Zombieload TSX TAA mitigation impact on Linux. Benchmarks by Michael Larabel for a future article.
TSX Enabled - Default Mitigation Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-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 -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002cJava Notes: OpenJDK Runtime Environment (build 11.0.5-ea+10-post-Ubuntu-0ubuntu1)Python Notes: Python 2.7.17rc1 + Python 3.7.5rc1Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable
TSX Enabled - Vulnerable Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-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 -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002cJava Notes: OpenJDK Runtime Environment (build 11.0.5-ea+10-post-Ubuntu-0ubuntu1)Python Notes: Python 2.7.17rc1 + Python 3.7.5rc1Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Vulnerable
TSX Disabled Processor: 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 386048MB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE
OS: Ubuntu 19.10, Kernel: 5.4.0-rc7-12nov-vulns (x86_64) 20191112, Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, Compiler: GCC 9.2.1 20191008, File-System: ext4, Screen Resolution: 1920x1080
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-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 -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002cJava Notes: OpenJDK Runtime Environment (build 11.0.5-ea+10-post-Ubuntu-0ubuntu1)Python Notes: Python 2.7.17rc1 + Python 3.7.5rc1Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled
Zombieload TAA Benchmark Impact OpenBenchmarking.org Phoronix Test Suite 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads) GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS) Intel Sky Lake-E DMI3 Registers 386048MB 280GB INTEL SSDPED1D280GA ASPEED VE228 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE Ubuntu 19.10 5.4.0-rc7-12nov-vulns (x86_64) 20191112 GNOME Shell 3.34.1 X Server 1.20.5 modesetting 1.20.5 GCC 9.2.1 20191008 ext4 1920x1080 Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Display Driver Compiler File-System Screen Resolution Zombieload TAA Benchmark Impact Performance System Logs - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-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 - NONE / errors=remount-ro,relatime,rw - Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c - OpenJDK Runtime Environment (build 11.0.5-ea+10-post-Ubuntu-0ubuntu1) - Python 2.7.17rc1 + Python 3.7.5rc1 - TSX Enabled - Default Mitigation: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable - TSX Enabled - Vulnerable: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Vulnerable - TSX Disabled: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled
TSX Enabled - Default Mitigation TSX Enabled - Vulnerable TSX Disabled Result Overview Phoronix Test Suite 100% 158% 217% 275% 333% ctx_clock Memtier_benchmark SQLite Hackbench GNU Octave Benchmark IOR Facebook RocksDB SQLite Speedtest DaCapo Benchmark GraphicsMagick Apache Benchmark glibc bench NGINX Benchmark Redis Stress-NG Memcached mcperf OSBench Timed GCC Compilation Timed LLVM Compilation NAS Parallel Benchmarks PostgreSQL pgbench Go Benchmarks Timed Linux Kernel Compilation SVT-VP9 ACES DGEMM MariaDB Renaissance
Zombieload TAA Benchmark Impact mt-dgemm: Sustained Floating-Point Rate apache: Static Web Page Serving ctx-clock: Context Switch Time dacapobench: Tradesoap rocksdb: Rand Fill rocksdb: Seq Fill glibc-bench: exp glibc-bench: ffs glibc-bench: modf glibc-bench: sqrt glibc-bench: tanh glibc-bench: ffsll glibc-bench: pthread_once octave-benchmark: go-benchmark: build graphics-magick: Rotate graphics-magick: Resizing graphics-magick: Noise-Gaussian graphics-magick: HWB Color Space hackbench: 32 - Process ior: Write Test ior: Read Test mysqlslap: 256 mcperf: Add mcperf: Get mcperf: Set memtier-benchmark: Redis npb: FT.C nginx: Static Web Page Serving osbench: Create Files osbench: Create Threads osbench: Create Processes osbench: Memory Allocations 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 redis: SET renaissance: Savina Reactors.IO renaissance: In-Memory Database Shootout sqlite: 64 sqlite-speedtest: Timed Time - Size 1,000 stress-ng: Semaphores stress-ng: Socket Activity stress-ng: Glibc C String Functions stress-ng: System V Message Passing svt-vp9: VMAF Optimized - Bosphorus 1080p svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080p build-gcc: Time To Compile build-linux-kernel: Time To Compile build-llvm: Time To Compile TSX Enabled - Default Mitigation TSX Enabled - Vulnerable TSX Disabled 19.484871 23867.35 447 7959 176082 176806 5.84241 1.79191 2.30222 2.04460 13.5902 1.79032 1.79695 23.400 29373863177 565 1015 453 724 51.113 1181.17 1786.20 438 60388.2 103583.5 61022.2 3667723.01 46690.94 29896.15 14.774549 21.406810 46.935876 91.116031 889115.083056 23397.579267 890217.581908 23449.880832 1698250.45 28158.509 17445.921 21.692 70.604 2113073.64 30181.41 