Tests for a future article.
FSGSBASE Patched Compiler Notes: --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 -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500012cJava Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-3ubuntu1)Python Notes: + Python 3.8.2Security 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
No FSGSBASE Processor: Intel Core i9-10980XE @ 4.80GHz (18 Cores / 36 Threads), Motherboard: ASRock X299 Steel Legend (P1.30 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 32GB, Disk: Samsung SSD 970 PRO 512GB, Graphics: NVIDIA NV132 11GB, Audio: Realtek ALC1220, Monitor: ASUS MG28U, Network: Intel I219-V + Intel I211
OS: Ubuntu 20.04, Kernel: 5.7.0-rc4-fsgsbase (x86_64) 20200510, Desktop: GNOME Shell 3.36.1, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.3 Mesa 20.0.4, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160
FSGSBASE Benchmarks 2020 OpenBenchmarking.org Phoronix Test Suite Intel Core i9-10980XE @ 4.80GHz (18 Cores / 36 Threads) ASRock X299 Steel Legend (P1.30 BIOS) Intel Sky Lake-E DMI3 Registers 32GB Samsung SSD 970 PRO 512GB NVIDIA NV132 11GB Realtek ALC1220 ASUS MG28U Intel I219-V + Intel I211 Ubuntu 20.04 5.7.0-rc4-fsgsbase (x86_64) 20200510 GNOME Shell 3.36.1 X Server 1.20.8 modesetting 1.20.8 4.3 Mesa 20.0.4 GCC 9.3.0 ext4 3840x2160 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution FSGSBASE Benchmarks 2020 Performance System Logs - --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 - NONE / errors=remount-ro,relatime,rw - Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500012c - OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-3ubuntu1) - + Python 3.8.2 - 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
FSGSBASE Patched vs. No FSGSBASE Comparison Phoronix Test Suite Baseline +39.3% +39.3% +78.6% +78.6% +117.9% +117.9% +157.2% +157.2% 14.6% 6% 5.2% 3.8% 3.6% 3.5% 3.3% 2.6% 2.4% 2.3% TCP - Connections/s - 64 157.3% Seq Read - IO_uring - Yes - No - 2MB 41.7% Seq Read - IO_uring - Yes - No - 2MB 41.6% LPOP 41.4% Seq Read - IO_uring - Yes - No - 4KB 18.4% Seq Read - IO_uring - Yes - No - 4KB 18.4% T.T.F.S.S Seq Write - 32 12.1% Async Rand Write - 32 9.8% Async Rand Write - 32 9.2% Context Switching 8.9% S.W.P.S GET 5.7% G.C.S.F CPU Cache Rand Write - IO_uring - Yes - No - 4KB Rand Write - IO_uring - Yes - No - 4KB Read While Writing IMB-MPI1 PingPong 3% SADD 2.9% Buffer Test - Heavy Contention - Read Write 2.7% S.V.M.P Increment - 32 2.6% Rand Fill Sync 2.6% Seq Read - 32 2.6% Socket Activity 2.5% Seq Read - 32 2.4% Memorial Rand Write - 32 2.4% Increment - 32 2.4% LPUSH 2.3% Rand Write - 32 Seq Write - IO_uring - Yes - No - 2MB 2.2% Seq Write - IO_uring - Yes - No - 2MB 2.2% Ethr Flexible IO Tester Flexible IO Tester Redis Flexible IO Tester Flexible IO Tester YafaRay Apache HBase Apache HBase Apache HBase Stress-NG Apache Benchmark Redis Stress-NG Stress-NG Flexible IO Tester Flexible IO Tester Facebook RocksDB Intel MPI Benchmarks Redis PostgreSQL pgbench Stress-NG Apache HBase Facebook RocksDB Apache HBase Stress-NG Apache HBase Intel Open Image Denoise Apache HBase Apache HBase Redis Apache HBase Flexible IO Tester Flexible IO Tester FSGSBASE Patched No FSGSBASE
Intel MPI Benchmarks Intel MPI Benchmarks for stressing MPI implementations. At this point the test profile aggregates results for some common MPI functionality. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Average Mbytes/sec, More Is Better Intel MPI Benchmarks 2019.3 Test: IMB-MPI1 Exchange FSGSBASE Patched No FSGSBASE 1000 2000 3000 4000 5000 SE +/- 43.96, N = 3 SE +/- 43.00, N = 3 4740.27 4701.89 MAX: 23870.04 MAX: 23362.31 1. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.org Average Mbytes/sec, More Is Better Intel MPI Benchmarks 2019.3 Test: IMB-MPI1 PingPong FSGSBASE Patched No FSGSBASE 800 1600 2400 3200 4000 SE +/- 33.26, N = 3 SE +/- 51.56, N = 3 3898.16 3782.92 MIN: 7.24 / MAX: 14832.21 MIN: 7.5 / MAX: 13226.49 1. