K 45K SE +/- 212.28, N = 3 SE +/- 137.97, N = 3 41216.7 40688.9 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
Apache Siege Concurrent Users: 10 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 10 FSGSBASE Enabled nofsgsbase 4K 8K 12K 16K 20K SE +/- 311.87, N = 3 SE +/- 49.03, N = 3 20529.19 20215.87 1. (CC) gcc options: -O3 -march=native -lpthread -ldl -lssl -lcrypto
Apache Siege Concurrent Users: 100 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 100 FSGSBASE Enabled nofsgsbase 7K 14K 21K 28K 35K SE +/- 342.39, N = 3 SE +/- 232.96, N = 3 33549.01 33594.07 1. (CC) gcc options: -O3 -march=native -lpthread -ldl -lssl -lcrypto
Apache HBase Test: Increment - Clients: 1 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.2.3 Test: Increment - Clients: 1 FSGSBASE Enabled nofsgsbase 1600 3200 4800 6400 8000 SE +/- 70.17, N = 3 SE +/- 97.74, N = 5 7682 7601
Apache HBase Test: Increment - Clients: 1 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.2.3 Test: Increment - Clients: 1 FSGSBASE Enabled nofsgsbase 30 60 90 120 150 SE +/- 1.20, N = 3 SE +/- 1.74, N = 5 129 130
Apache HBase Test: Increment - Clients: 32 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.2.3 Test: Increment - Clients: 32 FSGSBASE Enabled nofsgsbase 20K 40K 60K 80K 100K SE +/- 963.41, N = 3 SE +/- 876.82, N = 3 77797 78493
Apache HBase Test: Increment - Clients: 32 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.2.3 Test: Increment - Clients: 32 FSGSBASE Enabled nofsgsbase 90 180 270 360 450 SE +/- 3.21, N = 3 SE +/- 2.60, N = 3 407 404
Memtier_benchmark Protocol: Redis OpenBenchmarking.org Ops/sec, More Is Better Memtier_benchmark 1.2.17 Protocol: Redis FSGSBASE Enabled nofsgsbase 500K 1000K 1500K 2000K 2500K SE +/- 8587.72, N = 3 SE +/- 43966.04, N = 15 2528818.11 2366095.56 1. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre
KeyDB OpenBenchmarking.org Ops/sec, More Is Better KeyDB 5.3.1 FSGSBASE Enabled nofsgsbase 90K 180K 270K 360K 450K SE +/- 201.40, N = 3 SE +/- 2373.13, N = 3 407915.56 406845.91 1. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre
Redis Test: LPOP OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: LPOP FSGSBASE Enabled nofsgsbase 500K 1000K 1500K 2000K 2500K SE +/- 61099.04, N = 15 SE +/- 13875.24, N = 3 2325065.01 1527744.88 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native
Redis Test: GET OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: GET FSGSBASE Enabled nofsgsbase 500K 1000K 1500K 2000K 2500K SE +/- 74105.75, N = 15 SE +/- 54904.71, N = 12 2203748.33 1996260.39 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native
Redis Test: SET OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: SET FSGSBASE Enabled nofsgsbase 400K 800K 1200K 1600K 2000K SE +/- 30095.24, N = 15 SE +/- 29112.89, N = 15 1654333.00 1580580.22 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native
Facebook RocksDB Test: Random Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Fill FSGSBASE Enabled nofsgsbase 170K 340K 510K 680K 850K SE +/- 6529.64, N = 3 SE +/- 4918.03, N = 3 765374 774825 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Read FSGSBASE Enabled nofsgsbase 20M 40M 60M 80M 100M SE +/- 771206.69, N = 3 SE +/- 123767.54, N = 3 110651332 110807697 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
Facebook RocksDB Test: Sequential Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Sequential Fill FSGSBASE Enabled nofsgsbase 200K 400K 600K 800K 1000K SE +/- 3163.32, N = 3 SE +/- 7062.29, N = 3 788878 798050 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
Facebook RocksDB Test: Random Fill Sync OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Fill Sync FSGSBASE Enabled nofsgsbase 40K 80K 120K 160K 200K SE +/- 392.83, N = 3 SE +/- 173.43, N = 3 173150 172835 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
Facebook RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Read While Writing FSGSBASE Enabled nofsgsbase 900K 1800K 2700K 3600K 4500K SE +/- 23791.70, N = 3 SE +/- 48452.32, N = 3 4308730 4362967 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
LevelDB Benchmark: Hot Read OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Hot Read FSGSBASE Enabled nofsgsbase 10 20 30 40 50 SE +/- 0.36, N = 3 SE +/- 0.35, N = 3 41.95 41.73 1. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread
LevelDB Benchmark: Fill Sync OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Fill Sync FSGSBASE Enabled nofsgsbase 3 6 9 12 15 SE +/- 0.06, N = 3 SE +/- 0.19, N = 3 11.4 11.3 1. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread
LevelDB Benchmark: Fill Sync OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Fill Sync FSGSBASE Enabled nofsgsbase 100 200 300 400 500 SE +/- 2.82, N = 3 SE +/- 6.48, N = 3 459.89 462.62 1. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread
LevelDB Benchmark: Overwrite OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Overwrite FSGSBASE Enabled nofsgsbase 5 10 15 20 25 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 22.4 22.4 1. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread
LevelDB Benchmark: Overwrite OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Overwrite FSGSBASE Enabled nofsgsbase 50 100 150 200 250 SE +/- 0.90, N = 3 SE +/- 0.50, N = 3 236.92 237.47 1. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread
LevelDB Benchmark: Random Fill OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Random Fill FSGSBASE Enabled nofsgsbase 5 10 15 20 25 SE +/- 0.12, N = 3 SE +/- 0.12, N = 3 22.3 22.3 1. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread
LevelDB Benchmark: Random Fill OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Fill FSGSBASE Enabled nofsgsbase 50 100 150 200 250 SE +/- 1.33, N = 3 SE +/- 1.38, N = 3 237.99 237.77 1. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread
LevelDB Benchmark: Random Read OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Read FSGSBASE Enabled nofsgsbase 10 20 30 40 50 SE +/- 0.32, N = 3 SE +/- 0.15, N = 3 42.23 41.91 1. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread
LevelDB Benchmark: Seek Random OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Seek Random FSGSBASE Enabled nofsgsbase 15 30 45 60 75 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 66.18 66.75 1. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread
LevelDB Benchmark: Random Delete OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Delete FSGSBASE Enabled nofsgsbase 50 100 150 200 250 SE +/- 0.28, N = 3 SE +/- 1.83, N = 3 221.89 223.52 1. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread
LevelDB Benchmark: Sequential Fill OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Sequential Fill FSGSBASE Enabled nofsgsbase 6 12 18 24 30 SE +/- 0.09, N = 3 SE +/- 0.10, N = 3 23.2 23.3 1. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread
LevelDB Benchmark: Sequential Fill OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Sequential Fill FSGSBASE Enabled nofsgsbase 50 100 150 200 250 SE +/- 1.09, N = 3 SE +/- 0.88, N = 3 229.02 227.78 1. (CXX) g++ options: -O3 -march=native -lsnappy -lpthread
Apache Cassandra Test: Writes OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 3.11.4 Test: Writes FSGSBASE Enabled nofsgsbase 40K 80K 120K 160K 200K SE +/- 1511.54, N = 3 SE +/- 2335.43, N = 3 180025 174383
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Only FSGSBASE Enabled nofsgsbase 90K 180K 270K 360K 450K SE +/- 179.66, N = 3 SE +/- 487.15, N = 3 405682.82 405095.48 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write FSGSBASE Enabled nofsgsbase 7K 14K 21K 28K 35K SE +/- 31.72, N = 3 SE +/- 133.10, N = 3 32504.54 32344.34 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
PostgreSQL pgbench Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Only FSGSBASE Enabled nofsgsbase 80K 160K 240K 320K 400K SE +/- 2182.44, N = 3 SE +/- 6497.34, N = 3 393719.96 386767.37 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
PostgreSQL pgbench Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Write FSGSBASE Enabled nofsgsbase 6K 12K 18K 24K 30K SE +/- 155.99, N = 3 SE +/- 71.87, N = 3 29160.09 29332.96 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
MariaDB Clients: 16 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 16 FSGSBASE Enabled nofsgsbase 1400 2800 4200 5600 7000 SE +/- 5.91, N = 7 SE +/- 13.79, N = 3 6446 6438 1. (CXX) g++ options: -O3 -march=native -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lcrypt -lz -lm -lssl -lcrypto -ldl
MariaDB Clients: 32 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 32 FSGSBASE Enabled nofsgsbase 600 1200 1800 2400 3000 SE +/- 2.74, N = 3 SE +/- 2.74, N = 3 2871 2871 1. (CXX) g++ options: -O3 -march=native -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lcrypt -lz -lm -lssl -lcrypto -ldl
MariaDB Clients: 64 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 64 FSGSBASE Enabled nofsgsbase 300 600 900 1200 1500 SE +/- 0.53, N = 3 SE +/- 0.92, N = 3 1265 1263 1. (CXX) g++ options: -O3 -march=native -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lcrypt -lz -lm -lssl -lcrypto -ldl
Phoronix Test Suite v10.8.4