LVI Mitigations

Intel Xeon E3-1275 v6 testing with a ASUS P10S-M WS (4401 BIOS) and Intel HD P630 on Ubuntu 20.04 via the Phoronix Test Suite for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2003126-NI-LVIMITIGA83&sro&gru.

LVI MitigationsProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverCompilerFile-SystemScreen ResolutionNo LVI MitigationLFENCE Before Indirect BranchLFENCE Before RETLFENCE After LoadLFENCE Load + Indirect Branch + RetIntel Xeon E3-1275 v6 @ 4.20GHz (4 Cores / 8 Threads)ASUS P10S-M WS (4401 BIOS)Intel Xeon E3-1200 v6/7th16GBSamsung SSD 970 EVO Plus 500GBIntel HD P630 (1150MHz)Realtek ALC1150DELL S2409W2 x Intel I210Ubuntu 20.045.4.0-14-generic (x86_64)GNOME Shell 3.35.91X Server 1.20.7modesetting 1.20.7GCC 9.2.1 20200304ext41920x1080OpenBenchmarking.orgEnvironment Details- No LVI Mitigation: CXXFLAGS=-O3 CFLAGS=-O3- LFENCE Before Indirect Branch: CXXFLAGS="-O3 -Wa,-mlfence-before-indirect-branch=all" CFLAGS="-O3 -Wa,-mlfence-before-indirect-branch=all"- LFENCE Before RET: CXXFLAGS="-O3 -Wa,-mlfence-before-ret=or" CFLAGS="-O3 -Wa,-mlfence-before-ret=or"- LFENCE After Load: CXXFLAGS="-O3 -Wa,-mlfence-after-load=yes" CFLAGS="-O3 -Wa,-mlfence-after-load=yes"- LFENCE Load + Indirect Branch + Ret: CXXFLAGS="-O3 -Wa,-mlfence-after-load=yes -Wa,-mlfence-before-indirect-branch=all -Wa,-mlfence-before-ret=or" CFLAGS="-O3 -Wa,-mlfence-after-load=yes -Wa,-mlfence-before-indirect-branch=all -Wa,-mlfence-before-ret=or" 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 Processor Details- Scaling Governor: intel_pstate powersave - CPU Microcode: 0xcaSecurity Details- itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable

LVI Mitigationssysbench: CPUdav1d: Summer Nature 1080psvt-av1: Enc Mode 8 - 1080psvt-hevc: 1080p 8-bit YUV To HEVC Video Encodevpxenc: Speed 5x264: H.264 Video Encodingmt-dgemm: Sustained Floating-Point Rategraphics-magick: Rotategraphics-magick: Resizingcoremark: CoreMark Size 666 - Iterations Per Secondleveldb: Fill Syncipc-benchmark: Unnamed Pipe - 2048ipc-benchmark: FIFO Named Pipe - 2048fftw: Float + SSE - 2D FFT Size 128himeno: Poisson Pressure Solverbotan: KASUMIbotan: AES-256botan: Twofishbotan: Blowfishbotan: CAST-256smhasher: wyhashsmhasher: fasthash32smhasher: t1ha0_aes_avx2lammps: Rhodopsin Proteinrocksdb: Read While Writingmcperf: Add - 1mcperf: Get - 1mcperf: Set - 1mcperf: Add - 16john-the-ripper: Blowfishjohn-the-ripper: MD5redis: GETopenssl: RSA 4096-bit Performancepgbench: Buffer Test - Normal Load - Read Onlypgbench: Buffer Test - Normal Load - Read Writesmhasher: wyhashsmhasher: fasthash32smhasher: t1ha0_aes_avx2leveldb: Hot Readleveldb: Fill Syncleveldb: Rand Readleveldb: Seek Randmrbayes: Primate Phylogeny Analysishmmer: Pfam Database Searchc-ray: Total Time - 4K, 16 Rays Per Pixelencode-flac: WAV To FLACencode-mp3: WAV To MP3No LVI MitigationLFENCE Before Indirect BranchLFENCE Before RETLFENCE After LoadLFENCE Load + Indirect Branch + Ret8863.9974281.0713.84124.4123.8644.541.121684735437155734.92712415203611482097362073504.38217494.5344027.591364.617450.387143.94015371.586302.8839576.773.05492584974622.1126791.274530.774588.577034383592902781.851217.6109133.8349476337.39772630.8739.97340.4063.4386078.9533.4694.58180.0945.172160.7528.9228.6418482.7413279.9213.58023.8323.7043.591.125063720435155387.1929670.115015881442004345693495.06565594.5564012.193365.472455.182143.74215139.166305.0039743.373.09190142773822.3122542.873056.177044507302807336.751217.5107867.8723276489.71745144.59471.41647.8093.5356172.7603.4584.67081.2665.190160.7408.8798.7008475.1843273.7312.15621.2820.3241.301.134689688435150838.3881760.114756471458219331093502.53896594.3153548.671361.857449.685143.33615368.406301.2540155.932.99989980572552.0125504.072700.472514.576324421282964800.421214.9101653.3291486622.93502848.44692.46073.1343.8336140.0123.8005.34386.7295.778161.2329.0069.3819160.575285.952.1693.882.6310.810.1991131626530075.832607150678914822063179.7182.68075911.961656.42623.66127.04113.7861459.641108.632536.980.27591167169923.1112679.369868.970035.3646924572290110.92138.149296.6619285470.214751183.606158.320100.1425.5576279.4065.56110.540861.63530.0261234.59197.94176.7279160.685285.042.1333.792.5910.590.1968991656529308.801462145444212815223147.0182.68520811.947667.16323.62627.03613.8431460.061108.262578.170.27590437569416.7108597.868935.869368.6646923522157109.92138.145420.1824225255.447869199.766205.397129.6325.7466343.5905.79410.963865.29530.0581235.08297.73277.149OpenBenchmarking.org