3789431.68 7749223.14 251.99 254.93 938.438 25.453 118.324 19.904714 24645.32 135 7382 194543 195264 5.63132 1.67233 2.18157 1.92311 13.3266 1.67153 1.67940 20.193 28877584189 597 1105 471 767 46.454 1275.61 1879.09 441 62451.2 108348.7 62582.1 4496083.39 48076.61 31364.50 14.246883 20.532608 46.166579 90.164979 903471.038822 23895.260141 921548.748491 23854.143655 1788806.00 26830.669 17247.176 17.730 66.119 2168856.20 32401.87 3924142.52 8322741.69 259.46 258.63 901.876 25.007 114.485 19.840702 25420.84 134 7250 195534 195628 5.60681 1.67090 2.18276 1.92308 13.3172 1.67261 1.68009 21.334 28733203837 606 1118 472 780 43.949 1351.15 1996.37 442 63145.5 109040.9 63190.8 3791904.46 48264.82 31504.78 13.945165 20.370483 45.399666 88.446061 906703.218127 23997.627692 896808.095722 23993.983667 1716280.65 27100.061 16808.406 18.531 64.819 2122557.46 32287.43 3618199.19 7965249.71 250.24 258.00 902.105 24.901 114.431 OpenBenchmarking.org
Apache Benchmark This is a test of ab, which is the Apache benchmark program. This test profile measures how many requests per second a given system can sustain when carrying out 1,000,000 requests with 100 requests being carried out concurrently. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.29 Static Web Page Serving TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 5K 10K 15K 20K 25K SE +/- 110.45, N = 3 SE +/- 16.08, N = 3 SE +/- 204.74, N = 3 24645.32 23867.35 25420.84 1. (CC) gcc options: -shared -fPIC -O2 -pthread
Facebook RocksDB This is a benchmark of 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.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Fill TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 40K 80K 120K 160K 200K SE +/- 458.07, N = 3 SE +/- 134.25, N = 3 SE +/- 117.32, N = 3 194543 176082 195534 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Sequential Fill TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 40K 80K 120K 160K 200K SE +/- 336.77, N = 3 SE +/- 198.59, N = 3 SE +/- 178.12, N = 3 195264 176806 195628 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
glibc bench The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more.
Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: exp TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 1.3145 2.629 3.9435 5.258 6.5725 SE +/- 0.02766, N = 3 SE +/- 0.09855, N = 3 SE +/- 0.00137, N = 3 5.63132 5.84241 5.60681
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: ffs TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 0.4032 0.8064 1.2096 1.6128 2.016 SE +/- 0.00020, N = 12 SE +/- 0.00023, N = 12 SE +/- 0.00033, N = 15 1.67233 1.79191 1.67090
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: modf TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 0.518 1.036 1.554 2.072 2.59 SE +/- 0.00053, N = 14 SE +/- 0.00051, N = 15 SE +/- 0.00086, N = 3 2.18157 2.30222 2.18276
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: sqrt TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 0.46 0.92 1.38 1.84 2.3 SE +/- 0.00048, N = 3 SE +/- 0.00131, N = 3 SE +/- 0.00051, N = 3 1.92311 2.04460 1.92308
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: tanh TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 3 6 9 12 15 SE +/- 0.00, N = 4 SE +/- 0.15, N = 3 SE +/- 0.01, N = 3 13.33 13.59 13.32
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: ffsll TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 0.4028 0.8056 1.2084 1.6112 2.014 SE +/- 0.00018, N = 15 SE +/- 0.00038, N = 12 SE +/- 0.00037, N = 8 1.67153 1.79032 1.67261
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: pthread_once TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 0.4043 0.8086 1.2129 1.6172 2.0215 SE +/- 0.00032, N = 15 SE +/- 0.00078, N = 3 SE +/- 0.00046, N = 12 1.67940 1.79695 1.68009
GNU Octave Benchmark This test profile measures how long it takes to complete several reference GNU Octave files via octave-benchmark. GNU Octave is used for numerical computations and is an open-source alternative to MATLAB. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better GNU Octave Benchmark 4.4.1 TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 6 12 18 24 30 SE +/- 0.19, N = 3 SE +/- 0.52, N = 15 SE +/- 0.06, N = 3 20.19 23.40 21.33
Go Benchmarks Benchmark for monitoring real time performance of the Go implementation for HTTP, JSON and garbage testing per iteration. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: build TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 6000M 12000M 18000M 24000M 30000M SE +/- 30335417.30, N = 3 SE +/- 25336863.06, N = 3 SE +/- 20030611.67, N = 3 28877584189 29373863177 28733203837