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.org Average Mbytes/sec, More Is Better Intel MPI Benchmarks 2019.3 Test: IMB-MPI1 Sendrecv FSGSBASE Patched No FSGSBASE 800 1600 2400 3200 4000 SE +/- 21.45, N = 3 SE +/- 11.81, N = 3 3672.75 3690.03 MAX: 15715.85 MAX: 15556.85 1. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.org Average Msg/sec, More Is Better Intel MPI Benchmarks 2019.3 Test: IMB-P2P PingPong FSGSBASE Patched No FSGSBASE 3M 6M 9M 12M 15M SE +/- 39053.39, N = 3 SE +/- 20383.25, N = 3 11866913.04 11848791.64 MIN: 2958 / MAX: 32895299 MIN: 2957 / MAX: 32783983 1. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: NUMA FSGSBASE Patched No FSGSBASE 110 220 330 440 550 SE +/- 1.07, N = 3 SE +/- 1.85, N = 3 523.75 521.92 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: MEMFD FSGSBASE Patched No FSGSBASE 300 600 900 1200 1500 SE +/- 0.33, N = 3 SE +/- 0.28, N = 3 1297.55 1293.76 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Atomic FSGSBASE Patched No FSGSBASE 30K 60K 90K 120K 150K SE +/- 1764.26, N = 3 SE +/- 835.22, N = 3 162937.45 161346.24 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Crypto FSGSBASE Patched No FSGSBASE 800 1600 2400 3200 4000 SE +/- 2.81, N = 3 SE +/- 3.89, N = 3 3709.05 3709.67 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Malloc FSGSBASE Patched No FSGSBASE 40M 80M 120M 160M 200M SE +/- 85057.19, N = 3 SE +/- 162313.50, N = 3 187336739.66 187608200.86 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: RdRand FSGSBASE Patched No FSGSBASE 40K 80K 120K 160K 200K SE +/- 7.21, N = 3 SE +/- 14.02, N = 3 184112.42 184112.80 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Forking FSGSBASE Patched No FSGSBASE 20K 40K 60K 80K 100K SE +/- 361.24, N = 3 SE +/- 506.24, N = 3 101466.08 102393.93 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: SENDFILE FSGSBASE Patched No FSGSBASE 60K 120K 180K 240K 300K SE +/- 65.32, N = 3 SE +/- 57.66, N = 3 296211.76 296194.46 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Cache FSGSBASE Patched No FSGSBASE 20 40 60 80 100 SE +/- 0.80, N = 15 SE +/- 0.48, N = 3 85.70 88.93 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Stress FSGSBASE Patched No FSGSBASE 1500 3000 4500 6000 7500 SE +/- 8.17, N = 3 SE +/- 7.06, N = 3 6789.58 6790.89 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Semaphores FSGSBASE Patched No FSGSBASE 500K 1000K 1500K 2000K 2500K SE +/- 1395.86, N = 3 SE +/- 596.53, N = 3 2493698.97 2489944.88 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Matrix Math FSGSBASE Patched No FSGSBASE 20K 40K 60K 80K 100K SE +/- 70.50, N = 3 SE +/- 30.83, N = 3 95249.61 95088.32 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Vector Math FSGSBASE Patched No FSGSBASE 30K 60K 90K 120K 150K SE +/- 5.94, N = 3 SE +/- 3.13, N = 3 131749.52 131748.40 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Memory Copying FSGSBASE Patched No FSGSBASE 600 1200 1800 2400 3000 SE +/- 5.20, N = 3 SE +/- 3.44, N = 3 2595.03 2587.80 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Socket Activity FSGSBASE Patched No FSGSBASE 2K 4K 6K 8K 10K SE +/- 8.02, N = 3 SE +/- 73.53, N = 3 10983.48 10719.32 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Context Switching FSGSBASE Patched No FSGSBASE 1.1M 2.2M 3.3M 4.4M 5.5M SE +/- 137371.78, N = 12 SE +/- 93165.75, N = 15 5040915.43 4630906.12 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Glibc C String Functions FSGSBASE Patched No FSGSBASE 500K 1000K 1500K 2000K 2500K SE +/- 53756.04, N = 15 SE +/- 6559.70, N = 3 2137280.92 2247443.14 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Glibc Qsort Data Sorting FSGSBASE Patched No FSGSBASE 60 120 180 240 300 SE +/- 0.42, N = 3 SE +/- 0.67, N = 3 258.00 258.73 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: System V Message Passing FSGSBASE Patched No FSGSBASE 2M 4M 6M 8M 10M SE +/- 5280.10, N = 3 SE +/- 3690.98, N = 3 8436729.32 8656893.10 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