Sysbench

Test: CPU

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 2018-07-28Test: CPULFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation2K4K6K8K10KSE +/- 0.95, N = 3SE +/- 0.77, N = 3SE +/- 1.05, N = 3SE +/- 0.43, N = 3SE +/- 0.57, N = 39160.588482.748475.189160.698864.001. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=core2 -rdynamic -ldl -laio -lm

dav1d

Video Input: Summer Nature 1080p

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.6.0Video Input: Summer Nature 1080pLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation60120180240300SE +/- 0.04, N = 3SE +/- 0.43, N = 3SE +/- 0.44, N = 3SE +/- 0.06, N = 3SE +/- 0.44, N = 385.95279.92273.7385.04281.07MIN: 78.9 / MAX: 97.75MIN: 254.67 / MAX: 306.05MIN: 248.49 / MAX: 298.86MIN: 78.13 / MAX: 96.33MIN: 263 / MAX: 305.721. (CC) gcc options: -O3 -pthread

SVT-AV1

Encoder Mode: Enc Mode 8 - Input: 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation48121620SE +/- 0.003, N = 3SE +/- 0.015, N = 3SE +/- 0.020, N = 3SE +/- 0.001, N = 3SE +/- 0.012, N = 32.16913.58012.1562.13313.8411. (CXX) g++ options: -O3 -fPIE -fPIC -pie

SVT-HEVC

1080p 8-bit YUV To HEVC Video Encode

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.4.11080p 8-bit YUV To HEVC Video EncodeLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation612182430SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 33.8823.8321.283.7924.411. (CC) gcc options: -O3 -fPIE -fPIC -O2 -pie -rdynamic -lpthread -lrt

VP9 libvpx Encoding

Speed: Speed 5

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.2Speed: Speed 5LFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation612182430SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 32.6323.7020.322.5923.861. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11

x264

H.264 Video Encoding

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2019-12-17H.264 Video EncodingLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation1020304050SE +/- 0.01, N = 3SE +/- 0.28, N = 3SE +/- 0.11, N = 3SE +/- 0.02, N = 3SE +/- 0.49, N = 310.8143.5941.3010.5944.541. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

ACES DGEMM

Sustained Floating-Point Rate

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation0.25530.51060.76591.02121.2765SE +/- 0.000251, N = 3SE +/- 0.009027, N = 3SE +/- 0.011024, N = 3SE +/- 0.001089, N = 3SE +/- 0.009404, N = 30.1991131.1250631.1346890.1968991.1216841. (CC) gcc options: -O3 -march=native -fopenmp

GraphicsMagick

Operation: Rotate

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: RotateLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation160320480640800SE +/- 8.62, N = 3SE +/- 1.00, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 31627206881657351. (CC) gcc options: -fopenmp -O3 -pthread -ljpeg -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Resizing