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Rotate TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 130 260 390 520 650 SE +/- 5.93, N = 3 SE +/- 5.17, N = 3 597 565 606 1. (CC) gcc options: -fopenmp -O2 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Resizing TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 200 400 600 800 1000 SE +/- 14.45, N = 3 SE +/- 15.23, N = 15 SE +/- 15.28, N = 15 1105 1015 1118 1. (CC) gcc options: -fopenmp -O2 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Noise-Gaussian TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 100 200 300 400 500 SE +/- 3.48, N = 3 SE +/- 3.86, N = 13 471 453 472 1. (CC) gcc options: -fopenmp -O2 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: HWB Color Space TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 200 400 600 800 1000 SE +/- 6.66, N = 15 SE +/- 7.81, N = 3 SE +/- 11.42, N = 15 767 724 780 1. (CC) gcc options: -fopenmp -O2 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread
IOR IOR is a parallel I/O storage benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better IOR 3.2.1 Write Test TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 300 600 900 1200 1500 SE +/- 12.98, N = 12 SE +/- 23.77, N = 15 SE +/- 35.87, N = 15 1275.61 1181.17 1351.15 MIN: 779.79 / MAX: 1819.85 MIN: 728.79 / MAX: 1749.8 MIN: 667.19 / MAX: 1909.73 1. (CC) gcc options: -O2 -lm -pthread -lmpi
OpenBenchmarking.org MB/s, More Is Better IOR 3.2.1 Read Test TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 400 800 1200 1600 2000 SE +/- 13.15, N = 12 SE +/- 20.50, N = 15 SE +/- 22.79, N = 15 1879.09 1786.20 1996.37 MIN: 1536.94 / MAX: 2299.57 MIN: 1390.34 / MAX: 2174.36 MIN: 1526.48 / MAX: 2317.62 1. (CC) gcc options: -O2 -lm -pthread -lmpi
MariaDB This is a MariaDB MySQL database server benchmark making use of mysqlslap. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.3.8 Clients: 256 TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 100 200 300 400 500 SE +/- 0.34, N = 3 SE +/- 0.29, N = 3 SE +/- 1.40, N = 3 441 438 442 1. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Get TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 20K 40K 60K 80K 100K SE +/- 634.59, N = 3 SE +/- 359.26, N = 3 SE +/- 1716.86, N = 3 108348.7 103583.5 109040.9 1. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Set TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 14K 28K 42K 56K 70K SE +/- 137.33, N = 3 SE +/- 582.30, N = 3 SE +/- 258.42, N = 3 62582.1 61022.2 63190.8 1. (CC) gcc options: -O2 -lm -rdynamic
Memtier_benchmark Memtier_benchmark is a NoSQL Redis/Memcache traffic generation plus benchmarking tool. This current test profile currently just stresses the Redis protocol and basic options exposed wotj a 1:1 Set/Get ratio, 30 pipeline, 100 clients per thread, and thread count equal to the number of CPU cores/threads present. Patches to extend the test are welcome as always. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ops/sec, More Is Better Memtier_benchmark 1.2.17 Protocol: Redis TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 1000K 2000K 3000K 4000K 5000K SE +/- 17852.67, N = 3 SE +/- 179523.26, N = 15 SE +/- 172253.35, N = 13 4496083.39 3667723.01 3791904.46 1. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 10K 20K 30K 40K 50K SE +/- 94.92, N = 3 SE +/- 379.91, N = 3 SE +/- 39.03, N = 3 48076.61 46690.94 48264.82 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
NGINX Benchmark This is a test of ab, which is the Apache Benchmark program running against nginx. This test profile measures how many requests per second a given system can sustain when carrying out 2,000,000 requests with 500 requests being carried out concurrently. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better NGINX Benchmark 1.9.9 Static Web Page Serving TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 7K 14K 21K 28K 35K SE +/- 247.74, N = 14 SE +/- 223.35, N = 3 SE +/- 64.36, N = 3 31364.50 29896.15 31504.78 1. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native
OSBench OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Files TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 14.25 14.77 13.95 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Threads TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 5 10 15 20 25 SE +/- 0.04, N = 3 SE +/- 0.11, N = 3 SE +/- 0.01, N = 3 20.53 21.41 20.37 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Processes TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 11 22 33 44 55 SE +/- 0.53, N = 3 SE +/- 0.78, N = 3 SE +/- 0.34, N = 3 46.17 46.94 45.40 1. (CC) gcc options: -lm
OpenBenchmarking.org Ns Per Event, Fewer Is Better OSBench Test: Memory Allocations TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 20 40 60 80 100 SE +/- 0.13, N = 3 SE +/- 0.29, N = 3 SE +/- 0.13, N = 3 90.16 91.12 88.45 1. (CC) gcc options: -lm