Ethr Ethr is a cross-platform Golang-written network performance measurement tool developed by Microsoft that is capable of testing multiple protocols and different measurements. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Connections/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 1 FSGSBASE Patched No FSGSBASE 2K 4K 6K 8K 10K SE +/- 107.13, N = 3 SE +/- 81.08, N = 15 10127 10152
OpenBenchmarking.org Connections/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 64 FSGSBASE Patched No FSGSBASE 12K 24K 36K 48K 60K SE +/- 7704.52, N = 12 SE +/- 6323.18, N = 15 53988 20979
SVT-AV1 This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 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-AV1 0.8 Encoder Mode: Enc Mode 0 - Input: 1080p FSGSBASE Patched No FSGSBASE 0.029 0.058 0.087 0.116 0.145 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 0.129 0.129 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8 Encoder Mode: Enc Mode 4 - Input: 1080p FSGSBASE Patched No FSGSBASE 1.2193 2.4386 3.6579 4.8772 6.0965 SE +/- 0.015, N = 3 SE +/- 0.009, N = 3 5.414 5.419 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8 Encoder Mode: Enc Mode 8 - Input: 1080p FSGSBASE Patched No FSGSBASE 10 20 30 40 50 SE +/- 0.12, N = 3 SE +/- 0.23, N = 3 42.84 43.00 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
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 FSGSBASE Patched No FSGSBASE 70 140 210 280 350 SE +/- 5.18, N = 3 SE +/- 4.22, N = 3 307.24 307.65 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p FSGSBASE Patched No FSGSBASE 70 140 210 280 350 SE +/- 0.92, N = 3 SE +/- 1.08, N = 3 316.85 318.31 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p FSGSBASE Patched No FSGSBASE 60 120 180 240 300 SE +/- 0.63, N = 3 SE +/- 0.48, N = 3 257.48 256.52 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.8.2 Speed: Speed 5 FSGSBASE Patched No FSGSBASE 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 21.19 21.15 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11
x264 This is a simple test of the x264 encoder run on the CPU (OpenCL support disabled) with a sample video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better x264 2019-12-17 H.264 Video Encoding FSGSBASE Patched No FSGSBASE 30 60 90 120 150 SE +/- 0.36, N = 3 SE +/- 2.19, N = 3 134.26 132.76 1. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
Flexible IO Tester Fio is an advanced disk benchmark that depends upon the kernel's AIO access library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.18 Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory FSGSBASE Patched No FSGSBASE 300 600 900 1200 1500 SE +/- 0.33, N = 3 SE +/- 2.52, N = 3 1407 1408 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.18 Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory FSGSBASE Patched No FSGSBASE 70K 140K 210K 280K 350K SE +/- 333.33, N = 3 318333 319000 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.18 Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory FSGSBASE Patched No FSGSBASE 170 340 510 680 850 SE +/- 3.18, N = 3 SE +/- 3.18, N = 3 766 767 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.18 Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory FSGSBASE Patched No FSGSBASE 50K 100K 150K 200K 250K SE +/- 1732.05, N = 3 226000 234000 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.18 Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory FSGSBASE Patched No FSGSBASE 300 600 900 1200 1500 SE +/- 0.67, N = 3 1401 989 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.18 Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory FSGSBASE Patched No FSGSBASE 120K 240K 360K 480K 600K SE +/- 2962.73, N = 3 SE +/- 881.92, N = 3 541667 457333 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.18 Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory FSGSBASE Patched No FSGSBASE 160 320 480 640 800 SE +/- 3.48, N = 3 SE +/- 7.42, N = 9 758 742 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.18 Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory FSGSBASE Patched No FSGSBASE 60K 120K 180K 240K 300K SE +/- 1333.33, N = 3 SE +/- 333.33, N = 3 297667 294667 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.18 Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory FSGSBASE Patched No FSGSBASE 600 1200 1800 2400 3000 SE +/- 0.67, N = 3 SE +/- 5.17, N = 3 2822 2824 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.18 Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory FSGSBASE Patched No FSGSBASE 300 600 900 1200 1500 SE +/- 1.00, N = 3 1243 1246 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.18 Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory FSGSBASE Patched No FSGSBASE 300 600 900 1200 1500 SE +/- 6.06, N = 3 SE +/- 6.39, N = 3 1539 1541 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.18 Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory FSGSBASE Patched No FSGSBASE 200 400 600 800 1000 SE +/- 2.19, N = 3 SE +/- 7.26, N = 3 882 914 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.18 Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory FSGSBASE Patched No FSGSBASE 600 1200 1800 2400 3000 SE +/- 2.96, N = 3 SE +/- 1.53, N = 3 2810 1985 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.18 Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory FSGSBASE Patched No FSGSBASE 500 1000 1500 2000 2500 SE +/- 11.22, N = 3 SE +/- 3.93, N = 3 2115 1787 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.18 Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory FSGSBASE Patched No FSGSBASE 300 600 900 1200 1500 SE +/- 6.96, N = 3 SE +/- 14.85, N = 9 1524 1491 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.18 Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory FSGSBASE Patched No FSGSBASE 200 400 600 800 1000 SE +/- 4.67, N = 3 SE +/- 2.03, N = 3 1161 1151 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
LevelDB LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Fill Sync FSGSBASE Patched No FSGSBASE 0.1125 0.225 0.3375 0.45 0.5625 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.5 0.5 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Overwrite FSGSBASE Patched No FSGSBASE 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.07, N = 3 10.4 10.4 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Random Fill FSGSBASE Patched No FSGSBASE 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 10.4 10.3 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Sequential Fill FSGSBASE Patched No FSGSBASE 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 10.4 10.3 1. (CXX) g++ options: -O3 -lsnappy -lpthread
Ethr Ethr is a cross-platform Golang-written network performance measurement tool developed by Microsoft that is capable of testing multiple protocols and different measurements. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 1 FSGSBASE Patched No FSGSBASE 60000M 120000M 180000M 240000M 300000M SE +/- 77529684004.71, N = 16 SE +/- 76964082767.76, N = 16 300220508112.72 298018476860.52 MIN: 579.33 / MAX: 618620000000 MIN: 577.15 / MAX: 615170000000
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 64 FSGSBASE Patched No FSGSBASE 50K 100K 150K 200K 250K SE +/- 368.21, N = 3 SE +/- 1852.20, N = 3 247729.11 246089.33 MIN: 235490 / MAX: 262340 MIN: 234100 / MAX: 258070
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 64 FSGSBASE Patched No FSGSBASE 50K 100K 150K 200K 250K SE +/- 269.99, N = 3 SE +/- 204.25, N = 3 218262.89 220315.33 MIN: 213030 / MAX: 223290 MIN: 213770 / MAX: 225390
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 64 FSGSBASE Patched No FSGSBASE 800 1600 2400 3200 4000 SE +/- 19.59, N = 3 SE +/- 41.06, N = 3 3913.13 3900.42 MIN: 3660 / MAX: 4110 MIN: 3540 / MAX: 4170
iPerf iPerf is a network bandwidth throughput testing software. This test profile is used for automated testing of an iperf client and requires you have access to an iperf server. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 1 FSGSBASE Patched No FSGSBASE 8K 16K 24K 32K 40K SE +/- 117.05, N = 3 SE +/- 134.51, N = 3 38073 38424 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 1 FSGSBASE Patched No FSGSBASE 0.2363 0.4726 0.7089 0.9452 1.1815 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.05 1.05 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 64 FSGSBASE Patched No FSGSBASE 8K 16K 24K 32K 40K SE +/- 128.54, N = 3 SE +/- 42.19, N = 3 37246 37287 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 64 FSGSBASE Patched No FSGSBASE 15 30 45 60 75 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 67.1 67.1 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