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: ResizingLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation90180270360450SE +/- 1.73, N = 365435435654371. (CC) gcc options: -fopenmp -O3 -pthread -ljpeg -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread

Coremark

CoreMark Size 666 - Iterations Per Second

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation30K60K90K120K150KSE +/- 15.75, N = 3SE +/- 406.60, N = 3SE +/- 696.48, N = 3SE +/- 3.16, N = 3SE +/- 594.80, N = 330075.83155387.19150838.3929308.80155734.931. (CC) gcc options: -O2 -O3 -lrt" -lrt

LevelDB

Benchmark: Fill Sync

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Fill SyncLFENCE Before Indirect BranchLFENCE Before RET0.02250.0450.06750.090.1125SE +/- 0.00, N = 3SE +/- 0.01, N = 150.10.11. (CXX) g++ options: -O3 -lsnappy -lpthread

IPC_benchmark

Type: Unnamed Pipe - Message Bytes: 2048

OpenBenchmarking.orgMessages Per Second, More Is BetterIPC_benchmarkType: Unnamed Pipe - Message Bytes: 2048LFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation300K600K900K1200K1500KSE +/- 5934.66, N = 3SE +/- 14185.23, N = 10SE +/- 22792.63, N = 13SE +/- 24328.97, N = 15SE +/- 23319.71, N = 315067891501588147564714544421520361

IPC_benchmark

Type: FIFO Named Pipe - Message Bytes: 2048

OpenBenchmarking.orgMessages Per Second, More Is BetterIPC_benchmarkType: FIFO Named Pipe - Message Bytes: 2048LFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation300K600K900K1200K1500KSE +/- 23424.58, N = 3SE +/- 6206.38, N = 3SE +/- 22765.74, N = 3SE +/- 15759.80, N = 3SE +/- 6688.93, N = 314822061442004145821912815221482097

FFTW

Build: Float + SSE - Size: 2D FFT Size 128

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 128LFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation8K16K24K32K40KSE +/- 2.37, N = 3SE +/- 335.87, N = 3SE +/- 402.02, N = 6SE +/- 5.21, N = 3SE +/- 457.98, N = 33179.734569.033109.03147.036207.01. (CC) gcc options: -pthread -O3 -lm

Himeno Benchmark

Poisson Pressure Solver

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation8001600240032004000SE +/- 0.04, N = 3SE +/- 2.74, N = 3SE +/- 2.71, N = 3SE +/- 0.03, N = 3SE +/- 8.50, N = 3182.683495.073502.54182.693504.381. (CC) gcc options: -O3 -mavx2

Botan

Test: KASUMI

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: KASUMILFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation20406080100SE +/- 0.00, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 311.9694.5694.3211.9594.531. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Botan

Test: AES-256

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: AES-256LFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation9001800270036004500SE +/- 0.42, N = 3SE +/- 0.68, N = 3SE +/- 0.17, N = 3SE +/- 0.03, N = 3SE +/- 3.22, N = 3656.434012.193548.67667.164027.591. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Botan

Test: Twofish

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: TwofishLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation80160240320400SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.26, N = 3SE +/- 0.02, N = 3SE +/- 0.27, N = 323.66365.47361.8623.63364.621. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Botan

Test: Blowfish

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: BlowfishLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation100200300400500SE +/- 0.00, N = 3SE +/- 0.10, N = 3SE +/- 0.09, N = 3SE +/- 0.00, N = 3SE +/- 4.11, N = 327.04455.18449.6927.04450.391. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Botan

Test: CAST-256

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: CAST-256LFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation306090120150SE +/- 0.01, N = 3SE +/- 0.21, N = 3SE +/- 0.06, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 313.79143.74143.3413.84143.941. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

SMHasher

Hash: wyhash

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: wyhashLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation3K6K9K12K15KSE +/- 0.34, N = 3SE +/- 172.83, N = 3SE +/- 61.62, N = 3SE +/- 0.18, N = 3SE +/- 91.45, N = 31459.6415139.1615368.401460.0615371.581. (CXX) g++ options: -O3 -march=native -lpthread

SMHasher

Hash: fasthash32

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: fasthash32LFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation14002800420056007000SE +/- 0.06, N = 3SE +/- 2.33, N = 3SE +/- 2.59, N = 3SE +/- 0.06, N = 3SE +/- 4.58, N = 31108.636305.006301.251108.266302.881. (CXX) g++ options: -O3 -march=native -lpthread