PostgreSQL pgbench This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Only TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 200K 400K 600K 800K 1000K SE +/- 8997.88, N = 3 SE +/- 2834.03, N = 3 SE +/- 3822.91, N = 3 903471.04 889115.08 906703.22 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 5K 10K 15K 20K 25K SE +/- 23.84, N = 3 SE +/- 45.71, N = 3 SE +/- 43.55, N = 3 23895.26 23397.58 23997.63 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Only TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 200K 400K 600K 800K 1000K SE +/- 721.60, N = 3 SE +/- 3201.11, N = 3 SE +/- 7821.36, N = 3 921548.75 890217.58 896808.10 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Write TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 5K 10K 15K 20K 25K SE +/- 60.36, N = 3 SE +/- 51.60, N = 3 SE +/- 38.05, N = 3 23854.14 23449.88 23993.98 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Redis Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: SET TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 400K 800K 1200K 1600K 2000K SE +/- 29496.37, N = 3 SE +/- 33632.12, N = 15 SE +/- 20530.69, N = 15 1788806.00 1698250.45 1716280.65 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Renaissance Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.9.0 Test: Savina Reactors.IO TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 6K 12K 18K 24K 30K SE +/- 424.53, N = 40 SE +/- 403.65, N = 40 SE +/- 500.20, N = 40 26830.67 28158.51 27100.06
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.9.0 Test: In-Memory Database Shootout TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 4K 8K 12K 16K 20K SE +/- 158.59, N = 8 SE +/- 100.53, N = 40 SE +/- 161.29, N = 8 17247.18 17445.92 16808.41
SQLite This is a simple benchmark of SQLite. At present this test profile just measures the time to perform a pre-defined number of insertions on an indexed database. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.30.1 Threads / Copies: 64 TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 5 10 15 20 25 SE +/- 0.23, N = 3 SE +/- 0.35, N = 15 SE +/- 0.02, N = 3 17.73 21.69 18.53 1. (CC) gcc options: -O2 -lz -lm -ldl -lpthread
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Semaphores TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 500K 1000K 1500K 2000K 2500K SE +/- 34445.77, N = 3 SE +/- 27414.16, N = 4 SE +/- 20194.01, N = 3 2168856.20 2113073.64 2122557.46 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Socket Activity TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 7K 14K 21K 28K 35K SE +/- 324.90, N = 8 SE +/- 372.29, N = 4 SE +/- 483.61, N = 4 32401.87 30181.41 32287.43 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Glibc C String Functions TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 800K 1600K 2400K 3200K 4000K SE +/- 22365.08, N = 3 SE +/- 45333.30, N = 15 SE +/- 56453.12, N = 3 3924142.52 3789431.68 3618199.19 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: System V Message Passing TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 2M 4M 6M 8M 10M SE +/- 78426.67, N = 3 SE +/- 27501.34, N = 3 SE +/- 73986.08, N = 3 8322741.69 7749223.14 7965249.71 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
SVT-VP9 This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: VMAF Optimized - Input: Bosphorus 1080p TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 60 120 180 240 300 SE +/- 2.41, N = 10 SE +/- 3.16, N = 5 SE +/- 1.91, N = 3 259.46 251.99 250.24 1. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p TSX Enabled - Vulnerable TSX Enabled - Default Mitigation TSX Disabled 60 120 180 240 300 SE +/- 4.44, N = 3 SE +/- 3.67, N = 4 SE +/- 0.78, N = 3 258.63 254.93 258.00 1. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -lm
TSX Enabled - Default Mitigation Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-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 -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002cJava Notes: OpenJDK Runtime Environment (build 11.0.5-ea+10-post-Ubuntu-0ubuntu1)Python Notes: Python 2.7.17rc1 + Python 3.7.5rc1Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable
Testing initiated at 12 November 2019 17:28 by user phoronix.
TSX Enabled - Vulnerable Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-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 -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002cJava Notes: OpenJDK Runtime Environment (build 11.0.5-ea+10-post-Ubuntu-0ubuntu1)Python Notes: Python 2.7.17rc1 + Python 3.7.5rc1Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Vulnerable
Testing initiated at 13 November 2019 07:26 by user phoronix.
TSX Disabled Processor: 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 386048MB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE
OS: Ubuntu 19.10, Kernel: 5.4.0-rc7-12nov-vulns (x86_64) 20191112, Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, Compiler: GCC 9.2.1 20191008, File-System: ext4, Screen Resolution: 1920x1080
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-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 -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002cJava Notes: OpenJDK Runtime Environment (build 11.0.5-ea+10-post-Ubuntu-0ubuntu1)Python Notes: Python 2.7.17rc1 + Python 3.7.5rc1Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled
Testing initiated at 13 November 2019 20:08 by user phoronix.