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 FSGSBASE Patched No FSGSBASE 300K 600K 900K 1200K 1500K SE +/- 17699.32, N = 3 SE +/- 14046.59, N = 3 1414337 1405775 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: Random Read FSGSBASE Patched No FSGSBASE 20M 40M 60M 80M 100M SE +/- 40117.51, N = 3 SE +/- 252410.28, N = 3 93621859 93449392 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 FSGSBASE Patched No FSGSBASE 300K 600K 900K 1200K 1500K SE +/- 15596.22, N = 3 SE +/- 8673.15, N = 3 1546586 1548834 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: Random Fill Sync FSGSBASE Patched No FSGSBASE 1000 2000 3000 4000 5000 SE +/- 7.75, N = 3 SE +/- 41.44, N = 11 4800 4680 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: Read While Writing FSGSBASE Patched No FSGSBASE 900K 1800K 2700K 3600K 4500K SE +/- 19354.09, N = 3 SE +/- 44863.47, N = 8 4118869 4256231 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Get - Connections: 1 FSGSBASE Patched No FSGSBASE 20K 40K 60K 80K 100K SE +/- 354.12, N = 3 SE +/- 920.00, N = 3 110740.0 110410.7 1. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Set - Connections: 1 FSGSBASE Patched No FSGSBASE 13K 26K 39K 52K 65K SE +/- 80.55, N = 3 SE +/- 354.05, N = 3 61558.6 61800.6 1. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Append - Connections: 1 FSGSBASE Patched No FSGSBASE 14K 28K 42K 56K 70K SE +/- 592.68, N = 3 SE +/- 300.54, N = 3 64193.4 65121.9 1. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Delete - Connections: 1 FSGSBASE Patched No FSGSBASE 20K 40K 60K 80K 100K SE +/- 431.94, N = 3 SE +/- 1054.55, N = 3 109298.2 110107.3 1. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Prepend - Connections: 1 FSGSBASE Patched No FSGSBASE 14K 28K 42K 56K 70K SE +/- 69.50, N = 3 SE +/- 148.44, N = 3 64105.6 65190.0 1. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Replace - Connections: 1 FSGSBASE Patched No FSGSBASE 14K 28K 42K 56K 70K SE +/- 155.49, N = 3 SE +/- 319.45, N = 3 64372.7 64752.0 1. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 16 FSGSBASE Patched No FSGSBASE 120 240 360 480 600 SE +/- 2.99, N = 3 SE +/- 1.00, N = 3 558 561 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lnuma -lcrypt -lz -lm -lssl -lcrypto -ldl
OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: SADD FSGSBASE Patched No FSGSBASE 500K 1000K 1500K 2000K 2500K SE +/- 38848.07, N = 3 SE +/- 9544.76, N = 3 2416689.58 2347495.50 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: LPUSH FSGSBASE Patched No FSGSBASE 400K 800K 1200K 1600K 2000K SE +/- 22661.66, N = 3 SE +/- 11389.91, N = 3 1886156.66 1842891.79 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: GET FSGSBASE Patched No FSGSBASE 600K 1200K 1800K 2400K 3000K SE +/- 28244.30, N = 15 SE +/- 24930.64, N = 15 2824129.95 2671484.22 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: SET FSGSBASE Patched No FSGSBASE 500K 1000K 1500K 2000K 2500K SE +/- 12206.81, N = 3 SE +/- 4588.13, N = 3 2249007.50 2279653.67 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
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 FSGSBASE Patched No FSGSBASE 11K 22K 33K 44K 55K SE +/- 99.12, N = 3 SE +/- 117.05, N = 3 52853.85 52790.11 1. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native
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 FSGSBASE Patched No FSGSBASE 7K 14K 21K 28K 35K SE +/- 385.58, N = 4 SE +/- 47.52, N = 3 29409.16 31185.40 1. (CC) gcc options: -shared -fPIC -O2 -pthread
OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.2.3 Test: Random Read - Clients: 32 FSGSBASE Patched No FSGSBASE 40K 80K 120K 160K 200K SE +/- 1029.85, N = 3 SE +/- 1732.82, N = 3 180781 179254
OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.2.3 Test: Random Write - Clients: 32 FSGSBASE Patched No FSGSBASE 50K 100K 150K 200K 250K SE +/- 40722.04, N = 12 SE +/- 29825.95, N = 15 221982 216740
OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.2.3 Test: Sequential Read - Clients: 32 FSGSBASE Patched No FSGSBASE 30K 60K 90K 120K 150K SE +/- 1563.62, N = 3 SE +/- 2099.51, N = 3 135103 131892
OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.2.3 Test: Sequential Write - Clients: 32 FSGSBASE Patched No FSGSBASE 90K 180K 270K 360K 450K SE +/- 6508.07, N = 3 SE +/- 23676.54, N = 6 416177 411805
OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.2.3 Test: Async Random Write - Clients: 32 FSGSBASE Patched No FSGSBASE 9K 18K 27K 36K 45K SE +/- 1782.13, N = 3 SE +/- 973.32, N = 12 41708 38199
PHPBench PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. The number of iterations used is 1,000,000. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite FSGSBASE Patched No FSGSBASE 200K 400K 600K 800K 1000K SE +/- 231.11, N = 3 SE +/- 1234.36, N = 3 788354 789669
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write FSGSBASE Patched No FSGSBASE 2K 4K 6K 8K 10K SE +/- 9.73, N = 3 SE +/- 18.22, N = 3 10214.58 10193.31 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 FSGSBASE Patched No FSGSBASE 100K 200K 300K 400K 500K SE +/- 863.78, N = 3 SE +/- 1245.79, N = 3 479686.72 478581.81 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 FSGSBASE Patched No FSGSBASE 2K 4K 6K 8K 10K SE +/- 170.08, N = 3 SE +/- 16.63, N = 3 11127.26 10834.68 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Intel MPI Benchmarks Intel MPI Benchmarks for stressing MPI implementations. At this point the test profile aggregates results for some common MPI functionality. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Average usec, Fewer Is Better Intel MPI Benchmarks 2019.3 Test: IMB-MPI1 Exchange FSGSBASE Patched No FSGSBASE 80 160 240 320 400 SE +/- 0.76, N = 3 SE +/- 0.38, N = 3 373.67 371.45 MIN: 0.73 / MAX: 7093.23 MIN: 0.73 / MAX: 6963.28 1. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.org Average usec, Fewer Is Better Intel MPI Benchmarks 2019.3 Test: IMB-MPI1 Sendrecv FSGSBASE Patched No FSGSBASE 40 80 120 160 200 SE +/- 0.19, N = 3 SE +/- 0.78, N = 3 178.07 177.83 MIN: 0.53 / MAX: 3411.15 MIN: 0.53 / MAX: 3409.19 1. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
NAMD NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.13 ATPase Simulation - 327,506 Atoms FSGSBASE Patched No FSGSBASE 0.2173 0.4346 0.6519 0.8692 1.0865 SE +/- 0.00236, N = 3 SE +/- 0.00171, N = 3 0.96525 0.96581
OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.2.3 Test: Random Read - Clients: 32 FSGSBASE Patched No FSGSBASE 40 80 120 160 200 SE +/- 0.67, N = 3 SE +/- 1.76, N = 3 173 175
OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.2.3 Test: Random Write - Clients: 32 FSGSBASE Patched No FSGSBASE 50 100 150 200 250 SE +/- 40.08, N = 12 SE +/- 41.03, N = 15 219 214
OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.2.3 Test: Sequential Read - Clients: 32 FSGSBASE Patched No FSGSBASE 50 100 150 200 250 SE +/- 2.60, N = 3 SE +/- 4.10, N = 3 235 241
OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.2.3 Test: Sequential Write - Clients: 32 FSGSBASE Patched No FSGSBASE 20 40 60 80 100 SE +/- 24.34, N = 3 SE +/- 20.20, N = 6 99 111
OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.2.3 Test: Async Random Write - Clients: 32 FSGSBASE Patched No FSGSBASE 200 400 600 800 1000 SE +/- 32.09, N = 3 SE +/- 24.88, N = 12 767 842