SMHasher

Hash: t1ha0_aes_avx2

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: t1ha0_aes_avx2LFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation9K18K27K36K45KSE +/- 0.19, N = 3SE +/- 549.98, N = 4SE +/- 280.18, N = 3SE +/- 1.85, N = 3SE +/- 278.78, N = 32536.9839743.3740155.932578.1739576.771. (CXX) g++ options: -O3 -march=native -lpthread

LAMMPS Molecular Dynamics Simulator

Model: Rhodopsin Protein

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 9Jan2020Model: Rhodopsin ProteinLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation0.69551.3912.08652.7823.4775SE +/- 0.000, N = 3SE +/- 0.005, N = 3SE +/- 0.004, N = 3SE +/- 0.001, N = 3SE +/- 0.006, N = 30.2753.0912.9990.2753.0541. (CXX) g++ options: -O3 -rdynamic -ljpeg -lfftw3 -lm

Facebook RocksDB

Test: Read While Writing

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Read While WritingLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation200K400K600K800K1000KSE +/- 6024.37, N = 3SE +/- 6920.01, N = 3SE +/- 10108.45, N = 3SE +/- 1624.30, N = 3SE +/- 14182.06, N = 39116719014278998059043759258491. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Memcached mcperf

Method: Add - Connections: 1

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Add - Connections: 1LFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation16K32K48K64K80KSE +/- 120.28, N = 3SE +/- 230.88, N = 3SE +/- 475.38, N = 3SE +/- 115.20, N = 3SE +/- 110.28, N = 369923.173822.372552.069416.774622.11. (CC) gcc options: -O3 -lm -rdynamic

Memcached mcperf

Method: Get - Connections: 1

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Get - Connections: 1LFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation30K60K90K120K150KSE +/- 613.45, N = 3SE +/- 188.33, N = 3SE +/- 529.02, N = 3SE +/- 214.95, N = 3SE +/- 1437.67, N = 3112679.3122542.8125504.0108597.8126791.21. (CC) gcc options: -O3 -lm -rdynamic

Memcached mcperf

Method: Set - Connections: 1

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Set - Connections: 1LFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation16K32K48K64K80KSE +/- 157.67, N = 3SE +/- 149.20, N = 3SE +/- 129.57, N = 3SE +/- 383.89, N = 3SE +/- 403.77, N = 369868.973056.172700.468935.874530.71. (CC) gcc options: -O3 -lm -rdynamic

Memcached mcperf

Method: Add - Connections: 16

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Add - Connections: 16LFENCE After LoadLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation16K32K48K64K80KSE +/- 120.20, N = 3SE +/- 114.33, N = 3SE +/- 85.00, N = 3SE +/- 293.57, N = 370035.372514.569368.674588.51. (CC) gcc options: -O3 -lm -rdynamic

John The Ripper

Test: Blowfish

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: BlowfishLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation17003400510068008500SE +/- 0.88, N = 3SE +/- 1.45, N = 36467704763264677031. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -pthread -lm -lz -ldl -lcrypt -lbz2

John The Ripper

Test: MD5

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: MD5LFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation100K200K300K400K500KSE +/- 10.33, N = 3SE +/- 90.21, N = 3SE +/- 520.74, N = 3SE +/- 6.67, N = 3SE +/- 42.78, N = 392457450730442128923524383591. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -pthread -lm -lz -ldl -lcrypt -lbz2

Redis

Test: GET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: GETLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation600K1200K1800K2400K3000KSE +/- 6290.25, N = 3SE +/- 37253.75, N = 3SE +/- 23623.92, N = 3SE +/- 20411.81, N = 3SE +/- 33984.11, N = 152290110.922807336.752964800.422157109.922902781.851. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

OpenSSL

RSA 4096-bit Performance

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit PerformanceLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation30060090012001500SE +/- 0.00, N = 3SE +/- 0.63, N = 3SE +/- 0.70, N = 3SE +/- 0.00, N = 3SE +/- 1.65, N = 3138.11217.51214.9138.11217.61. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

PostgreSQL pgbench

Scaling: Buffer Test - Test: Normal Load - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read OnlyLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation20K40K60K80K100KSE +/- 54.85, N = 3SE +/- 95.59, N = 3SE +/- 196.17, N = 3SE +/- 47.38, N = 3SE +/- 413.63, N = 349296.66107867.87101653.3345420.18109133.831. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

PostgreSQL pgbench

Scaling: Buffer Test - Test: Normal Load - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read WriteLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation14002800420056007000SE +/- 19.12, N = 3SE +/- 42.83, N = 3SE +/- 98.41, N = 3SE +/- 71.67, N = 3SE +/- 63.09, N = 155470.216489.726622.945255.456337.401. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

SMHasher

Hash: wyhash

OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: wyhashLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation4080120160200SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3183.6144.5948.45199.7730.871. (CXX) g++ options: -O3 -march=native -lpthread

SMHasher

Hash: fasthash32

OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: fasthash32LFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation50100150200250SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3158.3271.4292.46205.4039.971. (CXX) g++ options: -O3 -march=native -lpthread

SMHasher

Hash: t1ha0_aes_avx2

OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: t1ha0_aes_avx2LFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation306090120150SE +/- 0.45, N = 3SE +/- 0.01, N = 4SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3100.1447.8173.13129.6340.411. (CXX) g++ options: -O3 -march=native -lpthread

LevelDB

Benchmark: Hot Read

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot ReadLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation1.29292.58583.87875.17166.4645SE +/- 0.011, N = 3SE +/- 0.029, N = 3SE +/- 0.016, N = 3SE +/- 0.011, N = 3SE +/- 0.010, N = 35.5573.5353.8335.7463.4381. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Fill Sync

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Fill SyncLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation14002800420056007000SE +/- 121.57, N = 15SE +/- 26.04, N = 3SE +/- 102.63, N = 15SE +/- 9.49, N = 3SE +/- 114.30, N = 36279.416172.766140.016343.596078.951. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Random Read

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random ReadLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation1.30372.60743.91115.21486.5185SE +/- 0.001, N = 3SE +/- 0.034, N = 3SE +/- 0.036, N = 3SE +/- 0.007, N = 3SE +/- 0.003, N = 35.5613.4583.8005.7943.4691. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Seek Random

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Seek RandomLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation3691215SE +/- 0.039, N = 3SE +/- 0.034, N = 3SE +/- 0.045, N = 3SE +/- 0.039, N = 3SE +/- 0.013, N = 310.5404.6705.34310.9634.5811. (CXX) g++ options: -O3 -lsnappy -lpthread

Timed MrBayes Analysis

Primate Phylogeny Analysis

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny AnalysisLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation2004006008001000SE +/- 0.18, N = 3SE +/- 1.31, N = 3SE +/- 0.06, N = 3SE +/- 0.22, N = 3SE +/- 0.03, N = 3861.6481.2786.73865.3080.091. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mmpx -mabm -O3 -std=c99 -pedantic -lm

Timed HMMer Search

Pfam Database Search

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 2.3.2Pfam Database SearchLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation714212835SE +/- 0.079, N = 3SE +/- 0.020, N = 3SE +/- 0.053, N = 3SE +/- 0.047, N = 3SE +/- 0.005, N = 330.0265.1905.77830.0585.1721. (CC) gcc options: -O3 -pthread -lhmmer -lsquid -lm

C-Ray

Total Time - 4K, 16 Rays Per Pixel

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation30060090012001500SE +/- 0.56, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.84, N = 3SE +/- 0.06, N = 31234.59160.74161.231235.08160.751. (CC) gcc options: -lm -lpthread -O3

FLAC Audio Encoding

WAV To FLAC

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLACLFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation20406080100SE +/- 0.094, N = 5SE +/- 0.008, N = 5SE +/- 0.005, N = 5SE +/- 0.023, N = 5SE +/- 0.004, N = 597.9418.8799.00697.7328.9221. (CXX) g++ options: -O3 -fvisibility=hidden -lm

LAME MP3 Encoding

WAV To MP3

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3LFENCE After LoadLFENCE Before Indirect BranchLFENCE Before RETLFENCE Load + Indirect Branch + RetNo LVI Mitigation20406080100SE +/- 0.005, N = 3SE +/- 0.003, N = 3SE +/- 0.001, N = 3SE +/- 0.016, N = 3SE +/- 0.004, N = 376.7278.7009.38177.1498.6411. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lncurses -lm

Phoronix Test Suite v10.8.5