LevelDB LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Hot Read FSGSBASE Patched No FSGSBASE 7 14 21 28 35 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 27.52 27.81 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Fill Sync FSGSBASE Patched No FSGSBASE 1600 3200 4800 6400 8000 SE +/- 9.08, N = 3 SE +/- 21.21, N = 3 7451.28 7479.78 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Overwrite FSGSBASE Patched No FSGSBASE 80 160 240 320 400 SE +/- 0.30, N = 3 SE +/- 2.64, N = 3 382.38 383.71 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Fill FSGSBASE Patched No FSGSBASE 80 160 240 320 400 SE +/- 1.11, N = 3 SE +/- 0.73, N = 3 383.91 385.20 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Read FSGSBASE Patched No FSGSBASE 7 14 21 28 35 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 27.60 28.13 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Seek Random FSGSBASE Patched No FSGSBASE 8 16 24 32 40 SE +/- 0.07, N = 3 SE +/- 0.11, N = 3 33.21 33.42 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Delete FSGSBASE Patched No FSGSBASE 80 160 240 320 400 SE +/- 0.16, N = 3 SE +/- 1.04, N = 3 375.33 377.22 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Sequential Fill FSGSBASE Patched No FSGSBASE 80 160 240 320 400 SE +/- 0.69, N = 3 SE +/- 1.13, N = 3 383.36 385.46 1. (CXX) g++ options: -O3 -lsnappy -lpthread
Ethr Ethr is a cross-platform Golang-written network performance measurement tool developed by Microsoft that is capable of testing multiple protocols and different measurements. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Microseconds, Fewer Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 1 FSGSBASE Patched No FSGSBASE 4 8 12 16 20 SE +/- 0.27, N = 3 SE +/- 0.15, N = 3 15.98 15.81 MIN: 11.58 / MAX: 28.5 MIN: 13.15 / MAX: 28.87
OpenBenchmarking.org Microseconds, Fewer Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 64 FSGSBASE Patched No FSGSBASE 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.11, N = 3 15.75 15.68 MIN: 10.9 / MAX: 29.86 MIN: 13.06 / MAX: 28
PyBench This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times FSGSBASE Patched No FSGSBASE 200 400 600 800 1000 SE +/- 1.45, N = 3 SE +/- 0.33, N = 3 889 888
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: 1 FSGSBASE Patched No FSGSBASE 11 22 33 44 55 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 47.37 47.48 1. (CC) gcc options: -O2 -lz -lm -ldl -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.30.1 Threads / Copies: 8 FSGSBASE Patched No FSGSBASE 30 60 90 120 150 SE +/- 0.32, N = 3 SE +/- 0.58, N = 3 156.47 156.05 1. (CC) gcc options: -O2 -lz -lm -ldl -lpthread
YafaRay YafaRay is an open-source physically based montecarlo ray-tracing engine. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better YafaRay 3.4.1 Total Time For Sample Scene FSGSBASE Patched No FSGSBASE 30 60 90 120 150 SE +/- 13.41, N = 12 SE +/- 1.66, N = 3 119.54 104.29 1. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lpthread
Git This test measures the time needed to carry out some sample Git operations on an example, static repository that happens to be a copy of the GNOME GTK tool-kit repository. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Git Time To Complete Common Git Commands FSGSBASE Patched No FSGSBASE 11 22 33 44 55 SE +/- 0.06, N = 3 SE +/- 0.13, N = 3 48.47 48.47 1. git version 2.25.1
FSGSBASE Patched Compiler Notes: --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 -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500012cJava Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-3ubuntu1)Python Notes: + Python 3.8.2Security 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 10 May 2020 15:15 by user system.
No FSGSBASE Processor: Intel Core i9-10980XE @ 4.80GHz (18 Cores / 36 Threads), Motherboard: ASRock X299 Steel Legend (P1.30 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 32GB, Disk: Samsung SSD 970 PRO 512GB, Graphics: NVIDIA NV132 11GB, Audio: Realtek ALC1220, Monitor: ASUS MG28U, Network: Intel I219-V + Intel I211
OS: Ubuntu 20.04, Kernel: 5.7.0-rc4-fsgsbase (x86_64) 20200510, Desktop: GNOME Shell 3.36.1, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.3 Mesa 20.0.4, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160
Compiler Notes: --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 -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500012cJava Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-3ubuntu1)Python Notes: + Python 3.8.2Security 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 11 May 2020 06:15 by user system.